Cover Image

How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Adarsh, Shivam, Maistro, Maria, Lioma, Christina
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Reality Check on Context Utilisation for Retrieval-Augmented Generation
by: Hagström, Lovisa, et al.
Published: (2024)

Stairway to Fairness: Connecting Group and Individual Fairness
by: Rampisela, Theresia Veronika, et al.
Published: (2025)

TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
by: Wei, Zhepei, et al.
Published: (2025)

Testing the Limits of Truth Directions in LLMs
by: Poulis, Angelos, et al.
Published: (2026)

TruthFlow: Truthful LLM Generation via Representation Flow Correction
by: Wang, Hanyu, et al.
Published: (2025)

Truth is Universal: Robust Detection of Lies in LLMs
by: Bürger, Lennart, et al.
Published: (2024)

TruthStance: An Annotated Dataset of Conversations on Truth Social
by: Ameen, Fathima, et al.
Published: (2026)

TruthEval: A Dataset to Evaluate LLM Truthfulness and Reliability
by: Khatun, Aisha, et al.
Published: (2024)

Autonomous Evaluation of LLMs for Truth Maintenance and Reasoning Tasks
by: Karia, Rushang, et al.
Published: (2024)

Truth Knows No Language: Evaluating Truthfulness Beyond English
by: Figueras, Blanca Calvo, et al.
Published: (2025)

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models
by: Marjanović, Sara Vera, et al.
Published: (2024)

Graphing the Truth: Structured Visualizations for Automated Hallucination Detection in LLMs
by: Agrawal, Tanmay
Published: (2025)

Reasoning Isn't Enough: Examining Truth-Bias and Sycophancy in LLMs
by: Barkett, Emilio, et al.
Published: (2025)

Debating with More Persuasive LLMs Leads to More Truthful Answers
by: Khan, Akbir, et al.
Published: (2024)

Fact or Fiction? Can LLMs be Reliable Annotators for Political Truths?
by: Chatrath, Veronica, et al.
Published: (2024)

Ground Truth Generation for Multilingual Historical NLP using LLMs
by: Gladstone, Clovis, et al.
Published: (2025)

When Bias Pretends to Be Truth: How Spurious Correlations Undermine Hallucination Detection in LLMs
by: Wang, Shaowen, et al.
Published: (2025)

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
by: Chen, Zhongzhi, et al.
Published: (2023)

AggTruth: Contextual Hallucination Detection using Aggregated Attention Scores in LLMs
by: Matys, Piotr, et al.
Published: (2025)

How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
by: Du, Hongzhe, et al.
Published: (2025)

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
by: Zhang, Shaolei, et al.
Published: (2024)

Measuring Individual User Fairness with User Similarity and Effectiveness Disparity
by: Rampisela, Theresia Veronika, et al.
Published: (2026)

The Quest for Reliable Metrics of Responsible AI
by: Rampisela, Theresia Veronika, et al.
Published: (2025)

To Tell The Truth: Language of Deception and Language Models
by: Hazra, Sanchaita, et al.
Published: (2023)

Recon, Answer, Verify: Agents in Search of Truth
by: Shukla, Satyam, et al.
Published: (2025)

Truth, Trust, and Trouble: Medical AI on the Edge
by: Azeez, Mohammad Anas, et al.
Published: (2025)

As easy as PIE: understanding when pruning causes language models to disagree
by: Tropeano, Pietro, et al.
Published: (2025)

Soft Tokens, Hard Truths
by: Butt, Natasha, et al.
Published: (2025)

Collective Reasoning Among LLMs: A Framework for Answer Validation Without Ground Truth
by: Davoudi, Seyed Pouyan Mousavi, et al.
Published: (2025)

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
by: Luo, Wen, et al.
Published: (2026)

On the Relationship between Truth and Political Bias in Language Models
by: Fulay, Suyash, et al.
Published: (2024)

The Geometries of Truth Are Orthogonal Across Tasks
by: Azizian, Waiss, et al.
Published: (2025)

Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning
by: Wu, Tianyi, et al.
Published: (2025)

Towards Reliable Truth-Aligned Uncertainty Estimation in Large Language Models
by: Srey, Ponhvoan, et al.
Published: (2026)

TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment
by: Nguyen, Thi-Nhung, et al.
Published: (2026)

Meaning-infused grammar: Gradient Acceptability Shapes the Geometric Representations of Constructions in LLMs
by: Rakshit, Supantho, et al.
Published: (2025)

Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement
by: Lu, Yuxiao, et al.
Published: (2026)

SymLoc: Symbolic Localization of Hallucination across HaluEval and TruthfulQA
by: Lamba, Naveen, et al.
Published: (2025)

SH2: Self-Highlighted Hesitation Helps You Decode More Truthfully
by: Kai, Jushi, et al.
Published: (2024)

Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
by: Zhang, Kongcheng, et al.
Published: (2025)