Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning

Documenti analoghi

• BenchGuard: Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
  di: Tu, Xinming, et al.
  Pubblicazione: (2026)
• IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models
  di: Imtiaz, Sayem Mohammad, et al.
  Pubblicazione: (2025)
• Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems
  di: Martinez, Matias, et al.
  Pubblicazione: (2025)
• Benchmarking Open-Source Safety Guard Models: A Comprehensive Evaluation
  di: Harsh, Reetu Raj, et al.
  Pubblicazione: (2026)
• Pragmatic Reasoning improves LLM Code Generation
  di: Cao, Zhuchen, et al.
  Pubblicazione: (2025)