TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.
Control the
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Open-weight LLMs reach 81-91% success generating formally verified Dafny code for complex algorithmic problems when given structural signatures and self-healing verifier feedback.
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
The paper outlines opportunities, limitations, and practical parameters for integrating LLMs into qualitative research while aligning with epistemological commitments like reflexivity and interpretive judgment.
citing papers explorer
-
Diversity in Large Language Models under Supervised Fine-Tuning
TOFU loss mitigates the narrowing of generative diversity in LLMs after supervised fine-tuning by addressing neglect of low-frequency patterns and forgetting of prior knowledge.
-
From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
Open-weight LLMs reach 81-91% success generating formally verified Dafny code for complex algorithmic problems when given structural signatures and self-healing verifier feedback.
-
Sustainable Code Generation Using Large Language Models: A Systematic Literature Review
A systematic review finds research on the sustainability of LLM-generated code to be limited, fragmented, and without accepted frameworks for measurement or benchmarking.
-
LLMs in Qualitative Research: Opportunities, Limitations, and Practical Considerations
The paper outlines opportunities, limitations, and practical parameters for integrating LLMs into qualitative research while aligning with epistemological commitments like reflexivity and interpretive judgment.