Paper Citation Record · LEDGER

Improving Multilingual Language Models by Aligning Representations through Steering

As of 17 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 1 inbound Pith citation observation for arXiv:2505.12584.

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

pith.paper-citation-record.v1
2505.12584 v2

Coverage vector

measured 44 of 44 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-15T20:42:27.386477Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-26T10:41:19.777779Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T08:59:42.908122Z

Reference resolution

44 of 44 outbound references displayed

verified exact1
verified fuzzy0
unresolved43
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c4127601-a9bf-4295-bcce-35754096ffcc · outbound

This paper cites online" 'onlinestring :=.

Improving Multilingual Language Models by Aligning Representations through Steering online" 'onlinestring :=

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.205243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e575fa6-dd83-42ab-88a7-35b878af865b · outbound

This paper cites write newline.

Improving Multilingual Language Models by Aligning Representations through Steering write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.210789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3eb5883-f65f-499c-b744-17eb7d565d1a · outbound

This paper cites an unresolved cited work.

Improving Multilingual Language Models by Aligning Representations through Steering Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:42:27.919365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1caf80b4-a8c0-499d-be13-782c8e9c4612 · outbound

This paper cites Aya 23: Open Weight Releases to Further Multilingual Progress.

Improving Multilingual Language Models by Aligning Representations through Steering Aya 23: Open Weight Releases to Further Multilingual Progress

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.220302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 413be24b-0fdf-4dfa-8feb-41ba6475f487 · outbound

This paper cites Eliciting Latent Predictions from Transformers with the Tuned Lens.

Improving Multilingual Language Models by Aligning Representations through Steering Eliciting Latent Predictions from Transformers with the Tuned Lens

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.225647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f747ac16-ce9f-47d4-8cdc-f19d7b01b424 · outbound

This paper cites Language Models are Few-Shot Learners.

Improving Multilingual Language Models by Aligning Representations through Steering Language Models are Few-Shot Learners

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.231157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6531a382-1173-4db6-ab3c-5929cb0c2ce6 · outbound

This paper cites Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization.

Improving Multilingual Language Models by Aligning Representations through Steering Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.235449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b0fe641-3b44-4408-90b9-acee9d2c9dd6 · outbound

This paper cites Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations.

Improving Multilingual Language Models by Aligning Representations through Steering Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.239740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd8daeb2-9b6f-4bd5-b043-dc7973a09f13 · outbound

This paper cites Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca.

Improving Multilingual Language Models by Aligning Representations through Steering Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.244206Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c7180e8-be52-4fd7-b518-09b6eb99f823 · outbound

This paper cites Bowman, Holger Schwenk, and Veselin Stoyanov.

Improving Multilingual Language Models by Aligning Representations through Steering Bowman, Holger Schwenk, and Veselin Stoyanov

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.248682Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f8d8f0b-3c5b-4186-b3f7-c29a153b6591 · outbound

This paper cites No Language Left Behind: Scaling Human-Centered Machine Translation.

Improving Multilingual Language Models by Aligning Representations through Steering No Language Left Behind: Scaling Human-Centered Machine Translation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.252703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77edc85f-36d4-4561-b1ce-553263a37b3a · outbound

This paper cites RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs.

Improving Multilingual Language Models by Aligning Representations through Steering RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.257190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ee55208-9590-4773-b364-0f1059e8191b · outbound

This paper cites Do Multilingual Language Models Think Better in English?.

Improving Multilingual Language Models by Aligning Representations through Steering Do Multilingual Language Models Think Better in English?

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.261062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08efb218-033e-4b72-bf98-fc6243f98454 · outbound

This paper cites The Llama 3 Herd of Models.

Improving Multilingual Language Models by Aligning Representations through Steering The Llama 3 Herd of Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.265336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6e7c28d-f7f7-42fe-b473-68b526618e1e · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Improving Multilingual Language Models by Aligning Representations through Steering Measuring Massive Multitask Language Understanding

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.269202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5776a95f-d35f-4b2f-918d-dcc35f07383b · outbound

This paper cites Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting.

Improving Multilingual Language Models by Aligning Representations through Steering Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.272858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b4092e6-5e1d-4c07-a80b-f8927811a228 · outbound

This paper cites MindMerger: Efficient Boosting LLM Reasoning in non-English Languages.

Improving Multilingual Language Models by Aligning Representations through Steering MindMerger: Efficient Boosting LLM Reasoning in non-English Languages

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.276533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84f70932-39a2-4503-b4a2-7a238078fbbf · outbound

This paper cites Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective.

Improving Multilingual Language Models by Aligning Representations through Steering Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.280816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b0306f2-8a6e-499f-90c5-475a009a03db · outbound

This paper cites Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages.

Improving Multilingual Language Models by Aligning Representations through Steering Language Ranker: A Metric for Quantifying LLM Performance Across High and Low-Resource Languages

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.284933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61d222e6-9206-4678-8ed5-8c2a10eca2f3 · outbound

This paper cites Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models.

Improving Multilingual Language Models by Aligning Representations through Steering Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.288762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74d60476-52cf-4a54-8fc3-2b07cb725fb3 · outbound

This paper cites Investigating Bias Representations in Llama 2 Chat via Activation Steering.

Improving Multilingual Language Models by Aligning Representations through Steering Investigating Bias Representations in Llama 2 Chat via Activation Steering

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.292583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dadba7a6-952a-4a09-9529-638c1dd4c83b · outbound

This paper cites an unresolved cited work.

Improving Multilingual Language Models by Aligning Representations through Steering Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:42:27.890755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e1f1aeb2-4dd6-4dc6-8529-cde356651a88 · outbound

This paper cites Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress.

Improving Multilingual Language Models by Aligning Representations through Steering Multilingual Arbitrage: Optimizing Data Pools to Accelerate Multilingual Progress

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.300490Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c48a4d15-f548-4510-b25b-76b759443433 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Improving Multilingual Language Models by Aligning Representations through Steering Steering Llama 2 via Contrastive Activation Addition

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.305176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cd9c909-26f7-4ae8-aeb2-a184bbc244f9 · outbound

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

Improving Multilingual Language Models by Aligning Representations through Steering The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.309283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3803c9bc-b947-4b56-a4c0-7aac8b35bdd8 · outbound

This paper cites an unresolved cited work.

Improving Multilingual Language Models by Aligning Representations through Steering Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.313421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d60906d0-8715-4f11-a3f4-48bb808a7668 · outbound

This paper cites an unresolved cited work.

Improving Multilingual Language Models by Aligning Representations through Steering Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.317086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf66948-ab19-4513-bf56-94bb7781ba2d · outbound

This paper cites Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers.

Improving Multilingual Language Models by Aligning Representations through Steering Multilingual Large Language Model: A Survey of Resources, Taxonomy and Frontiers

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.320820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb241f6-1dd9-4cef-928d-eaf2cc2eb72a · outbound

This paper cites Language Models are Multilingual Chain-of-Thought Reasoners.

Improving Multilingual Language Models by Aligning Representations through Steering Language Models are Multilingual Chain-of-Thought Reasoners

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.324602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7822990-5395-4403-97b4-6de277bca94e · outbound

This paper cites Gemma: Open Models Based on Gemini Research and Technology.

Improving Multilingual Language Models by Aligning Representations through Steering Gemma: Open Models Based on Gemini Research and Technology

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.328362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 955c316e-a04f-4eeb-87ef-c950169ec588 · outbound

This paper cites an unresolved cited work.

Improving Multilingual Language Models by Aligning Representations through Steering Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.332026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f5f595b-aa12-4acb-8bc6-5acb64bb6d89 · outbound

This paper cites an unresolved cited work.

Improving Multilingual Language Models by Aligning Representations through Steering Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.335583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5389b57b-7963-46a3-bfb2-e0bd082b69a2 · outbound

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

Improving Multilingual Language Models by Aligning Representations through Steering Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.339016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0edccbc-9058-4a21-ab17-e03d4e0de2a8 · outbound

This paper cites Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.

Improving Multilingual Language Models by Aligning Representations through Steering Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.342800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d253569b-8003-4e90-bd35-d948a4463271 · outbound

This paper cites Do Llamas Work in English? On the Latent Language of Multilingual Transformers.

Improving Multilingual Language Models by Aligning Representations through Steering Do Llamas Work in English? On the Latent Language of Multilingual Transformers

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.346343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa1ad64b-a966-4397-818e-9d0a441b036b · outbound

This paper cites Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels.

Improving Multilingual Language Models by Aligning Representations through Steering Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.350397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ceda3a-4a7b-4c41-9017-417604d094b4 · outbound

This paper cites LangBridge: Multilingual Reasoning Without Multilingual Supervision.

Improving Multilingual Language Models by Aligning Representations through Steering LangBridge: Multilingual Reasoning Without Multilingual Supervision

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.354261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83f3c9d1-27e8-4c7f-ae10-e6276442cabb · outbound

This paper cites M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models.

Improving Multilingual Language Models by Aligning Representations through Steering M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.358121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d75beeed-39a5-40d5-945e-2b89d42a9542 · outbound

This paper cites Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages.

Improving Multilingual Language Models by Aligning Representations through Steering Enhancing Multilingual Capabilities of Large Language Models through Self-Distillation from Resource-Rich Languages

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.361924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb056d3b-e1fc-41ba-a282-48d0b81525a0 · outbound

This paper cites How do Large Language Models Handle Multilingualism?.

Improving Multilingual Language Models by Aligning Representations through Steering How do Large Language Models Handle Multilingualism?

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.365566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8041645e-3d03-468b-b0c3-768c48373fb7 · outbound

This paper cites Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?.

Improving Multilingual Language Models by Aligning Representations through Steering Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.369703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c7b76bc-e71e-4bb2-98a6-585b6ec9195e · outbound

This paper cites Question Translation Training for Better Multilingual Reasoning.

Improving Multilingual Language Models by Aligning Representations through Steering Question Translation Training for Better Multilingual Reasoning

Reference 42

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:42:27.463446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 15fb997a-997c-4039-bca6-8f8b2e3e1794 · outbound

This paper cites Extrapolating Large Language Models to Non-English by Aligning Languages.

Improving Multilingual Language Models by Aligning Representations through Steering Extrapolating Large Language Models to Non-English by Aligning Languages

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.380358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d6de966-ad25-4885-b3df-6d658994983b · outbound

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

Improving Multilingual Language Models by Aligning Representations through Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T20:42:27.386477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation b0030c84-6db0-4892-acda-4c10ffeed90c · inbound

Interleaved Speech Language Models Latently Work In Text cites this paper.

Interleaved Speech Language Models Latently Work In Text Improving Multilingual Language Models by Aligning Representations through Steering

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-04T08:59:42.909674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.