arXiv AI
Jul 17
Analytic Abduction: Causal Decomposition and Governed Commitment for Human--AI Coordination
arXiv:2607. 14641v1 Announce Type: new Abstract: Abductive reasoning operates in two directions.
A Minimal $\kappa$--$\tau$ Logic for Risk-Sensitive Abduction
arXiv:2608. 08192v1 Announce Type: new Abstract: Standard approaches to abductive reasoning can retain multiple candidate explanations, but they do not generally combine explicit compositional cross-hypothesis interaction with an internal, rival-sensitive commitment judgment.
Related stories
arXiv AI
Jun 30
Safety from Honesty in a Disinterested AI Predictor
arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
arXiv AI
6d ago
The Off-Support Barrier: Why Semantic Safety Constraints Are Not Learning-Problem Invariants, and What Follows for Prior Design, Containment, and Verification
arXiv:2608. 11243v1 Announce Type: new Abstract: We argue that a single structural fact organizes a wide range of phenomena in contemporary AI safety: a semantic safety constraint (e.
Hugging Face Trending Papers
Jun 28
Safety from Honesty in a Disinterested AI Predictor
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
arXiv AI
Jun 30
Reported Confidence in LLMs Tracks Commitment More Than Correctness
arXiv:2606. 29490v1 Announce Type: cross Abstract: Confidence is an estimate of the probability that a chosen answer is correct.
arXiv AI
1d ago
Incoherent by Design? On the Moral Self-Consistency of LLMs
arXiv:2608. 15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations.
arXiv Machine Learning
Jul 9
Final Checkpoints Are Not Enough: Analyzing Latent Reasoning Faithfulness Along Training Trajectories
arXiv:2607. 06648v1 Announce Type: new Abstract: Latent reasoning methods perform multi-step inference entirely in the model's continuous hidden states, promising more compact and efficient reasoning.
arXiv Machine Learning
Aug 4
Emergence Invariance: From Symbolized Thought to Interface Refinement
arXiv:2608. 01548v1 Announce Type: cross Abstract: Language can be viewed as a formalized subset of thought: a consequence-governed symbolic structure projected from wider situated cognition.
arXiv Machine Learning
Jun 25
Do Thinking Tokens Help with Safety?
arXiv:2606. 25013v1 Announce Type: new Abstract: Today's reasoning models use thinking tokens to attain stronger performance on benchmarks than their instruction-tuned counterparts.
arXiv AI
Jul 14
Scaffolding the Strategist: Architecture-Dependent Reasoning Interventions in Hotelling Spatial Markets
arXiv:2607. 09743v1 Announce Type: new Abstract: We investigate whether structured reasoning interventions improve the strategic economic reasoning of large language models, and whether their effects depend on model architecture.
arXiv Machine Learning
Jul 24
The Weight of Silence: A Causal Case for Weights Over the Scratchpad in Latent Chess Reasoning
arXiv:2607. 20952v1 Announce Type: new Abstract: Latent, or silent, reasoning lets language models carry out intermediate computation in continuous vector space instead of words, and is widely assumed to function as an internal scratchpad the model actively consults during inference.
arXiv AI
Jun 26
Narration-of-Thought: Inference-Time Scaffolding for Defeasible Ethical Reasoning in Large Language Models
arXiv:2606. 26366v1 Announce Type: new Abstract: Standard chain-of-thought on moral dilemmas exhibits two failure modes: stakeholder collapse (the trace names at most one party with a stake in the outcome) and uncertainty suppression (no explicit unknowns or hedges before committing to an action).