Paper Citation Record · LEDGER

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels

As of 21 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 1 inbound Pith citation observation for arXiv:2605.15208.

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

pith.paper-citation-record.v1
2605.15208 v1

Coverage vector

measured 25 of 25 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-19T17:55:35.764347Z

measured 26 of 26 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T08:38:52.168891Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

25 of 25 outbound references displayed

verified exact13
verified fuzzy11
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a9b94384-239e-45d5-805a-aacecfc74c42 · outbound

This paper cites Large Language Models: A Survey.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Large Language Models: A Survey

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-19T17:57:42.543982Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 78c1b437-26bf-421f-a092-0808be762b66 · outbound

This paper cites A survey of post-training scaling in large language models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels A survey of post-training scaling in large language models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.327045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 81f1a329-29f5-46a6-bae7-dd633ef67336 · outbound

This paper cites LLMCBench: Benchmarking large language model com- pression for efficient deployment.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels LLMCBench: Benchmarking large language model com- pression for efficient deployment

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.324758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 985048e7-75dc-4726-879f-8a060cc018ef · outbound

This paper cites A survey of model compression techniques: Past, present, and future.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels A survey of model compression techniques: Past, present, and future

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.316046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 471d4443-7597-4bec-933d-5325bf0677e7 · outbound

This paper cites A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-19T17:57:42.521114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4e063007-2832-4169-b019-205129e3a238 · outbound

This paper cites A survey on hallucination in large language and foundation models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels A survey on hallucination in large language and foundation models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.515664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fc0a8228-3235-4b12-9449-eb8e668b21f0 · outbound

This paper cites Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in Product QA Agents.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Winning Big with Small Models: Knowledge Distillation vs. Self-Training for Reducing Hallucination in Product QA Agents

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.512107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 143f2603-292c-4235-b830-b3c2b6487410 · outbound

This paper cites Bias and fairness in large language models: A survey.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Bias and fairness in large language models: A survey

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.307852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8452ba2d-36bf-46ef-a48c-cf11b1776990 · outbound

This paper cites Beyond perplexity: Multi-dimensional safety evaluation of LLM compression.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Beyond perplexity: Multi-dimensional safety evaluation of LLM compression

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.305476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bf0e9f81-fb65-4ea5-a49e-78c95e3c145b · outbound

This paper cites A Survey on Out-of-Distribution Evaluation of Neural NLP Models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels A Survey on Out-of-Distribution Evaluation of Neural NLP Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.539865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 902288b6-666d-4eca-9fbe-18693aa5ac5a · outbound

This paper cites A Survey on Large Language Model Benchmarks.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels A Survey on Large Language Model Benchmarks

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.491127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4a18eb4c-ea0b-49a1-bfe0-376588f60048 · outbound

This paper cites Robust Lottery Tickets for Pre-trained Language Models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Robust Lottery Tickets for Pre-trained Language Models

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.487055Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a0aab113-6fbe-4e58-b677-32aa145baf5d · outbound

This paper cites Understanding and over- coming the challenges of efficient transformer quantization.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Understanding and over- coming the challenges of efficient transformer quantization

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.322397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2fd9e2ec-2442-4a61-afcd-dfac1a0d5907 · outbound

This paper cites The compression techniques applied on deep learning model.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels The compression techniques applied on deep learning model

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.320302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 672bc7a9-9046-4b56-8729-0ff2fd426598 · outbound

This paper cites The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T17:57:42.499733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 46b14417-7a05-4b87-b40d-8829e0af3514 · outbound

This paper cites Understanding the effect of model compression on social bias in large language models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Understanding the effect of model compression on social bias in large language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.318211Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f6704a4f-47df-4ec2-8dda-3f1118b95bef · outbound

This paper cites How Does Quantization Affect Multilingual LLMs?.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels How Does Quantization Affect Multilingual LLMs?

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.503592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation eb2e1ace-dc33-4d63-8522-6058e770afea · outbound

This paper cites Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.507878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 98905bc3-8204-4352-937a-2a3a3036ddc9 · outbound

This paper cites What Do Compressed Deep Neural Networks Forget?.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels What Do Compressed Deep Neural Networks Forget?

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.535481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e76988ec-6b84-452a-be1f-166ee7280d25 · outbound

This paper cites BBQ: A hand-built bias benchmark for question answering.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels BBQ: A hand-built bias benchmark for question answering

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.313870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5525bf5f-7525-4b71-ad42-af6c1f06599b · outbound

This paper cites MLX: An array framework for Apple Silicon.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels MLX: An array framework for Apple Silicon

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.311935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1dd28d74-8a3a-4d7d-b4e1-8954e0d54e1d · outbound

This paper cites Cohen,Statistical Power Analysis for the Behavioral Sciences, 2nd ed.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Cohen,Statistical Power Analysis for the Behavioral Sciences, 2nd ed

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T17:57:43.309967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 03be5546-2aa0-4ddc-83ae-6fd0cd91f904 · outbound

This paper cites Uncertainty drives social bias changes in quantized large language models.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Uncertainty drives social bias changes in quantized large language models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.547977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7763e137-dfaa-43d8-b682-d0740a956300 · outbound

This paper cites Alignment-aware quantization for LLM safety.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Alignment-aware quantization for LLM safety

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.495422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0f1e3dc1-6919-4ef8-9d56-4592b38885cf · outbound

This paper cites Accuracy is Not All You Need.

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels Accuracy is Not All You Need

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:57:42.525569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 0d8c76db-04db-49c7-9c08-469a3e12f32f · inbound

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs cites this paper.

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T08:38:52.168891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.