Paper Citation Record · LEDGER

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering

As of 19 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 4 inbound Pith citation observations for arXiv:2504.14492.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2504.14492 v2

Coverage vector

measured 86 of 86 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T11:54:00.230462Z

measured 90 of 90 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:12:59.059412Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-05-25T05:36:40.383162Z

Reference resolution

86 of 86 outbound references displayed

verified exact4
verified fuzzy0
unresolved82
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation bcdde4b1-3007-48c0-ba78-0b7861a0901e · outbound

This paper cites GPT-4 Technical Report.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.137097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5be6675-60db-4022-bcf5-54060a558f8f · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.149422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d671a6f3-3381-4a2c-8065-9a6742733a7c · outbound

This paper cites BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.158646Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6029b2e4-1c35-4e7c-ad99-340165e8664d · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Refusal in Language Models Is Mediated by a Single Direction

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.168615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 364cbe21-0021-4d2f-bee2-9c2d9194ba23 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.179944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b910985b-247d-4efa-9d68-1e124c9e0290 · outbound

This paper cites DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.193531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 855ad296-cefe-4bda-92e3-67262794066e · outbound

This paper cites Learnable Privacy Neurons Localization in Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Learnable Privacy Neurons Localization in Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.205574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42a29f74-6bc7-4656-9525-e80357490ab5 · outbound

This paper cites Identifying and Mitigating Social Bias Knowledge in Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Identifying and Mitigating Social Bias Knowledge in Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.220387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a29f94d6-61c7-46a7-b74f-9d2dc64c41ce · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.236138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dee8169-00d8-489a-96ad-be445796a3d6 · outbound

This paper cites PAD: Personalized Alignment of LLMs at Decoding-Time.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering PAD: Personalized Alignment of LLMs at Decoding-Time

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.243501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87446892-17a4-4a21-add1-9547e49cf46c · outbound

This paper cites FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.256067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 265d5ee5-99db-4c42-b23a-07427147d15a · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.265653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93035524-3c2d-4e95-9f45-cfeb40ce6a99 · outbound

This paper cites Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Increasing Diversity While Maintaining Accuracy: Text Data Generation with Large Language Models and Human Interventions

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.276264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ee2ea29-1285-41bf-ba1f-de745e7e8b68 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.287532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eb61449-3a67-4d6a-ba4a-467908b7c9c7 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.298486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92810b9-c756-4617-adec-9bf11965c7e3 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.321448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71f2d8c8-d71f-4bb1-ab78-c18054c2e863 · outbound

This paper cites Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Co$^2$PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:54:02.830824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5c04aba1-59bd-4fb5-a7ec-c356c95848ec · outbound

This paper cites Toy Models of Superposition.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Toy Models of Superposition

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.361194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88b051bc-6481-4524-b445-30c5f33544d8 · outbound

This paper cites FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.372470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2329fd3d-c3f3-4ec0-8ae3-b3682ce40663 · outbound

This paper cites BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering BiasAlert: A Plug-and-play Tool for Social Bias Detection in LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.393537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d372cba0-8155-4795-b6ee-d1a7a5718349 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:04.215388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 3aeb11e7-56c1-4977-8039-5ce9990f1cf7 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:04.140195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4967e6da-b101-46a0-abe7-0deeb639efae · outbound

This paper cites Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.437570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1627e8f8-9081-4419-a8f0-6c2a5e4599fb · outbound

This paper cites Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.447640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2590f0d5-55d9-4c3c-862a-487d0bf58963 · outbound

This paper cites Diverse Adversaries for Mitigating Bias in Training.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Diverse Adversaries for Mitigating Bias in Training

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:54:02.517915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 01545454-2b39-400c-9958-272a29ee5adb · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:04.112470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7532c959-964d-4261-8b4c-f50f05cff7f2 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Measuring Massive Multitask Language Understanding

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.485579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14c08e5b-c13a-454a-a42f-580ff8569332 · outbound

This paper cites Social Biases in NLP Models as Barriers for Persons with Disabilities.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Social Biases in NLP Models as Barriers for Persons with Disabilities

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.495009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08a5e698-4946-40ca-a3b3-c795f01c417d · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.502376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1e742c3-2b47-4012-bc65-044efaa10634 · outbound

This paper cites Mistral 7B.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Mistral 7B

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.513820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd82f866-0123-4595-a3e5-4b30f6f0f621 · outbound

This paper cites On the Origins of Linear Representations in Large Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering On the Origins of Linear Representations in Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.525452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 165a27b6-d288-47a8-bd00-09e1feb1ee7e · outbound

This paper cites On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:54:02.277389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 23aaf3b0-e127-4f5f-b931-3f19537920c4 · outbound

This paper cites Critic-Guided Decoding for Controlled Text Generation.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Critic-Guided Decoding for Controlled Text Generation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.548759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe29ac95-d21b-4706-a90a-840984c2d467 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.559033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 406601f7-2d47-48c7-80f2-4a5dc287748b · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.566437Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b9a788b-c372-494d-9ae8-57c4d0f07923 · outbound

This paper cites UnQovering Stereotyping Biases via Underspecified Questions.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering UnQovering Stereotyping Biases via Underspecified Questions

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.589444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ceb0468c-ddf6-46d1-a898-2e8c1c84dae3 · outbound

This paper cites Towards Debiasing Sentence Representations.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Towards Debiasing Sentence Representations

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.603548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6774030b-3d68-4452-a88f-6506404ef188 · outbound

This paper cites Debiasing Algorithm through Model Adaptation.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Debiasing Algorithm through Model Adaptation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.609648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57fc15ea-ce3c-4c75-be07-8addd43b4c40 · outbound

This paper cites DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.620618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3abd41-a8c1-4f0c-900b-f55b94d36c40 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 40

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:04.029010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4071f3e8-4d22-4ed5-a70c-d370bde9a4a2 · outbound

This paper cites BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.658361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e49d3ec-9ee8-42a0-a078-982b5417ac33 · outbound

This paper cites The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Pre-trained Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.672465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9876f04-7f08-4852-871b-e6775236e6be · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:04.000278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e92b0c4a-5698-4ccd-95de-2417fecc30a6 · outbound

This paper cites NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.719022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b725b2b-7864-4862-9cd0-7ca333bf1fe1 · outbound

This paper cites Language Models are Few-Shot Learners.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Language Models are Few-Shot Learners

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.729267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18b6c45c-0369-4ea3-bdbb-1c96966a1e90 · outbound

This paper cites It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.745926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fd70da0-0d97-4d86-ad5d-4f2b6f863995 · outbound

This paper cites Using In-Context Learning to Improve Dialogue Safety.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Using In-Context Learning to Improve Dialogue Safety

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.753133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c514bb08-21e2-4619-a3d2-7af27ae00f37 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 48

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.977138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 615ab022-3dd3-4248-b0bf-d4d7f5fddc4c · outbound

This paper cites Pointer Sentinel Mixture Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Pointer Sentinel Mixture Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.778084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85be979d-254b-4d19-936d-48ba65bdfeea · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.789139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92136935-c3a2-494b-b0d8-867cc0137979 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 51

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.947305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8225761b-51d6-4fa0-a9f5-62022ac26cb3 · outbound

This paper cites CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.815517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3eb442f-f8a0-4a67-b2a6-8dbc43564d0c · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.826343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22dd4900-da96-49b3-b38a-360f026b1b54 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.876681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e4c27958-de40-41f7-a60c-202b9bd5dc5f · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.840362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f522dd67-f386-4ddf-85d9-87f8a3f229a1 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.857921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 512463f3-cb2c-4e9c-9f74-09aeb58ee387 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Steering Llama 2 via Contrastive Activation Addition

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.872302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4e09fe3-3331-42be-8b06-9027746e4b8f · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.879404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52fff505-8709-4a25-99d8-8367ad7dc94a · outbound

This paper cites BBQ: A Hand-Built Bias Benchmark for Question Answering.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering BBQ: A Hand-Built Bias Benchmark for Question Answering

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.889404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6857142f-932b-430a-96db-d2a880acf9be · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.897721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 480119d3-8f87-4cab-8b7a-4afa7fb54bd5 · outbound

This paper cites Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.910681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4588d3-f301-4007-abd4-445ff183dea2 · outbound

This paper cites First the worst: Finding better gender translations during beam search.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering First the worst: Finding better gender translations during beam search

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.924376Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b4d514b-51f7-4676-8900-f79500fae720 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.935631Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b42cb274-03a6-45fc-9868-12635938e047 · outbound

This paper cites The Woman Worked as a Babysitter: On Biases in Language Generation.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering The Woman Worked as a Babysitter: On Biases in Language Generation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.941617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf17d77b-229f-496f-999c-6dec415d5554 · outbound

This paper cites "Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering "Nice Try, Kiddo": Investigating Ad Hominems in Dialogue Responses

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-08-16T11:54:01.196847Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e2b36b66-9e59-4876-be22-4fb7cf2814be · outbound

This paper cites Societal Biases in Language Generation: Progress and Challenges.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Societal Biases in Language Generation: Progress and Challenges

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.960310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71175a39-9233-4dc5-99f8-e0f71ba2c155 · outbound

This paper cites Prompting GPT-3 To Be Reliable.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Prompting GPT-3 To Be Reliable

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.970159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88f146c5-9e2d-463c-8949-b92adc5805ba · outbound

This paper cites Does Representation Matter? Exploring Intermediate Layers in Large Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Does Representation Matter? Exploring Intermediate Layers in Large Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.982612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71a4601f-4497-4a9f-b69b-96758386f275 · outbound

This paper cites "I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering "I'm sorry to hear that": Finding New Biases in Language Models with a Holistic Descriptor Dataset

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.989339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf510eb-e37b-4453-92cf-3eb158dd4a59 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-16T11:53:59.998714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61307ccf-3422-4e3b-9746-df549be7287b · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.691353Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 412fc57b-34c0-4260-8d03-3a05a7ade03f · outbound

This paper cites Linear Representations of Sentiment in Large Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Linear Representations of Sentiment in Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.039753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3871eec4-db93-402d-83e1-915d141f07d2 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering LLaMA: Open and Efficient Foundation Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.054825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddd2a9ac-a4ad-43de-b616-e7dfa802dfe4 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.067711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13fd75c9-2256-4d0b-80b1-0d12ba9f6319 · outbound

This paper cites A Language Model's Guide Through Latent Space.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering A Language Model's Guide Through Latent Space

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.078545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6f95930-2188-47c5-a9e1-80f52c1994a5 · outbound

This paper cites CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering CEB: Compositional Evaluation Benchmark for Fairness in Large Language Models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.099707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1574066-9843-41e3-b5c3-a325a8a91506 · outbound

This paper cites Measuring and Reducing Gendered Correlations in Pre-trained Models.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Measuring and Reducing Gendered Correlations in Pre-trained Models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.110702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2b15f66-1867-4f15-9254-6796506e70bd · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.612487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e18352bd-9234-4d26-bdf2-564e1dd9e05b · outbound

This paper cites Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.136014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eda39a06-aa90-40b5-bdce-eb03a094fea9 · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.546835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a1f0b380-6771-414d-b6d5-fab86889e57e · outbound

This paper cites an unresolved cited work.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Unresolved cited work

Reference 81

Resolution: unresolved; raw_fallback, observed 2026-08-16T11:54:03.488144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f3c638d8-bc9b-442d-bf52-0f04026f3655 · outbound

This paper cites Gender Bias in Contextualized Word Embeddings.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Gender Bias in Contextualized Word Embeddings

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.168313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93cdae8c-1584-47dc-8930-a98efeba1d0d · outbound

This paper cites Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.175765Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 873f273a-a332-486c-b375-86ca32f02518 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.187771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5da907af-8566-4635-93a5-76f35c74f44c · outbound

This paper cites online" 'onlinestring :=.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering online" 'onlinestring :=

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.208598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 333a8d13-38a0-4667-836a-8395a7e506d5 · outbound

This paper cites write newline.

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering write newline

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-16T11:54:00.230462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b0389be1-d2c8-4a46-8efb-dfe0389321ab · inbound

BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models cites this paper.

BiasGuard: A Reasoning-enhanced Bias Detection Tool For Large Language Models FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-16T05:12:59.059412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 285fd62e-05cf-450c-957e-e1a73c13d77d · inbound

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models cites this paper.

BiasFilter: An Inference-Time Debiasing Framework for Large Language Models FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T13:21:29.077373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b200a2c-384b-49ae-89d0-0832808ec693 · inbound

Detection, Classification, and Mitigation of Gender Bias in Large Language Models cites this paper.

Detection, Classification, and Mitigation of Gender Bias in Large Language Models FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:51:07.518316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9ec87f0-9921-47f9-8cec-c4297020a915 · inbound

Steered Generation via Gradient-Based Optimization on Sparse Query Features cites this paper.

Steered Generation via Gradient-Based Optimization on Sparse Query Features FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-25T05:36:40.385475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.