Buchumschlag

Rethinking Prospect Theory for LLMs: Revealing the Instability of Decision-Making under Epistemic Uncertainty

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wang, Rui, Lin, Qihan, Liu, Jiayu, Zong, Qing, Zheng, Tianshi, Guo, Dadi, Shi, Haochen, Wang, Weiqi, Song, Yangqiu
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?
von: Liu, Jiayu, et al.
Veröffentlicht: (2025)

CritiCal: Can Critique Help LLM Uncertainty or Confidence Calibration?
von: Zong, Qing, et al.
Veröffentlicht: (2025)

Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observations
von: Li, Chunyang, et al.
Veröffentlicht: (2025)

ComparisonQA: Evaluating Factuality Robustness of LLMs Through Knowledge Frequency Control and Uncertainty
von: Zong, Qing, et al.
Veröffentlicht: (2024)

NAACL: Noise-AwAre Verbal Confidence Calibration for Robust LLMs in RAG Systems
von: Liu, Jiayu, et al.
Veröffentlicht: (2026)

INFERENCEDYNAMICS: Efficient Routing Across LLMs through Structured Capability and Knowledge Profiling
von: Shi, Haochen, et al.
Veröffentlicht: (2025)

KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?
von: Zheng, Tianshi, et al.
Veröffentlicht: (2024)

Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information
von: Yim, Yauwai, et al.
Veröffentlicht: (2024)

Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
von: Xu, Baixuan, et al.
Veröffentlicht: (2025)

MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset
von: Wang, Weiqi, et al.
Veröffentlicht: (2024)

Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework
von: Deng, Zheye, et al.
Veröffentlicht: (2025)

KNOWCOMP POKEMON Team at DialAM-2024: A Two-Stage Pipeline for Detecting Relations in Dialogical Argument Mining
von: Zheng, Zihao, et al.
Veröffentlicht: (2024)

DixitWorld: Evaluating Multimodal Abductive Reasoning in Vision-Language Models with Multi-Agent Dixit Gameplay
von: Mo, Yunxiang, et al.
Veröffentlicht: (2025)

Safety Compliance: Rethinking LLM Safety Reasoning through the Lens of Compliance
von: Hu, Wenbin, et al.
Veröffentlicht: (2025)

Decomposing Epistemic Uncertainty for Causal Decision Making
von: Rahman, Md Musfiqur, et al.
Veröffentlicht: (2026)

The Curse of CoT: On the Limitations of Chain-of-Thought in In-Context Learning
von: Zheng, Tianshi, et al.
Veröffentlicht: (2025)

From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
von: Zheng, Tianshi, et al.
Veröffentlicht: (2025)

The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas
von: Xu, Baixuan, et al.
Veröffentlicht: (2025)

LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game
von: Liang, Fangzhou, et al.
Veröffentlicht: (2025)

EcomEdit: An Automated E-commerce Knowledge Editing Framework for Enhanced Product and Purchase Intention Understanding
von: Lau, Ching Ming Samuel, et al.
Veröffentlicht: (2024)

Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
von: Zong, Chen-Chen, et al.
Veröffentlicht: (2025)

Decision Making under Cumulative Prospect Theory: An Alternating Direction Method of Multipliers
von: Cui, Xiangyu, et al.
Veröffentlicht: (2022)

Text-Tuple-Table: Towards Information Integration in Text-to-Table Generation via Global Tuple Extraction
von: Deng, Zheye, et al.
Veröffentlicht: (2024)

Rethinking Aleatoric and Epistemic Uncertainty
von: Smith, Freddie Bickford, et al.
Veröffentlicht: (2024)

GoldCoin: Grounding Large Language Models in Privacy Laws via Contextual Integrity Theory
von: Fan, Wei, et al.
Veröffentlicht: (2024)

AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph
von: Wang, Zhaowei, et al.
Veröffentlicht: (2023)

LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning
von: Zheng, Tianshi, et al.
Veröffentlicht: (2025)

Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
von: Yin, Hang, et al.
Veröffentlicht: (2023)

Acquiring and Modelling Abstract Commonsense Knowledge via Conceptualization
von: He, Mutian, et al.
Veröffentlicht: (2022)

Towards Subgraph Isomorphism Counting with Graph Kernels
von: Liu, Xin, et al.
Veröffentlicht: (2024)

ConKE: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
von: Zhang, Liyu, et al.
Veröffentlicht: (2024)

Advancing Abductive Reasoning in Knowledge Graphs through Complex Logical Hypothesis Generation
von: Bai, Jiaxin, et al.
Veröffentlicht: (2023)

Decision Making under Deep Uncertainty
Veröffentlicht: (2020)

Legal Rule Induction: Towards Generalizable Principle Discovery from Analogous Judicial Precedents
von: Fan, Wei, et al.
Veröffentlicht: (2025)

Measuring Epistemic Unfairness for Algorithmic Decision-Making
von: Quaresmini, Camilla, et al.
Veröffentlicht: (2026)

Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?
von: Wang, Qineng, et al.
Veröffentlicht: (2024)

Chain-of-Choice Hierarchical Policy Learning for Conversational Recommendation
von: Fan, Wei, et al.
Veröffentlicht: (2023)

CLR-Fact: Evaluating the Complex Logical Reasoning Capability of Large Language Models over Factual Knowledge
von: Zheng, Tianshi, et al.
Veröffentlicht: (2024)

When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure
von: Xiao, Boyu, et al.
Veröffentlicht: (2026)

Newsvendor Decisions under Stochastic and Strategic Uncertainties: Theory and Experimental Evidence
von: Wu, Hang, et al.
Veröffentlicht: (2025)