Image de couverture de livre

Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yin, Fan, Srinivasa, Jayanth, Chang, Kai-Wei
Format:	Preprint
Publié:	2024
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

Less is More: Local Intrinsic Dimensions of Contextual Language Models
par: Ruppik, Benjamin Matthias, et autres
Publié: (2025)

Attention Reveals More Than Tokens: Training-Free Long-Context Reasoning with Attention-guided Retrieval
par: Zhang, Yuwei, et autres
Publié: (2025)

Memorization in Language Models through the Lens of Intrinsic Dimension
par: Arnold, Stefan
Publié: (2025)

A Comparative Study of Learning Paradigms in Large Language Models via Intrinsic Dimension
par: Janapati, Saahith, et autres
Publié: (2024)

LLMs Lean on Priors, Not Programming Language Semantics
par: Thimmaiah, Aditya, et autres
Publié: (2025)

The Hard Positive Truth about Vision-Language Compositionality
par: Kamath, Amita, et autres
Publié: (2024)

Machine Bullshit: Characterizing the Emergent Disregard for Truth in Large Language Models
par: Liang, Kaiqu, et autres
Publié: (2025)

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations
par: Luo, Wen, et autres
Publié: (2026)

Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models
par: Mohan, Jayanth, et autres
Publié: (2025)

Representational and Behavioral Stability of Truth in Large Language Models
par: Dies, Samantha, et autres
Publié: (2025)

Enhancing Large Vision Language Models with Self-Training on Image Comprehension
par: Deng, Yihe, et autres
Publié: (2024)

Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models
par: Vazhentsev, Artem, et autres
Publié: (2024)

KatotohananQA: Evaluating Truthfulness of Large Language Models in Filipino
par: Nery, Lorenzo Alfred, et autres
Publié: (2025)

A Retrieve-and-Read Framework for Knowledge Graph Link Prediction
par: Pahuja, Vardaan, et autres
Publié: (2022)

Improving Factuality in Large Language Models via Decoding-Time Hallucinatory and Truthful Comparators
par: Yang, Dingkang, et autres
Publié: (2024)

On Prompt-Driven Safeguarding for Large Language Models
par: Zheng, Chujie, et autres
Publié: (2024)

Open-world Multi-label Text Classification with Extremely Weak Supervision
par: Li, Xintong, et autres
Publié: (2024)

Re-Search for The Truth: Multi-round Retrieval-augmented Large Language Models are Strong Fake News Detectors
par: Li, Guanghua, et autres
Publié: (2024)

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space
par: Zhang, Shaolei, et autres
Publié: (2024)

Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models
par: Xiong, Guangzhi, et autres
Publié: (2025)

Control Large Language Models via Divide and Conquer
par: Li, Bingxuan, et autres
Publié: (2024)

Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
par: Gu, Jia-Chen, et autres
Publié: (2024)

Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning
par: Chen, Zhongzhi, et autres
Publié: (2023)

From Yes-Men to Truth-Tellers: Addressing Sycophancy in Large Language Models with Pinpoint Tuning
par: Chen, Wei, et autres
Publié: (2024)

On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation
par: Wu, Di, et autres
Publié: (2024)

When Truth Is Overridden: Uncovering the Internal Origins of Sycophancy in Large Language Models
par: Wang, Keyu, et autres
Publié: (2025)

ARREST: Adversarial Resilient Regulation Enhancing Safety and Truth in Large Language Models
par: Dasgupta, Sharanya, et autres
Publié: (2026)

Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Study
par: Wu, Di, et autres
Publié: (2022)

Geometry-Guided Adversarial Prompt Detection via Curvature and Local Intrinsic Dimension
par: Yung, Canaan, et autres
Publié: (2025)

CDEval: A Benchmark for Measuring the Cultural Dimensions of Large Language Models
par: Wang, Yuhang, et autres
Publié: (2023)

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation
par: Wu, Di, et autres
Publié: (2024)

Can Small Language Models Help Large Language Models Reason Better?: LM-Guided Chain-of-Thought
par: Lee, Jooyoung, et autres
Publié: (2024)

Large Language Model Instruction Following: A Survey of Progresses and Challenges
par: Lou, Renze, et autres
Publié: (2023)

Ranking Large Language Models without Ground Truth
par: Dhurandhar, Amit, et autres
Publié: (2024)

Answer is All You Need: Instruction-following Text Embedding via Answering the Question
par: Peng, Letian, et autres
Publié: (2024)

FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments
par: Saeidi, Amir, et autres
Publié: (2026)

From General to Specific: Tailoring Large Language Models for Personalized Healthcare
par: Shi, Ruize, et autres
Publié: (2024)

Debating Truth: Debate-driven Claim Verification with Multiple Large Language Model Agents
par: He, Haorui, et autres
Publié: (2025)

DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
par: Gao, Shangqian, et autres
Publié: (2024)

Emergence of Linear Truth Encodings in Language Models
par: Ravfogel, Shauli, et autres
Publié: (2025)