arXiv Computation and Language August 27, 2026 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 17

BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs

arXiv:2608. 14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications.

By Varsha Ramineni, Hossein A. Rahmani, Jerome Ramos, Karin Sevegnani, Emine Yilmaz

llms safety

arXiv AI

Jun 15

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

arXiv:2603. 05167v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as judges of chain-of-thought (CoT) reasoning, yet it remains unclear whether they can reliably assess process faithfulness rather than merely answer plausibility.

By Avni Mittal, Rauno Arike

llms benchmarks

arXiv AI

Oct 31

The Anatomy of Socio-Demographics in Pluralistic Offensiveness Modeling: When and Where It Helps, and the Role of Reasoning

The study investigates how socio-demographic data can improve pluralistic offensiveness modeling. It finds that demographic information yields modest, inconsistent gains for individual predictions but clearer benefits at group and population levels due to aggregation. By explicitly reasoning about baseline judgments and demographic-specific deviations, the authors show that both components improve predictions, and that reasoning outperforms simple conditioning on demographics.

By Yifan Wang, Leixin Zhang, Jinyi Mu, Yu Wang, Mayank Jobanputra, Isabel Valera, Vera Demberg

llms

arXiv Machine Learning

Aug 7

Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning

arXiv:2608. 05166v1 Announce Type: cross Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings.

By Sachini Weerasekara, Sagar Kamarthi, Jacqueline Isaacs

llms benchmarks safety

arXiv AI

Jul 14

Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

arXiv:2607. 11266v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to over-reasoning: the generation of redundant, verbose, or irrelevant steps.

By Daeyeop Lee, Hwanjo Yu

llms efficiency benchmarks

arXiv AI

Jun 11

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models

arXiv:2606. 11211v1 Announce Type: cross Abstract: The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment.

By Prakul Sunil Hiremath, Harshit R. Hiremath

llms

One email a morning, machine-written

Related stories

BiasTrace: Linking Reasoning Behaviours to Biased Outputs in LLMs

C2-Faith: Benchmarking LLM Judges for Causal and Coverage Faithfulness in Chain-of-Thought Reasoning

The Anatomy of Socio-Demographics in Pluralistic Offensiveness Modeling: When and Where It Helps, and the Role of Reasoning

Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning

Valid $\ne$ Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought

Calibration Drift Under Reasoning: How Chain-of-Thought Budgets Induce Overconfidence in Large Language Models