Cover Image

Are the Hidden States Hiding Something? Testing the Limits of Factuality-Encoding Capabilities in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Servedio, Giovanni, De Bellis, Alessandro, Di Palma, Dario, Anelli, Vito Walter, Di Noia, Tommaso
Format:	Preprint
Published:	2025
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

LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through Probing
by: Di Palma, Dario, et al.
Published: (2025)

Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Models
by: De Bellis, Alessandro, et al.
Published: (2025)

Exploring Diversity, Novelty, and Popularity Bias in ChatGPT's Recommendations
by: Di Palma, Dario, et al.
Published: (2026)

Evaluating ChatGPT as a Recommender System: A Rigorous Approach
by: Di Palma, Dario, et al.
Published: (2023)

RUVA: Personalized Transparent On-Device Graph Reasoning
by: Conte, Gabriele, et al.
Published: (2026)

The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI
by: Servedio, Giovanni, et al.
Published: (2026)

Exploring Approaches for Detecting Memorization of Recommender System Data in Large Language Models
by: Colacicco, Antonio, et al.
Published: (2026)

Do LLMs Memorize Recommendation Datasets? A Preliminary Study on MovieLens-1M
by: Di Palma, Dario, et al.
Published: (2025)

Scalable Cloud-Native Pipeline for Efficient 3D Model Reconstruction from Monocular Smartphone Images
by: Aghilar, Potito, et al.
Published: (2024)

GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models
by: Tritto, Mattia, et al.
Published: (2025)

Training-Free Consistency Pipeline for Fashion Repose
by: Aghilar, Potito, et al.
Published: (2025)

Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search
by: Attimonelli, Matteo, et al.
Published: (2025)

Challenging the Myth of Graph Collaborative Filtering: a Reasoned and Reproducibility-driven Analysis
by: Anelli, Vito Walter, et al.
Published: (2023)

XAI4LLM. Let Machine Learning Models and LLMs Collaborate for Enhanced In-Context Learning in Healthcare
by: Nazary, Fatemeh, et al.
Published: (2024)

Machine-learned Adversarial Attacks against Fault Prediction Systems in Smart Electrical Grids
by: Ardito, Carmelo, et al.
Published: (2023)

When Chain-of-Thought Fails, the Solution Hides in the Hidden States
by: Mehrafarin, Houman, et al.
Published: (2026)

Balancing Accuracy and Novelty with Sub-Item Popularity
by: Mallamaci, Chiara, et al.
Published: (2025)

Interactive Question Answering Systems: Literature Review
by: Biancofiore, Giovanni Maria, et al.
Published: (2022)

Enhancing Sequential Music Recommendation with Personalized Popularity Awareness
by: Abbattista, Davide, et al.
Published: (2024)

LLM Factoscope: Uncovering LLMs' Factual Discernment through Inner States Analysis
by: He, Jinwen, et al.
Published: (2023)

Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents
by: Turk, Matt
Published: (2026)

Inside-Out: Hidden Factual Knowledge in LLMs
by: Gekhman, Zorik, et al.
Published: (2025)

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

Is Factuality Enhancement a Free Lunch For LLMs? Better Factuality Can Lead to Worse Context-Faithfulness
by: Bi, Baolong, et al.
Published: (2024)

Mind Reading or Misreading? LLMs on the Big Five Personality Test
by: Di Cursi, Francesco, et al.
Published: (2025)

Factuality Challenges in the Era of Large Language Models
by: Augenstein, Isabelle, et al.
Published: (2023)

Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
by: Yang, Rui, et al.
Published: (2024)

Cognitive Limits Shape Language Statistics
by: Bellina, Alessandro, et al.
Published: (2025)

A Novel Evaluation Perspective on GNNs-based Recommender Systems through the Topology of the User-Item Graph
by: Malitesta, Daniele, et al.
Published: (2024)

How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMs
by: Feng, Guhao, et al.
Published: (2024)

Do Composed Image Retrieval Benchmarks Require Multimodal Composition?
by: Attimonelli, Matteo, et al.
Published: (2026)

I've got the "Answer"! Interpretation of LLMs Hidden States in Question Answering
by: Goloviznina, Valeriya, et al.
Published: (2024)

ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
by: Zhang, Zhenliang, et al.
Published: (2025)

X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs
by: Cao, Di, et al.
Published: (2026)

Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction
by: Wu, Shanglin, et al.
Published: (2025)

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
by: Zhang, Xiaoying, et al.
Published: (2024)

DyKnow: Dynamically Verifying Time-Sensitive Factual Knowledge in LLMs
by: Mousavi, Seyed Mahed, et al.
Published: (2024)

Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing
by: Zhang, Zhuoran, et al.
Published: (2024)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States
by: Sun, Yu, et al.
Published: (2024)

LLMs as Repositories of Factual Knowledge: Limitations and Solutions
by: Mousavi, Seyed Mahed, et al.
Published: (2025)