arXiv Computation and Language By Nayoung Kim, Mickey Mancenido, Huan Liu

Adaptive Triggering for Bias Correction in LLM Reasoning

Read the original on arXiv Computation and Language →

The paper introduces an adaptive triggering mechanism for bias correction in large language model (LLM) reasoning. By framing bias intervention as an online change‑point detection problem, the authors update a CUSUM statistic at each step using either a white‑box next‑token probability signal or a black‑box LLM judge signal, and inject corrective prompts only when the accumulated evidence exceeds a calibrated threshold. Experiments on gpt‑4o‑mini and six open‑weight models show that adaptive black‑box triggering restores most of the accuracy lost by fixed‑interval interventions while reducing the number of corrections, whereas the white‑box signal improves ambiguous‑item accuracy but can hurt disambiguated‑item accuracy due to difficulty distinguishing stereotype reliance from correct evidence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
Aug 12

UPAIR: Diagnosing Reasoning States via Uncertainty-Progress Alignment for Selective Intervention

arXiv:2607. 17188v2 Announce Type: replace Abstract: While test-time scaling improves the problem-solving ability of large reasoning models (LRMs) through additional inference-time computation, it can also exacerbate overthinking and underthinking, which we formulate as reasoning state--action mismatch.

By Cheng Yan, Zhijun Fan, Guangyang Ye, Fan Xu, Xiang Xia, Yawei Wang, Wuyang Zhang