pith. sign in

Self-consistency of the internal reward models improves self-rewarding language models

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.AI 1 cs.LG 1

years

2026 1 2025 1

roles

background 1

polarities

background 1

representative citing papers

Can LLMs Learn to Reason Robustly under Noisy Supervision?

cs.LG · 2026-04-05 · conditional · novelty 6.0

Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning benchmarks even at high noise levels.

citing papers explorer

Showing 2 of 2 citing papers.

  • Can LLMs Learn to Reason Robustly under Noisy Supervision? cs.LG · 2026-04-05 · conditional · none · ref 36

    Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning benchmarks even at high noise levels.

  • From System 1 to System 2: A Survey of Reasoning Large Language Models cs.AI · 2025-02-24 · accept · none · ref 171

    The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.