Image de couverture de livre

Balancing Truthfulness and Informativeness with Uncertainty-Aware Instruction Fine-Tuning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Tianyi, Ni, Jingwei, Hooi, Bryan, Zhang, Jiaheng, Ash, Elliott, Ng, See-Kiong, Sachan, Mrinmaya, Leippold, Markus
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ReProbe: Efficient Test-Time Scaling of Multi-Step Reasoning by Probing Internal States of Large Language Models
par: Ni, Jingwei, et autres
Publié: (2025)

AFaCTA: Assisting the Annotation of Factual Claim Detection with Reliable LLM Annotators
par: Ni, Jingwei, et autres
Publié: (2024)

DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation
par: Ni, Jingwei, et autres
Publié: (2024)

Can Reasoning Help Large Language Models Capture Human Annotator Disagreement?
par: Ni, Jingwei, et autres
Publié: (2025)

Geneshift: Impact of different scenario shift on Jailbreaking LLM
par: Wu, Tianyi, et autres
Publié: (2025)

Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering
par: Schimanski, Tobias, et autres
Publié: (2024)

Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
par: Zhao, James Xu, et autres
Publié: (2025)

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
par: Hu, Zhiyuan, et autres
Publié: (2024)

pdfQA: Diverse, Challenging, and Realistic Question Answering over PDFs
par: Schimanski, Tobias, et autres
Publié: (2026)

Co-DETECT: Collaborative Discovery of Edge Cases in Text Classification
par: Xiong, Chenfei, et autres
Publié: (2025)

The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure
par: Fan, Yu, et autres
Publié: (2025)

How Does Response Length Affect Long-Form Factuality
par: Zhao, James Xu, et autres
Publié: (2025)

Investigating the Zone of Proximal Development of Language Models for In-Context Learning
par: Cui, Peng, et autres
Publié: (2025)

CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
par: Fu, Jinlan, et autres
Publié: (2025)

Guiding VLM Agents with Process Rewards at Inference Time for GUI Navigation
par: Hu, Zhiyuan, et autres
Publié: (2025)

Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
par: Wu, Tianyi, et autres
Publié: (2026)

LEXam: Benchmarking Legal Reasoning on 340 Law Exams
par: Fan, Yu, et autres
Publié: (2025)

Spatio-Temporal Foundation Models: Vision, Challenges, and Opportunities
par: Goodge, Adam, et autres
Publié: (2025)

Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
par: Hu, Zhiyuan, et autres
Publié: (2026)

AI-Assisted Human Evaluation of Machine Translation
par: Zouhar, Vilém, et autres
Publié: (2024)

How to Select Datapoints for Efficient Human Evaluation of NLG Models?
par: Zouhar, Vilém, et autres
Publié: (2025)

TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs
par: Wang, Cheng, et autres
Publié: (2024)

Probing for Arithmetic Errors in Language Models
par: Sun, Yucheng, et autres
Publié: (2025)

Automated Knowledge Concept Annotation and Question Representation Learning for Knowledge Tracing
par: Ozyurt, Yilmazcan, et autres
Publié: (2024)

Uncertainty-Aware Attention Heads: Efficient Unsupervised Uncertainty Quantification for LLMs
par: Vazhentsev, Artem, et autres
Publié: (2025)

Exploring Nature: Datasets and Models for Analyzing Nature-Related Disclosures
par: Schimanski, Tobias, et autres
Publié: (2023)

On the Multi-turn Instruction Following for Conversational Web Agents
par: Deng, Yang, et autres
Publié: (2024)

LETGAMES: An LLM-Powered Gamified Approach to Cognitive Training for Patients with Cognitive Impairment
par: Shi, Jingwei, et autres
Publié: (2026)

CET2: Modelling Topic Transitions for Coherent and Engaging Knowledge-Grounded Conversations
par: Xu, Lin, et autres
Publié: (2024)

Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering
par: Zhang, Weikang, et autres
Publié: (2026)

Towards Proactive Information Probing: Customer Service Chatbots Harvesting Value from Conversation
par: Huang, Chen, et autres
Publié: (2026)

Confidence Elicitation: A New Attack Vector for Large Language Models
par: Formento, Brian, et autres
Publié: (2025)

Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
par: Do, Heejin, et autres
Publié: (2026)

Faithfulness-Aware Uncertainty Quantification for Fact-Checking the Output of Retrieval Augmented Generation
par: Fadeeva, Ekaterina, et autres
Publié: (2025)

AutoTutor meets Large Language Models: A Language Model Tutor with Rich Pedagogy and Guardrails
par: Chowdhury, Sankalan Pal, et autres
Publié: (2024)

Efficiently Computing Susceptibility to Context in Language Models
par: Liu, Tianyu, et autres
Publié: (2024)

Grammar Control in Dialogue Response Generation for Language Learning Chatbots
par: Glandorf, Dominik, et autres
Publié: (2025)

World Models for Math Story Problems
par: Opedal, Andreas, et autres
Publié: (2023)

Balancing Continuous Pre-Training and Instruction Fine-Tuning: Optimizing Instruction-Following in LLMs
par: Jindal, Ishan, et autres
Publié: (2024)

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
par: Hu, Zhiyuan, et autres
Publié: (2024)