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.
arXiv:2608. 14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications.
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.
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.
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.
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.
arXiv:2606. 11211v1 Announce Type: cross Abstract: The ability of large language models (LLMs) to express calibrated uncertainty is important for safe deployment.
The paper introduces a method for analyzing how interventions in a prompt affect a language model’s reasoning by using behavioral counterfactuals. It trains a module to edit the residual stream so that the next-token distributions for a fixed response match between a source and a counterfactual prompt, outperforming standard activation reconstruction. The resulting attribution maps and visualizations help identify causally important locations for counterfactual recovery and guide hypothesis testing with activation patching, as demonstrated in a case study on Gemma-4-E4B-it and DeepSeek-R1-0528-Qwen3-8B.
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.
Faithfully understanding the internal process that occurs as models form their chain of thought is an important problem with the rise in model capabilities. However, this remains challenging due to th...
arXiv:2510.15144v4 Announce Type: replace Abstract: Simulating human reasoning in open-ended tasks has long been a central aspiration in AI and cognitive science. While large language models now appr...
Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of newer evidence. Although recent studies have exami...
arXiv:2602. 20710v2 Announce Type: replace Abstract: Inspecting Chain-of-Thought reasoning is among the most common means of understanding why an LLM produced its output.