SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
Backtracking improves generation safety.arXiv preprint arXiv:2409.14586
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Training LLMs to verbalize uncertainty explicitly at the end or during reasoning reduces overconfident errors and improves answer quality on factual tasks while enabling RAG triggers.
citing papers explorer
-
Addressing Over-Refusal in LLMs with Competing Rewards
SEAR trains one LLM via adversarial process rewards to explore harmful reasoning paths but flip to safe outputs, reducing over-refusal while preserving safety.
-
LLMs Should Express Uncertainty Explicitly
Training LLMs to verbalize uncertainty explicitly at the end or during reasoning reduces overconfident errors and improves answer quality on factual tasks while enabling RAG triggers.