conftrace_

reasoning alignment

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

decision criteria injection (1) heuristic shortcut (1) adversarial prompt attack (1) goal hijacking (1) step-level reasoning (1) outcome reward model (1) small language model (1) test-time scaling (1) process reward model (1) reasoning ability (1)

Papers

A Comprehensive Survey of Process Reward Models: Data Generation, Model Construction, and Usage ACL 2026 Reasoning Hijacking: The Fragility of Reasoning Alignment in Large Language Models ACL 2026 Self-Refine Instruction-Tuning for Aligning Reasoning in Language Models EMNLP 2024