conftrace_

stem reasoning

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) paradox resolution (1) process-outcome alignment (1) derivation verification (1) verifier accuracy (1) reinforcement learning with verifiable reward (1) confidence-aware reasoning (1) ppo training (1) reasoning capabilities (1) confidence estimation (1)

Papers

ParaSuite: Boosting LLM Reasoning via Paradox Resolution ACL 2026 PRIME: A Process-Outcome Alignment Benchmark for Verifiable Reasoning in Mathematics and Engineering ACL 2026 Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning EMNLP 2025