The paper investigates whether the reasoning process in large language models mitigates or exacerbates bias. Using a within-model ablation on three high-stakes datasets (Adult, COMPAS, Credit) across three 32‑B models, the authors find that reasoning resolves some counterfactual fairness flips but creates roughly five times as many new flips at high confidence. They introduce two dynamic tools—Counterfactual Depth Probability Gap and Bias Transition Matrix—to trace how bias propagates and amplifies during reasoning depth and to explain the asymmetric dual effect.
arXiv:2606. 26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do.
Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items.
arXiv:2607. 18114v1 Announce Type: cross Abstract: Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer.
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.
arXiv:2607. 21433v1 Announce Type: cross Abstract: Chain-of-thought reasoning models such as DeepSeek-R1-Distill-Qwen-7B exhibit a bimodal convergence pattern: generations either terminate within a token budget (converged) or exhaust it without reaching a conclusion (non-converged).
arXiv:2607. 16451v1 Announce Type: cross Abstract: Chat models sometimes commit to an answer and then produce reasoning that justifies it rather than deriving it -- even when the answer contradicts a task premise.
arXiv:2607. 28319v1 Announce Type: cross Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs).
arXiv:2605. 03217v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased.
arXiv:2608. 13760v1 Announce Type: cross Abstract: Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors?
arXiv:2609.23065v1 Announce Type: cross Abstract: Chain-of-thought (CoT) can sound plausible yet be unfaithful to the model's underlying reasoning. Most prior work probes CoT faithfulness through inp...
Modern LLMs are alarmingly susceptible to surprisingly simple immaterial changes of input prompts: a casual hint, an incorrectly labeled few-shot example, or a fake prior assistant turn often flips an originally correct answer. We study where this susceptibility, spanning sycophancy and related cue-induced biases, lives inside the model.
arXiv:2607. 05861v1 Announce Type: cross Abstract: Large reasoning models (LRMs) improve language model capabilities by generating explicit thinking traces before final answers.