arXiv:2608. 14004v1 Announce Type: new Abstract: In-context learning is commonly formalized as inference from examples of a function.
arXiv:2605. 11644v3 Announce Type: replace-cross Abstract: Positive data can show that two tuple occurrences share a successful sentence context without certifying that they are safely interchangeable.
arXiv:2606. 07623v1 Announce Type: new Abstract: This paper develops a model-theoretic framework for verifying context-conditioned language-model behavior by replacing benchmark labels with finite semantic certificates.
arXiv:2607. 06407v1 Announce Type: new Abstract: The XAI community has studied a wide range of queries and scores for explaining predictions of ML models.
arXiv:2607. 21183v1 Announce Type: cross Abstract: The propositional abduction problem is a well-known form of non-monotonic reasoning where we are asked to find an explanation of a given manifestation.
arXiv:2604. 17621v2 Announce Type: replace Abstract: Many real-world questions appear deceptively simple yet implicitly demand two capabilities: (i) systematic coverage of a bounded knowledge universe and (ii) compositional set-based reasoning over that universe, a phenomenon we term "the tip of the iceberg.
The paper introduces SAGE, a framework designed to reduce long‑horizon reasoning biases in large language models. It identifies two key biases—exploration bias and compounding bias—arising from complex reasoning spaces and sparse rewards, and proposes Symbolic Closure Analysis (SCA) to understand these effects. SAGE applies algebraic sparsification and hyperbolic structural guidance to suppress spurious branching and provide dense depth‑wise signals, achieving up to an eight‑fold improvement on the Andrews‑Curtis problem across multiple benchmarks and model families.
The paper introduces DODR, a deterministic operator‑driven reasoning architecture that models reasoning as graph computations in a high‑dimensional linear‑algebraic space, replacing token‑level sampling with matrix operations. Reasoning states are snapshot vectors of semantic units, and three trainable matrix operators—deduction, induction, and abduction—implement Peirce’s inference types. Experiments on 503 records demonstrate near‑perfect deduction, high generalization for induction, and significant gains for abduction, while the design guarantees zero hallucination and supports continual learning.
The paper introduces F-ICL, a benchmark that measures in‑context algorithmic reasoning in language models by exhaustively enumerating 86 million valid programs of length ≤13 on a Turing‑complete machine and computing the exact posterior under a bounded Levin–Solomonoff prior. Unlike typical benchmarks, F‑ICL provides a distributional reference rather than just answers, allowing the evaluation of models’ inductive priors. Across 105 configurations of models ranging from 0.8 B to 675 B parameters, models achieve up to 92 % accuracy, yet many still deviate from the Bayes‑optimal reference, and the study derives theoretical bounds on cumulative loss for predictors with positive prior weight on the reference.
Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a fundamental constraint: language is a compressed and capacity-limited interface for conveying task information.
arXiv:2601. 18747v2 Announce Type: replace-cross Abstract: Modern AI agents increasingly rely on search infrastructure to execute complex, neuro-symbolic reasoning workflows.
The paper introduces ramework, a blackbox prompt‑minimization framework that identifies the minimal subset of few‑shot prompts necessary for large language models (LLMs). In a case study, the framework reduces few‑shot exemplars by an average of 65.3% in character count while maintaining full propositional output fidelity, revealing that models tend to keep logical identifiers and constraint declarations while discarding natural language prose. The analysis further distinguishes between universal encoder and decoder models, offering insights into prompt compression and structural analysis.
The paper introduces GUARD, a neuro‑symbolic system that autoformalizes argumentative material by completing missing premises (guards) before formal verification. It uses large language models to generate candidate guards, Isabelle/HOL to verify them, and a contrastive test to ensure the proof depends on the original premises and does not over‑generalize. Experiments on Debatepedia and ARCT show that GUARD improves verified‑faithful scores by over 30 points and reduces leakage by about 20 points compared to prior LLM‑driven theorem proving methods.