CODI compresses explicit CoT into continuous space via self-distillation and is the first implicit method to match explicit CoT performance on GSM8k at GPT-2 scale with 3.1x compression and 28.2% higher accuracy than prior implicit approaches.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
LLMs prompted with few-shot examples and rationales generate better reasoned distractors for MCQs than fine-tuned contrastive models across six benchmarks.
SAVeR adds self-auditing of internal beliefs in LLM agents via persona-based candidates and constraint-guided repairs, improving faithfulness on six benchmarks without hurting task performance.
citing papers explorer
-
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
SAVeR adds self-auditing of internal beliefs in LLM agents via persona-based candidates and constraint-guided repairs, improving faithfulness on six benchmarks without hurting task performance.