Paper Citation Record · LEDGER

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M

As of 15 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 0 inbound Pith citation observations for arXiv:2509.09055.

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

pith.paper-citation-record.v1
2509.09055 v1

Coverage vector

measured 10 of 10 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T19:48:23.200455Z

measured 10 of 10 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

10 of 10 outbound references displayed

verified exact0
verified fuzzy0
unresolved10
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e05c4997-8370-41ed-bce8-eefa7f93d9e5 · outbound

This paper cites Direct Preference Optimization: Your Language Model is Secretly a Reward Model.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:22.384196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 713eddfd-fe4b-429b-a5e1-ddcdc75da528 · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M OPT: Open Pre-trained Transformer Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:22.457324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1d66f49-ccf2-4d08-be9e-eaccbf368904 · outbound

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

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:22.569427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a73cc95-c9ce-4d0c-a535-f8894b8213b0 · outbound

This paper cites How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:22.658957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7740676d-a93a-4607-ba59-16987e2cb33d · outbound

This paper cites Realistic Evaluation of Toxicity in Large Language Models.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Realistic Evaluation of Toxicity in Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:22.761053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40651299-5700-4120-a563-dfeaa452eef7 · outbound

This paper cites Crafting Tomorrow's Evaluations: Assessment Design Strategies in the Era of Generative AI.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Crafting Tomorrow's Evaluations: Assessment Design Strategies in the Era of Generative AI

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:22.847237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91451675-098c-4626-8d54-ab661566828f · outbound

This paper cites Dynabench: Rethinking Benchmarking in NLP.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Dynabench: Rethinking Benchmarking in NLP

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:22.922729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ced9a9ae-fd1e-4e8f-b6bd-6c8b837f7175 · outbound

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

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Fine-Tuning Language Models from Human Preferences

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:23.005157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4adc5a6b-4463-4caf-831a-8f4ac4bf5faa · outbound

This paper cites Red Teaming Language Models with Language Models.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Red Teaming Language Models with Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:23.101317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b8aa4c-6825-4719-a95a-f90b96b1c0e0 · outbound

This paper cites Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks.

Improving LLM Safety and Helpfulness using SFT and DPO: A Study on OPT-350M Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T19:48:23.200455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.