Paper Citation Record · LEDGER

Risk-Averse Finetuning of Large Language Models

As of 12 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2501.06911.

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

pith.paper-citation-record.v1
2501.06911 v1

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T20:54:05.242057Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+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

33 of 33 outbound references displayed

verified exact1
verified fuzzy8
unresolved24
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3cfd475d-d010-4627-b1c5-cf309afa68a1 · outbound

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

Risk-Averse Finetuning of Large Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.034917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c731d022-e0b5-4ab2-af41-1e260a7b6081 · outbound

This paper cites Toxicity in ChatGPT: Analyzing Persona-assigned Language Models.

Risk-Averse Finetuning of Large Language Models Toxicity in ChatGPT: Analyzing Persona-assigned Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.066525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a00f026-83bf-4318-82e2-df7b8510debd · outbound

This paper cites BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding.

Risk-Averse Finetuning of Large Language Models BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.073392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee09e131-6f1e-4b0b-93e2-907218c1c4d8 · outbound

This paper cites Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.

Risk-Averse Finetuning of Large Language Models Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.079600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcd73537-6261-4a51-8ceb-ce1b2d892da4 · outbound

This paper cites WHEN I AM UNBLOCKED I SWEAR I WILL GO F**K YOUR M C.

Risk-Averse Finetuning of Large Language Models WHEN I AM UNBLOCKED I SWEAR I WILL GO F**K YOUR M C

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.863420Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 45be7a25-cdac-471f-b276-17624c861a8d · outbound

This paper cites DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts.

Risk-Averse Finetuning of Large Language Models DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.123385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fdee585-fe79-4fe5-9c7c-71cf1f75512e · outbound

This paper cites EPOpt: Learning Robust Neural Network Policies Using Model Ensembles.

Risk-Averse Finetuning of Large Language Models EPOpt: Learning Robust Neural Network Policies Using Model Ensembles

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.137785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 381e7469-1002-47d5-870c-8417caabbeba · outbound

This paper cites The Woman Worked as a Babysitter: On Biases in Language Generation.

Risk-Averse Finetuning of Large Language Models The Woman Worked as a Babysitter: On Biases in Language Generation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.158237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f092efe-31a3-4711-b7da-334899d6cfbe · outbound

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

Risk-Averse Finetuning of Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.172123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ecb8305-c134-450f-a5f8-5a22cb0f3d93 · outbound

This paper cites Universal Adversarial Triggers for Attacking and Analyzing NLP.

Risk-Averse Finetuning of Large Language Models Universal Adversarial Triggers for Attacking and Analyzing NLP

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.177311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274f79a1-7817-4abc-971e-aded10f64a4d · outbound

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

Risk-Averse Finetuning of Large Language Models Ethical and social risks of harm from Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.185085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04b72b7d-80c9-4cd4-bb81-ddc0e655768b · outbound

This paper cites Fine-Tuning Language Models from Human Preferences.

Risk-Averse Finetuning of Large Language Models Fine-Tuning Language Models from Human Preferences

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.191903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e3b5f31-4961-4eea-be33-3b00704744f7 · outbound

This paper cites In our work, we primarily focussed on generative tasks, and not the Question-Answer (Q&A) format.

Risk-Averse Finetuning of Large Language Models In our work, we primarily focussed on generative tasks, and not the Question-Answer (Q&A) format

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.953921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5df3b17b-9423-4bcb-b6db-115326511e04 · outbound

This paper cites Furthermore, even aligned versions of LLMs are not immune to exploitation.

Risk-Averse Finetuning of Large Language Models Furthermore, even aligned versions of LLMs are not immune to exploitation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.936478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 74a7bf16-41b5-47ee-98a0-f4b04e0894e9 · outbound

This paper cites an unresolved cited work.

Risk-Averse Finetuning of Large Language Models Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-10T20:54:05.918108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 66a36157-066c-451a-9918-dd0d8af762c8 · outbound

This paper cites Furthermore, even aligned versions of LLMs are not immune to exploitation.

Risk-Averse Finetuning of Large Language Models Furthermore, even aligned versions of LLMs are not immune to exploitation

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.900197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1c3e45d6-d485-47d1-be7a-2b5b69d76344 · outbound

This paper cites Risk Averseness in RL.

Risk-Averse Finetuning of Large Language Models Risk Averseness in RL

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.880538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 94cd4264-4635-402e-bb16-775317b7b7be · outbound

This paper cites The dataset utilized in this task is introduced by Gehman et al.

Risk-Averse Finetuning of Large Language Models The dataset utilized in this task is introduced by Gehman et al

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.846658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8a81c51f-ad58-4a6c-bccd-ce0535e95d7e · outbound

This paper cites We choose to work with regularized reward for two reasons: I.

Risk-Averse Finetuning of Large Language Models We choose to work with regularized reward for two reasons: I

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.806374Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 10bec7ae-4ad5-4f6c-ae8e-0e0cc07abb20 · outbound

This paper cites [PAD]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 100: AddedToken(.

Risk-Averse Finetuning of Large Language Models [PAD]", rstrip=False, lstrip=False, single_word=False, normalized=False, special=True), 100: AddedToken(

Reference 768

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T20:54:05.828970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4f6894a9-0bec-4174-b2b5-448f8278d076 · outbound

This paper cites Language models are few-shot learners.

Risk-Averse Finetuning of Large Language Models Language models are few-shot learners

Reference 1952

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.041769Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 799074a3-0bed-4808-93aa-00648c9f1c55 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Risk-Averse Finetuning of Large Language Models Proximal Policy Optimization Algorithms

Reference 2001

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.152427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8c71568-bd16-4288-abaf-efb32a7a799a · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Risk-Averse Finetuning of Large Language Models WebGPT: Browser-assisted question-answering with human feedback

Reference 2011

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.131854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e66f78b-29f4-4884-9793-12598b607891 · outbound

This paper cites RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback.

Risk-Averse Finetuning of Large Language Models RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.117708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa4b1f60-ffc2-4b51-b397-a44e9bbb9d2d · outbound

This paper cites Worst Cases Policy Gradients.

Risk-Averse Finetuning of Large Language Models Worst Cases Policy Gradients

Reference 2015

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.164564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8abc197-a505-4958-bbce-d00cd6bf48bd · outbound

This paper cites Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization.

Risk-Averse Finetuning of Large Language Models Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Reference 2016

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.145902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afa4f4c4-9db1-4bf7-a623-f4a8a538f8ad · outbound

This paper cites GeDi: Generative Discriminator Guided Sequence Generation.

Risk-Averse Finetuning of Large Language Models GeDi: Generative Discriminator Guided Sequence Generation

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.111068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de18ffcd-46cf-4c53-8b3a-d60c18d3f827 · outbound

This paper cites Safe RLHF: Safe Reinforcement Learning from Human Feedback.

Risk-Averse Finetuning of Large Language Models Safe RLHF: Safe Reinforcement Learning from Human Feedback

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.059653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b19e35a-fec8-443e-acd2-7b43bfcb77db · outbound

This paper cites Universal Language Model Fine-tuning for Text Classification.

Risk-Averse Finetuning of Large Language Models Universal Language Model Fine-tuning for Text Classification

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.093014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b67231ad-3244-4c56-be41-254761be35a1 · outbound

This paper cites Sparks of Artificial General Intelligence: Early experiments with GPT-4.

Risk-Averse Finetuning of Large Language Models Sparks of Artificial General Intelligence: Early experiments with GPT-4

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.047886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3607c869-9333-4d05-a8d4-8411918d39c6 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Risk-Averse Finetuning of Large Language Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.105089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0b296f1-c8bb-4395-9709-51788a0ce629 · outbound

This paper cites RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models.

Risk-Averse Finetuning of Large Language Models RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:05.086247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2d11885-206f-4c57-956a-741d2a3ce73f · outbound

This paper cites Systematic Rectification of Language Models via Dead-end Analysis.

Risk-Averse Finetuning of Large Language Models Systematic Rectification of Language Models via Dead-end Analysis

Reference 2023

Resolution: verified exact; local_arxiv, observed 2026-08-10T20:54:05.751272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Pith citing papers

No inbound Pith citation observations are available.