Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifying counterfactual report mediators that hold a model's reports to a causal contract: invariant to forbidden influences (pressure, prestige, restyling) and responsive to licensed ones (genuine evidence).
arXiv:2607. 12985v1 Announce Type: new Abstract: Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged.
By Sen Yang, Yuen-Hei Yeung
arXiv:2607. 29484v1 Announce Type: cross Abstract: Interventional data is widely regarded as the gold standard for teaching models causal reasoning.
By Xining Xun
The study investigates whether the reasoning steps a language model writes are causally responsible for its answers. Using a causal intervention method on the activation stream, the authors find that for Qwen3-4B, about 77% of stated steps are causally load‑bearing, while behavioral tests overestimate this by roughly 11 percentage points. The faithfulness of reasoning decreases with model size and depth of reasoning, especially for the smaller Qwen3-1.7B.
By Abhiram Bhupatiraju, Rayan Nyaupane
arXiv:2609.05834v1 Announce Type: new
Abstract: World models promise a general route to embodied intelligence: learn predictive dynamics once, then reason, plan, and act with them. Increasingly, the...
By Todd Y. Zhou, Daniel Zhang
arXiv:2608. 06425v1 Announce Type: cross Abstract: Comprehensive affective analysis is challenging for two reasons: it spans heterogeneous prediction tasks with continuous, ordinal, and multi-label outputs, and affective meaning is context-dependent, requiring conflicting cues to be reconciled rather than mapped directly to labels.
By Tianlei Zhu, Zhiwei Liu, Yuyan Wang, Xiao-Yang Liu, Sophia Ananiadou
arXiv:2503. 13445v3 Announce Type: replace-cross Abstract: When asked to explain their decisions, LLMs can often give explanations which sound plausible to humans.
By Noah Y. Siegel, Nicolas Heess, Maria Perez-Ortiz, Oana-Maria Camburu
arXiv:2605.11467v2 Announce Type: replace-cross
Abstract: Reasoning models post-hoc rationalize answers they have already committed to internally, producing chains of *reasoning theater*: deliberativ...
By Swapnil Parekh, Naman Goyal
arXiv:2609.39702v1 Announce Type: new
Abstract: Adapting a language model to a specialized corpus means choosing which instruction-tuning tasks to train on under a fixed budget, and testing one choic...
By Nima H. Siboni, Vahid Rostami
The paper introduces PACT, a method for unlearning deceptive behaviors in large language models by using contrastive forget sets that compare a model’s responses under deceptive and neutral contexts. PACT trains the model to produce pressure‑aware counterfactual targets, preserving benign system‑prompt adherence and reasoning traces while dramatically reducing deception rates from over 50% to under 3% on 32B reasoning models.
By Haoran Tang, Rajiv Khanna
arXiv:2607. 29062v1 Announce Type: new Abstract: Model capabilities have improved in large part due to scaling chain of thought.
By Matthew Nguyen, Kyle Cox, Austin Meek, Iv\'an Arcuschin
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.
By Peter Hase, Christopher Potts