A feedback-triggered regeneration method combined with dynamic multipath decoding improves LLM accuracy on math and coding benchmarks compared to prompt-based self-correction.
Towards mitigating LLM hallucina- tion via self reflection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Unleashing the True Potential of LLMs: A Feedback-Triggered Self-Correction with Long-Term Multipath Decoding
A feedback-triggered regeneration method combined with dynamic multipath decoding improves LLM accuracy on math and coding benchmarks compared to prompt-based self-correction.