Using frontier models to synthesize plausible-but-wrong FIM completions as hard negatives for SFT improves Delulu exact match by +18.8 and edit similarity by +0.22 on Qwen2.5-Coder-7B while also lifting HumanEval-Infilling and SAFIM.
Rafael Rafailov, Archit Sharma, E
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
RECAP captures, replays, and analyzes AI-assisted programming sessions by linking prompts, edits, and developer actions in a single timeline.
Post-editing LLM text increases stylistic similarity to the user's own writing yet keeps it closer to LLM output than human text and lowers diversity.
citing papers explorer
-
Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation
Using frontier models to synthesize plausible-but-wrong FIM completions as hard negatives for SFT improves Delulu exact match by +18.8 and edit similarity by +0.22 on Qwen2.5-Coder-7B while also lifting HumanEval-Infilling and SAFIM.
-
RECAP: An End-to-End Platform for Capturing, Replaying, and Analyzing AI-Assisted Programming Interactions
RECAP captures, replays, and analyzes AI-assisted programming sessions by linking prompts, edits, and developer actions in a single timeline.
-
Can You Make It Sound Like You? Post-Editing LLM-Generated Text for Personal Style
Post-editing LLM text increases stylistic similarity to the user's own writing yet keeps it closer to LLM output than human text and lowers diversity.