Cover Image

AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Höth, Max Henning, Kersting, Kristian, Deiseroth, Björn, Parcalabescu, Letitia
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence Machine Learning I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bounding Hallucinations: Information-Theoretic Guarantees for RAG Systems via Merlin-Arthur Protocols
by: Deiseroth, Björn, et al.
Published: (2025)

On Measuring Faithfulness or Self-consistency of Natural Language Explanations
by: Parcalabescu, Letitia, et al.
Published: (2023)

Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?
by: Parcalabescu, Letitia, et al.
Published: (2024)

MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks
by: Parcalabescu, Letitia, et al.
Published: (2022)

Verbosity Tradeoffs and the Impact of Scale on the Faithfulness of LLM Self-Explanations
by: Siegel, Noah Y., et al.
Published: (2025)

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
by: Young, Richard J.
Published: (2026)

Temporal Knowledge Question Answering via Abstract Reasoning Induction
by: Chen, Ziyang, et al.
Published: (2023)

Measuring Reasoning Utility in LLMs via Conditional Entropy Reduction
by: Guo, Xu
Published: (2025)

RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
by: Saji, Alan, et al.
Published: (2025)

Text-Based Approaches to Item Difficulty Modeling in Large-Scale Assessments: A Systematic Review
by: Peters, Sydney, et al.
Published: (2025)

Learning When to Think: Shaping Adaptive Reasoning in R1-Style Models via Multi-Stage RL
by: Tu, Songjun, et al.
Published: (2025)

Detecting Hallucinations in Graph Retrieval-Augmented Generation via Attention Patterns and Semantic Alignment
by: Li, Shanghao, et al.
Published: (2025)

ReFactX: Scalable Reasoning with Reliable Facts via Constrained Generation
by: Pozzi, Riccardo, et al.
Published: (2025)

Evaluating Explainable AI Attribution Methods in Neural Machine Translation via Attention-Guided Knowledge Distillation
by: Nourbakhsh, Aria, et al.
Published: (2026)

PerCoR: Evaluating Commonsense Reasoning in Persian via Multiple-Choice Sentence Completion
by: Alikhani, Morteza, et al.
Published: (2025)

A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models
by: Balasubramanian, Sriram, et al.
Published: (2025)

UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning
by: Ovcharov, Volodymyr
Published: (2026)

ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models
by: Dumitru, Razvan-Gabriel, et al.
Published: (2025)

Teaching Probabilistic Logical Reasoning to Transformers
by: Nafar, Aliakbar, et al.
Published: (2023)

AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection
by: Nourbakhsh, Aria, et al.
Published: (2026)

Paying Attention to Deflections: Mining Pragmatic Nuances for Whataboutism Detection in Online Discourse
by: Phi, Khiem, et al.
Published: (2024)

On Explaining with Attention Matrices
by: Naim, Omar, et al.
Published: (2024)

Analyzing LLM Reasoning to Uncover Mental Health Stigma
by: Sankar, Sreehari, et al.
Published: (2026)

Beyond Prefixes: Graph-as-Memory Cross-Attention for Knowledge Graph Completion with Large Language Models
by: Liu, Ruitong, et al.
Published: (2025)

Enigme: Generative Text Puzzles for Evaluating Reasoning in Language Models
by: Hawkins, John
Published: (2025)

Residual Drift Dominates Contradiction in Multi-Turn Constraint Reasoning
by: Kawada, Sebastien
Published: (2026)

Reasoning over Uncertain Text by Generative Large Language Models
by: Nafar, Aliakbar, et al.
Published: (2024)

Search-R3: Unifying Reasoning and Embedding in Large Language Models
by: Gui, Yuntao, et al.
Published: (2025)

KisMATH: Do LLMs Have Knowledge of Implicit Structures in Mathematical Reasoning?
by: Saha, Soumadeep, et al.
Published: (2025)

A Survey of Task-Oriented Knowledge Graph Reasoning: Status, Applications, and Prospects
by: Niu, Guanglin, et al.
Published: (2025)

Beyond Token Length: Step Pruner for Efficient and Accurate Reasoning in Large Language Models
by: Wu, Canhui, et al.
Published: (2025)

Seemingly Plausible Distractors in Multi-Hop Reasoning: Are Large Language Models Attentive Readers?
by: Bhuiya, Neeladri, et al.
Published: (2024)

Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision Alignment
by: Su, Ruoxi, et al.
Published: (2026)

Attentive Reasoning Queries: A Systematic Method for Optimizing Instruction-Following in Large Language Models
by: Karov, Bar, et al.
Published: (2025)

Internal Reasoning vs. External Control: A Thermodynamic Analysis of Sycophancy in Large Language Models
by: Chang, Edward Y.
Published: (2025)

Low-Resource Court Judgment Summarization for Common Law Systems
by: Liu, Shuaiqi, et al.
Published: (2024)

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration
by: Yuan, Weikang, et al.
Published: (2024)

Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought
by: Tan, Xiaoyu, et al.
Published: (2024)

Evaluating the Efficacy of Hybrid Deep Learning Models in Distinguishing AI-Generated Text
by: Oketunji, Abiodun Finbarrs
Published: (2023)

SADAS: A Dialogue Assistant System Towards Remediating Norm Violations in Bilingual Socio-Cultural Conversations
by: Hua, Yuncheng, et al.
Published: (2024)