Image de couverture de livre

Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Aljaafari, Nura, Valentino, Marco, Freitas, André
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Interpreting token compositionality in LLMs: A robustness analysis
par: Aljaafari, Nura, et autres
Publié: (2024)

TRACE: Training and Inference-Time Interpretability Analysis for Language Models
par: Aljaafari, Nura, et autres
Publié: (2025)

Emergence and Localisation of Semantic Role Circuits in LLMs
par: Aljaafari, Nura, et autres
Publié: (2025)

The Mechanics of Conceptual Interpretation in GPT Models: Interpretative Insights
par: Aljaafari, Nura, et autres
Publié: (2024)

TRACE for Tracking the Emergence of Semantic Representations in Transformers
par: Aljaafari, Nura, et autres
Publié: (2025)

CARMA: Enhanced Compositionality in LLMs via Advanced Regularisation and Mutual Information Alignment
par: Aljaafari, Nura, et autres
Publié: (2025)

From Circuit Evidence to Mechanistic Theory: An Inductive Logic Approach
par: Aljaafari, Nura, et autres
Publié: (2026)

Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inference
par: Kim, Geonhee, et autres
Publié: (2024)

Autoformalization in the Wild: Assessing LLMs on Real-World Mathematical Definitions
par: Zhang, Lan, et autres
Publié: (2025)

SemEval-2024 Task 2: Safe Biomedical Natural Language Inference for Clinical Trials
par: Jullien, Mael, et autres
Publié: (2024)

A Differentiable Integer Linear Programming Solver for Explanation-Based Natural Language Inference
par: Thayaparan, Mokanarangan, et autres
Publié: (2024)

Inferring Latent Intentions: Attributional Natural Language Inference in LLM Agents
par: Quan, Xin, et autres
Publié: (2026)

Decompose-and-Formalise: Recursively Verifiable Natural Language Inference
par: Quan, Xin, et autres
Publié: (2026)

Reasoning with Natural Language Explanations
par: Valentino, Marco, et autres
Publié: (2024)

Inference to the Best Explanation in Large Language Models
par: Dalal, Dhairya, et autres
Publié: (2024)

Monotonic Reference-Free Refinement for Autoformalization
par: Zhang, Lan, et autres
Publié: (2026)

Estimating the Causal Effects of Natural Logic Features in Neural NLI Models
par: Rozanova, Julia, et autres
Publié: (2023)

Estimating the Causal Effects of Natural Logic Features in Transformer-Based NLI Models
par: Rozanova, Julia, et autres
Publié: (2024)

Beyond Gold Standards: Epistemic Ensemble of LLM Judges for Formal Mathematical Reasoning
par: Zhang, Lan, et autres
Publié: (2025)

Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
par: Ranaldi, Leonardo, et autres
Publié: (2025)

MASA: LLM-Driven Multi-Agent Systems for Autoformalization
par: Zhang, Lan, et autres
Publié: (2025)

Integrating Expert Knowledge into Logical Programs via LLMs
par: Górski, Franciszek, et autres
Publié: (2025)

Improving Semantic Control in Discrete Latent Spaces with Transformer Quantized Variational Autoencoders
par: Zhang, Yingji, et autres
Publié: (2024)

Controlling Equational Reasoning in Large Language Models with Prompt Interventions
par: Meadows, Jordan, et autres
Publié: (2023)

Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitions
par: Valentino, Marco, et autres
Publié: (2023)

Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations
par: Ranaldi, Leonardo, et autres
Publié: (2024)

Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
par: Zhang, Yingji, et autres
Publié: (2025)

Adaptive LLM-Symbolic Reasoning via Dynamic Logical Solver Composition
par: Xu, Lei, et autres
Publié: (2025)

A Symbolic Framework for Evaluating Mathematical Reasoning and Generalisation with Transformers
par: Meadows, Jordan, et autres
Publié: (2023)

Dissecting Clinical Reasoning in Language Models: A Comparative Study of Prompts and Model Adaptation Strategies
par: Jullien, Mael, et autres
Publié: (2025)

Verification and Refinement of Natural Language Explanations through LLM-Symbolic Theorem Proving
par: Quan, Xin, et autres
Publié: (2024)

Enhancing Ethical Explanations of Large Language Models through Iterative Symbolic Refinement
par: Quan, Xin, et autres
Publié: (2024)

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective
par: Chandna, Bhavik, et autres
Publié: (2025)

SylloBio-NLI: Evaluating Large Language Models on Biomedical Syllogistic Reasoning
par: Wysocka, Magdalena, et autres
Publié: (2024)

Mechanistic Interpretability of Emotion Inference in Large Language Models
par: Tak, Ala N., et autres
Publié: (2025)

Faithful and Robust LLM-Driven Theorem Proving for NLI Explanations
par: Quan, Xin, et autres
Publié: (2025)

From Syntax to Emotion: A Mechanistic Analysis of Emotion Inference in LLMs
par: Shu, Bangzhao, et autres
Publié: (2026)

Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering
par: Yu, Zeping, et autres
Publié: (2024)

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
par: Valentino, Marco, et autres
Publié: (2025)

PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
par: Quan, Xin, et autres
Publié: (2025)