Paper Citation Record · LEDGER

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs

As of 13 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2412.06843.

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

pith.paper-citation-record.v1
2412.06843 v2

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T20:33:59.640530Z

measured 27 of 27 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

27 of 27 outbound references displayed

verified exact1
verified fuzzy1
unresolved25
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 15a04b44-2169-4193-9f1b-3e5fc76338e1 · outbound

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

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Fine-Tuning Language Models from Human Preferences

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.554020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d444e7d5-cb5b-4337-8bec-7d199fa225d0 · outbound

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

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.557825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 085d205f-8cdb-41d1-87e7-c66fa1ef3d0f · outbound

This paper cites Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.561706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e16bfab0-ae79-454e-945f-b81c262ea90e · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.565711Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 988817a1-8dd4-4379-ab0a-cdb181cabc28 · outbound

This paper cites R-Judge: Benchmarking Safety Risk Awareness for LLM Agents.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs R-Judge: Benchmarking Safety Risk Awareness for LLM Agents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.569717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d27409a3-dc29-48ef-ad1e-97ebab1d9c08 · outbound

This paper cites ORPO: Monolithic Preference Optimization without Reference Model.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs ORPO: Monolithic Preference Optimization without Reference Model

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.574024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09f16256-67d0-4308-ac73-4385e1aa14a7 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs KTO: Model Alignment as Prospect Theoretic Optimization

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.578757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7c02c9a-27b9-43be-af1b-bac8b97313e5 · outbound

This paper cites Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.583034Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a7c882e-489e-49f7-aed1-b97b597e2b0d · outbound

This paper cites Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.587315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d91eca39-ba59-410f-a4be-552abe4e1306 · outbound

This paper cites Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Safe LoRA: the Silver Lining of Reducing Safety Risks when Fine-tuning Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.593520Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19576853-9900-4303-a4d6-936240f74637 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs LLaMA: Open and Efficient Foundation Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.600583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83a6bf1-59e9-4e45-a6d4-1930296d5e01 · outbound

This paper cites Mistral 7B.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Mistral 7B

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.603933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66f137b4-4828-4e31-9dd9-a0f91ccef01c · outbound

This paper cites The Llama 3 Herd of Models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs The Llama 3 Herd of Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.608238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 022c2652-7026-4eee-8df1-90bc1ac82942 · outbound

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

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs LoRA: Low-Rank Adaptation of Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.611336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31f68ea1-ff3c-431d-92b6-f9861cefe203 · outbound

This paper cites DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.619238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 642c39c9-0c7c-440a-a1b0-6bac0444c4c6 · outbound

This paper cites BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.622547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a2cc4e8-3893-4068-b9a2-368cb93a7940 · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.627999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c13ad7-23f0-4c10-a127-758aa0bd4237 · outbound

This paper cites Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.633260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 163bf31f-14b5-4e4e-8ec7-e2fca2c8cf32 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.636728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a2d0ac-c57e-4ad8-b07b-39052ee0a6ab · outbound

This paper cites Mixtral of Experts.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Mixtral of Experts

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.640530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e70ce04d-a079-475a-873b-aae12b9ae1a5 · outbound

This paper cites EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs EMO: Earth Mover Distance Optimization for Auto-Regressive Language Modeling

Reference 1997

Resolution: verified exact; local_arxiv, observed 2026-08-11T20:34:00.061075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 47277483-7306-46d7-8541-2584d40c8870 · outbound

This paper cites Language Models are Few-Shot Learners.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Language Models are Few-Shot Learners

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.550341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d4f8019-7807-4045-a846-246cb306d110 · outbound

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

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs The Woman Worked as a Babysitter: On Biases in Language Generation

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.546061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7490d506-06b8-4faf-97c7-129aafd999db · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.615309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34fd8d9a-a25c-47c5-a20c-84e37a734807 · outbound

This paper cites Unveiling the Implicit Toxicity in Large Language Models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Unveiling the Implicit Toxicity in Large Language Models

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.537032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc2a4973-20ac-45a6-bea0-8c0ad398d8a2 · outbound

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

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T20:33:59.541946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 588e621b-2853-4f89-8348-1f57d7e05664 · outbound

This paper cites Predictability and surprise in large generative models.

Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs Predictability and surprise in large generative models

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:34:00.377140Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.