Paper Citation Record · LEDGER

On Teacher Hacking in Language Model Distillation

As of 9 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2502.02671.

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

pith.paper-citation-record.v1
2502.02671 v1

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T11:34:57.198738Z

measured 27 of 27 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 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T22:45:03.331296Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T22:45:05.037045Z

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy2
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2b76f6bd-3f57-457b-b833-4f55e15c42d3 · outbound

This paper cites an unresolved cited work.

On Teacher Hacking in Language Model Distillation Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:34:57.606640Z

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 960a8d90-3a91-4eda-aa8c-1c3ba9f7958d · outbound

This paper cites Unsolved Problems in ML Safety.

On Teacher Hacking in Language Model Distillation Unsolved Problems in ML Safety

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.920640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9318d52b-f9ce-4aaf-9865-f47d734a62cd · outbound

This paper cites Sequence-Level Knowledge Distillation.

On Teacher Hacking in Language Model Distillation Sequence-Level Knowledge Distillation

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.942721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d4cb55c-6109-4502-8d33-b59771de9ca1 · outbound

This paper cites Autoregressive Knowledge Distillation through Imitation Learning.

On Teacher Hacking in Language Model Distillation Autoregressive Knowledge Distillation through Imitation Learning

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.975671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 380e2e34-d2b9-4b37-8a5c-2a7648de7c00 · outbound

This paper cites DeepSeek-V3 Technical Report.

On Teacher Hacking in Language Model Distillation DeepSeek-V3 Technical Report

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.012110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae105ab-7403-4dea-80d8-168ec22821ea · outbound

This paper cites B., and Lapata, M.

On Teacher Hacking in Language Model Distillation B., and Lapata, M

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:34:57.640894Z

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 a9d1e721-e2b8-4dc9-95e0-c08bbe5ec341 · outbound

This paper cites The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models.

On Teacher Hacking in Language Model Distillation The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.100873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8af2d07-08a3-4725-832d-7f275034c4bd · outbound

This paper cites Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms.

On Teacher Hacking in Language Model Distillation Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.128745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9917ce7-d6d8-45b9-a5cf-cfb28070d176 · outbound

This paper cites WARM: On the Benefits of Weight Averaged Reward Models.

On Teacher Hacking in Language Model Distillation WARM: On the Benefits of Weight Averaged Reward Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.150732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 742b1719-657f-4cad-91f1-eb939d2eaeec · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

On Teacher Hacking in Language Model Distillation Gemma 2: Improving Open Language Models at a Practical Size

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.156496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ff5f2db-b2b4-4252-a7d6-66a689e57f8c · outbound

This paper cites Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$.

On Teacher Hacking in Language Model Distillation Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.167515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4841ee5f-8954-4e5f-94d9-926bbc1fbbe3 · outbound

This paper cites DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter.

On Teacher Hacking in Language Model Distillation DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.172471Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65b7cce2-5efb-4116-b854-1d57b5fe6d9a · outbound

This paper cites Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation.

On Teacher Hacking in Language Model Distillation Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.189016Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 175fecbf-e0a5-48ed-8931-99fe2d20241d · outbound

This paper cites an unresolved cited work.

On Teacher Hacking in Language Model Distillation Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-09T11:34:57.624594Z

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 644c30ee-7652-440f-8220-041e2483eada · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

On Teacher Hacking in Language Model Distillation Zephyr: Direct Distillation of LM Alignment

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.178509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2d964af-fd96-4424-8667-bbc72aba3a2b · outbound

This paper cites ODIN: Disentangled Reward Mitigates Hacking in RLHF.

On Teacher Hacking in Language Model Distillation ODIN: Disentangled Reward Mitigates Hacking in RLHF

Reference 2006

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.907788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04bdcc2c-96f8-48f9-adb2-c35da20ea704 · outbound

This paper cites doi: 10.3115/v1/W14-3302.

On Teacher Hacking in Language Model Distillation doi: 10.3115/v1/W14-3302

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.901841Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2f779b1-5788-41e3-a593-46cebc98585b · outbound

This paper cites TinyBERT: Distilling BERT for Natural Language Understanding.

On Teacher Hacking in Language Model Distillation TinyBERT: Distilling BERT for Natural Language Understanding

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.926817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2140783-1c12-4353-84c9-6e64a19afbdb · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

On Teacher Hacking in Language Model Distillation Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.890311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4c2bbc3-3adc-4e7f-b305-b9f914a969ac · outbound

This paper cites doi: 10.18653/v1/D18-1206.

On Teacher Hacking in Language Model Distillation doi: 10.18653/v1/D18-1206

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.071170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3446707-e7f7-4986-9c56-b33813e27238 · outbound

This paper cites Scaling Laws for Neural Language Models.

On Teacher Hacking in Language Model Distillation Scaling Laws for Neural Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.932470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5079aeb4-3010-4a7a-b30e-1bacc08cb956 · outbound

This paper cites PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning.

On Teacher Hacking in Language Model Distillation PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.937688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf2cbe1c-3a37-4d91-9527-518e6f543717 · outbound

This paper cites Language Models Learn to Mislead Humans via RLHF.

On Teacher Hacking in Language Model Distillation Language Models Learn to Mislead Humans via RLHF

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:57.183913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5037d20-7ab6-4d33-8ca2-542aea9cc5b3 · outbound

This paper cites Findings of the 2014 workshop on statistical machine translation.

On Teacher Hacking in Language Model Distillation Findings of the 2014 workshop on statistical machine translation

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T11:34:57.658851Z

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 be93f680-b27a-4f21-985b-94a377288f4a · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

On Teacher Hacking in Language Model Distillation Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.914050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 867258ab-a084-4776-b325-c25c5abea41e · outbound

This paper cites Concrete Problems in AI Safety.

On Teacher Hacking in Language Model Distillation Concrete Problems in AI Safety

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T11:34:56.883725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8a34b152-2464-440c-a5d0-9a7c4e36895b · inbound

Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation cites this paper.

Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation On Teacher Hacking in Language Model Distillation

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-08-06T22:45:05.113351Z

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.