Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items.
arXiv:2606. 26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do.
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: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:2506. 21571v3 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs), which autonomously produce a reasoning Chain of Thought (CoT) before producing final responses, offer a promising approach to interpreting and monitoring model behaviors.
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:2608.28623v2 Announce Type: replace-cross Abstract: Large multimodal reasoning models (LMRMs) are increasingly capable, largely through generating explicit chain-of-thought reasoning before ans...
The study investigates how limited reading capacity and claim wording influence consensus outcomes in language‑model networks. By modeling message capacity as the number of messages an agent reads, the authors show that when agents read fewer than about 6.4 messages on average, a wrong consensus becomes unreachable. However, the wording of a claim—its inherent threshold—can override this effect, leading to incorrect consensus even when most agents start correct.
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:2609.22090v1 Announce Type: new Abstract: An LLM producing the response pattern associated with a human psychological effect is not the same claim as the LLM possessing that bias. We present Ps...
arXiv:2608. 11797v1 Announce Type: new Abstract: Model merging by task arithmetic works until it doesn't, and the field diagnoses why with magnitudes: layerwise representation bias, deviations from cross-task linearity, parameter overlap.
LLM agents increasingly maintain personal memory across sessions, but it can conflict. Preferences depend on context, behavior evolves, and sources can conflict. When a query lacks context, time, or s...
The study investigates how demographic identity is represented in a language model, using representational similarity analysis against Pew survey data across 169 demographic cells. It finds that standard last‑token read‑outs underestimate the model’s fidelity, while specific attention heads (notably L11 H16) capture demographic structure more accurately, though race‑based types remain weak. Causal interventions reveal that high fidelity does not guarantee causal use, and a 128‑dimensional probe of a single head improves alignment with survey truth but fails to recover per‑question group ordering.