BALTO projects claim-level verification into balanced token-level rewards for RL-based hallucination mitigation in LLMs.
Toward reliable scientific hypothesis generation: Evaluat- ing truthfulness and hallucination in large language models.arXiv preprint arXiv:2505.14599, 2025
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
-
BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation
BALTO projects claim-level verification into balanced token-level rewards for RL-based hallucination mitigation in LLMs.