Paper Citation Record · LEDGER

Controlled LLM Decoding via Discrete Auto-regressive Biasing

As of 9 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2502.03685.

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

pith.paper-citation-record.v1
2502.03685 v1

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:11:25.391398Z

measured 28 of 28 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 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

28 of 28 outbound references displayed

verified exact3
verified fuzzy9
unresolved14
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c7439a20-50a4-40b6-9f5d-b27e5b29076a · outbound

This paper cites Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.376314Z

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 4380c031-ea9c-4ae9-8883-d3aa3ad2acbb · outbound

This paper cites 0.5 1.0 1.5 2.0 Bias Weight Value 0.70 0.75 0.80 0.85 0.90 0.95Ext.

Controlled LLM Decoding via Discrete Auto-regressive Biasing 0.5 1.0 1.5 2.0 Bias Weight Value 0.70 0.75 0.80 0.85 0.90 0.95Ext

Reference 2

Resolution: malformed identifier; raw_fallback, observed 2026-08-09T04:11:26.172274Z

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 8279158e-54ad-4f2e-b634-a6c68bdcf8f9 · outbound

This paper cites an unresolved cited work.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:11:26.156950Z

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 6018c9a3-a346-4d8c-a7a7-4df8f43bd7a6 · outbound

This paper cites Cold-attack: Jailbreaking llms with stealthiness and controllability.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Cold-attack: Jailbreaking llms with stealthiness and controllability

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.347289Z

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 2b629585-6b93-4aa2-ab6d-5892052d2f64 · outbound

This paper cites (2023a), Qin et al.

Controlled LLM Decoding via Discrete Auto-regressive Biasing (2023a), Qin et al

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.125332Z

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 0ed80a06-3ebb-4d87-a76d-943eb9c119fb · outbound

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

Controlled LLM Decoding via Discrete Auto-regressive Biasing Critic-Guided Decoding for Controlled Text Generation

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.108097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6f3533e-5bc4-4977-b7e9-5e5d914e9de3 · outbound

This paper cites GeDi: Generative Discriminator Guided Sequence Generation.

Controlled LLM Decoding via Discrete Auto-regressive Biasing GeDi: Generative Discriminator Guided Sequence Generation

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.113155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98cfbfc3-9bfc-4c06-aafb-6f7687707857 · outbound

This paper cites Alyssa Lees, Vinh Q.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Alyssa Lees, Vinh Q

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.123384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 647f5b38-5fc2-4a30-9b6f-81bf67ae69a4 · outbound

This paper cites doi: 10.1145/3534678.3539147.

Controlled LLM Decoding via Discrete Auto-regressive Biasing doi: 10.1145/3534678.3539147

Reference 12

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T04:11:25.822802Z

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 cd079fc9-b29c-41b1-be92-9d3f73a8e583 · outbound

This paper cites Don’t take it literally: An edit-invariant sequence loss for text generation.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Don’t take it literally: An edit-invariant sequence loss for text generation

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.315650Z

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 16fc4423-3058-4575-83c1-b5521c6f1c51 · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Prompt Injection attack against LLM-integrated Applications

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.139103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23d17ca9-25d5-4afb-82a4-0167fdd8e534 · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Efficient Estimation of Word Representations in Vector Space

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.143771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d70c7d8f-0f69-4814-bbea-ef14303f8587 · outbound

This paper cites John Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi.

Controlled LLM Decoding via Discrete Auto-regressive Biasing John Morris, Eli Lifland, Jin Yong Yoo, Jake Grigsby, Di Jin, and Yanjun Qi

Reference 16

Resolution: malformed identifier; raw_fallback, observed 2026-08-09T04:11:26.301275Z

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 aeacc19b-301c-46c8-ab9d-db15c1ab86a0 · outbound

This paper cites Lianhui Qin, Sean Welleck, Daniel Khashabi, and Yejin Choi.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Lianhui Qin, Sean Welleck, Daniel Khashabi, and Yejin Choi

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.223584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f33df39c-d741-408a-a4af-c35351a44b2d · outbound

This paper cites Classifiers are Better Experts for Controllable Text Generation.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Classifiers are Better Experts for Controllable Text Generation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.285084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfaa65c9-fb09-4f43-8a49-0dd6d20e581c · outbound

This paper cites FUDGE: Controlled text generation with future discriminators.

Controlled LLM Decoding via Discrete Auto-regressive Biasing FUDGE: Controlled text generation with future discriminators

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.287132Z

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 fa1848d0-6a08-43d8-b4e2-290df1bbd071 · outbound

This paper cites (2022), which is further investigated by Pynadath et al.

Controlled LLM Decoding via Discrete Auto-regressive Biasing (2022), which is further investigated by Pynadath et al

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.272903Z

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 4ac8a6c5-eda1-4dff-ab09-41166d3a323f · outbound

This paper cites an unresolved cited work.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:11:26.188635Z

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 bde96f53-baef-4316-9a36-d2cb2578669d · outbound

This paper cites an unresolved cited work.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:11:26.140763Z

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 aece0417-37ab-45ca-a596-3d8b15ccd468 · outbound

This paper cites In fact, we see that this degrades BOLT’s fluency slightly through a higher perplexity value.

Controlled LLM Decoding via Discrete Auto-regressive Biasing In fact, we see that this degrades BOLT’s fluency slightly through a higher perplexity value

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.107994Z

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 ac3d1513-2924-45ca-9d42-475f58113ded · outbound

This paper cites doi: 10.1023/A:1023562417138.

Controlled LLM Decoding via Discrete Auto-regressive Biasing doi: 10.1023/A:1023562417138

Reference 2002

Resolution: verified exact; doi, observed 2026-08-09T04:11:25.430330Z

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 27fb7867-5cfe-4519-8fd1-0b8749e6a0fb · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

Controlled LLM Decoding via Discrete Auto-regressive Biasing On the Opportunities and Risks of Foundation Models

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.072466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10ebb420-3e31-4544-9d64-ada7c30a7314 · outbound

This paper cites Ethical and social risks of harm from Language Models.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Ethical and social risks of harm from Language Models

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.316999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fc8cfbb-532b-4be2-b419-d1abdc19dd3d · outbound

This paper cites Katayoon Goshvadi, Haoran Sun, Xingchao Liu, Azade Nova, Ruqi Zhang, Will Sussman Grath- wohl, Dale Schuurmans, and Hanjun Dai.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Katayoon Goshvadi, Haoran Sun, Xingchao Liu, Azade Nova, Ruqi Zhang, Will Sussman Grath- wohl, Dale Schuurmans, and Hanjun Dai

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.092462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3352fa88-7ce5-47c7-a852-824bd58d85b8 · outbound

This paper cites doi: 10.1145/3442188.3445922.

Controlled LLM Decoding via Discrete Auto-regressive Biasing doi: 10.1145/3442188.3445922

Reference 2021

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T04:11:25.990803Z

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 b2fa0c54-2fe9-476d-abeb-fae7effeabe8 · outbound

This paper cites Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Samuel Gehman, Suchin Gururangan, Maarten Sap, Yejin Choi, and Noah A

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.362230Z

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 fa39a3ca-b1af-4b86-88dd-e91215dd646f · outbound

This paper cites Gradient-based constrained sampling from lan- guage models.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Gradient-based constrained sampling from lan- guage models

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:11:26.332182Z

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 1c9419c4-016d-41d3-8321-919f30c1fab0 · outbound

This paper cites Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models.

Controlled LLM Decoding via Discrete Auto-regressive Biasing Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T04:11:25.102184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.