Paper Citation Record · LEDGER

Mitigating the Alignment Tax of RLHF

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 23 inbound Pith citation observations for arXiv:2309.06256.

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

pith.paper-citation-record.v1
2309.06256 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 23 of 23 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 23 of 23 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T18:11:28.144815Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

9
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 7f479c68-b81b-4744-8438-a6a7a5cf0883 · inbound

Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial? cites this paper.

Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial? Mitigating the Alignment Tax of RLHF

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T18:11:28.144815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c608ac-143c-4e23-8001-10d4687a0371 · inbound

Compromising Honesty and Harmlessness in Language Models via Deception Attacks cites this paper.

Compromising Honesty and Harmlessness in Language Models via Deception Attacks Mitigating the Alignment Tax of RLHF

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-08T05:42:43.505543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02b76a65-7a54-43de-9bbc-5c7ad1d15192 · inbound

ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects cites this paper.

ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects Mitigating the Alignment Tax of RLHF

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:03.062616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68814b27-f0a7-4b71-bc79-75bc0a926d01 · inbound

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods cites this paper.

Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods Mitigating the Alignment Tax of RLHF

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T11:40:09.918152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b1f0d2a-e239-4670-9539-70369bca1236 · inbound

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary cites this paper.

Bradley-Terry and Multi-Objective Reward Modeling Are Complementary Mitigating the Alignment Tax of RLHF

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T18:51:31.112415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf35a2c0-128f-4efe-90fa-6dd0c16c0c5a · inbound

Cycle Context Verification for In-Context Medical Image Segmentation cites this paper.

Cycle Context Verification for In-Context Medical Image Segmentation Mitigating the Alignment Tax of RLHF

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:50.745763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46881b43-642c-4772-b5c1-270725d1f111 · inbound

A comprehensive taxonomy of hallucinations in Large Language Models cites this paper.

A comprehensive taxonomy of hallucinations in Large Language Models Mitigating the Alignment Tax of RLHF

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T05:29:14.879078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 652a0f17-da08-49ed-a08c-15566b8bdf03 · inbound

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training cites this paper.

Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training Mitigating the Alignment Tax of RLHF

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T22:40:43.282501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1f34472f-2b41-4fc4-af15-a05165cda945 · inbound

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning cites this paper.

Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruning Mitigating the Alignment Tax of RLHF

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T21:01:50.125128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c6b2640-fb55-435b-b9a5-497f3548e30e · inbound

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training cites this paper.

CapTrack: Multifaceted Evaluation of Forgetting in LLM Post-Training Mitigating the Alignment Tax of RLHF

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-25T06:45:26.492450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c9986d8d-5bad-41a8-8adf-dfdb044c48a7 · inbound

Generative AI Technologies, Techniques & Tensions: A Primer cites this paper.

Generative AI Technologies, Techniques & Tensions: A Primer Mitigating the Alignment Tax of RLHF

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:41:01.385099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 787e0af1-5a2b-480c-a4b2-6d089dd5ee3c · inbound

OLLM: Options-based Large Language Models cites this paper.

OLLM: Options-based Large Language Models Mitigating the Alignment Tax of RLHF

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T13:16:08.545128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 24c97580-deb9-4128-80cc-55e119410d26 · inbound

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion cites this paper.

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion Mitigating the Alignment Tax of RLHF

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T01:57:06.339401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f868b637-308a-4d11-9a44-e1df3252cccb · inbound

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion cites this paper.

Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion Mitigating the Alignment Tax of RLHF

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T21:12:58.908959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8718851e-af55-470f-9c06-cccf72d2c979 · inbound

Learning, Fast and Slow: Towards LLMs That Adapt Continually cites this paper.

Learning, Fast and Slow: Towards LLMs That Adapt Continually Mitigating the Alignment Tax of RLHF

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:07:18.462997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4ac69b6d-a040-4ae5-bfad-47abb874b41b · inbound

Learning, Fast and Slow: Towards LLMs That Adapt Continually cites this paper.

Learning, Fast and Slow: Towards LLMs That Adapt Continually Mitigating the Alignment Tax of RLHF

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T05:19:45.701852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8d86648-e791-47ff-a418-5c284e9d5afa · inbound

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training cites this paper.

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training Mitigating the Alignment Tax of RLHF

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:25:33.131993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8a5c7bdf-874e-4fb0-929b-75d6f025ea84 · inbound

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training cites this paper.

Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training Mitigating the Alignment Tax of RLHF

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-14T19:20:54.974570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140ebab7-adb2-4c5f-857d-4c936101c097 · inbound

ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering cites this paper.

ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering Mitigating the Alignment Tax of RLHF

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-06-30T04:54:16.249019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 71b40abc-9420-4341-99ca-719257dc5299 · inbound

Multi-Turn On-Policy Distillation with Prefix Replay cites this paper.

Multi-Turn On-Policy Distillation with Prefix Replay Mitigating the Alignment Tax of RLHF

Reference 249

Resolution: unresolved; no resolver link, observed 2026-07-11T13:53:36.775836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 737093c4-4e6b-43e1-8156-8c8d0465eb86 · inbound

Multi-Turn On-Policy Distillation with Prefix Replay cites this paper.

Multi-Turn On-Policy Distillation with Prefix Replay Mitigating the Alignment Tax of RLHF

Reference 250

Resolution: unresolved; no resolver link, observed 2026-08-02T08:41:01.426952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66d3b4ac-d4b1-49c5-8d8c-4c78377c6b24 · inbound

SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling cites this paper.

SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling Mitigating the Alignment Tax of RLHF

Reference 157

Resolution: unresolved; no resolver link, observed 2026-08-02T09:51:03.639953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce3cc3a-5cad-4056-8208-3bf5fef146ab · inbound

A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI cites this paper.

A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI Mitigating the Alignment Tax of RLHF

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T04:53:01.794216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.