DiARC improves LLM performance on ARC-like tasks by fine-tuning on preference pairs of positive demonstrations and three classes of constructed negative samples.
Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1 , pages =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
\textsc{DiARC}: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models
DiARC improves LLM performance on ARC-like tasks by fine-tuning on preference pairs of positive demonstrations and three classes of constructed negative samples.