Cover Image

Beyond Surface Statistics: Robust Conformal Prediction for LLMs via Internal Representations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Yanli, Kuang, Peng, Han, Xiaoyu, Xu, Kaidi, Wang, Haohan
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

Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling
by: Kuang, Peng, et al.
Published: (2025)

TECP: Token-Entropy Conformal Prediction for LLMs
by: Xu, Beining, et al.
Published: (2025)

Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension Ability
by: Han, Yujin, et al.
Published: (2024)

Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems
by: Jin, Haibo, et al.
Published: (2026)

Dialogue is Better Than Monologue: Instructing Medical LLMs via Strategical Conversations
by: Liu, Zijie, et al.
Published: (2025)

Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
by: Zhang, Zhuoxuan, et al.
Published: (2025)

SConU: Selective Conformal Uncertainty in Large Language Models
by: Wang, Zhiyuan, et al.
Published: (2025)

Beyond Words: A Latent Memory Approach to Internal Reasoning in LLMs
by: Orlicki, José I.
Published: (2025)

Beyond Prompting: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration (LOGIC)
by: Wang, Peidong
Published: (2026)

Principled Context Engineering for RAG: Statistical Guarantees via Conformal Prediction
by: Chakraborty, Debashish, et al.
Published: (2025)

Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
by: Yu, Ye, et al.
Published: (2026)

TriEx: A Game-based Tri-View Framework for Explaining Internal Reasoning in Multi-Agent LLMs
by: Wang, Ziyi, et al.
Published: (2026)

Probing the Lack of Stable Internal Beliefs in LLMs
by: Luo, Yifan, et al.
Published: (2026)

ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees
by: Wang, Zhiyuan, et al.
Published: (2024)

An Empirical Study of Conformal Prediction in LLM with ASP Scaffolds for Robust Reasoning
by: Kaur, Navdeep, et al.
Published: (2025)

Training LLMs Beyond Next Token Prediction -- Filling the Mutual Information Gap
by: Yang, Chun-Hao, et al.
Published: (2025)

Hallucination Detection with the Internal Layers of LLMs
by: Preiß, Martin
Published: (2025)

Activations as Features: Probing LLMs for Generalizable Essay Scoring Representations
by: Chi, Jinwei, et al.
Published: (2025)

Does This Look Familiar to You? Knowledge Analysis via Model Internal Representations
by: Park, Sihyun
Published: (2025)

Debate as Optimization: Adaptive Conformal Prediction and Diverse Retrieval for Event Extraction
by: Wang, Sijia, et al.
Published: (2024)

Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
by: Zhou, Andy, et al.
Published: (2024)

Beneath the Surface of Consistency: Exploring Cross-lingual Knowledge Representation Sharing in LLMs
by: Ifergan, Maxim, et al.
Published: (2024)

Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain
by: Cheng, Gang, et al.
Published: (2025)

Beyond Demonstrations: Dynamic Vector Construction from Latent Representations
by: Cai, Wang, et al.
Published: (2025)

Temporal Alignment of LLMs through Cycle Encoding for Long-Range Time Representations
by: Han, Xue, et al.
Published: (2025)

Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs
by: Bhattacharyya, Sree, et al.
Published: (2026)

Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models
by: Duan, Jinhao, et al.
Published: (2023)

Quantifying Fairness in LLMs Beyond Tokens: A Semantic and Statistical Perspective
by: Xu, Weijie, et al.
Published: (2025)

TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction
by: Li, Shuo, et al.
Published: (2023)

Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
by: Clymer, Joshua, et al.
Published: (2024)

Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
by: Jeoung, Sullam, et al.
Published: (2025)

Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
by: Xia, Yu, et al.
Published: (2024)

Evaluating Adjective-Noun Compositionality in LLMs: Functional vs Representational Perspectives
by: Dhar, Ruchira, et al.
Published: (2026)

Evaluate Bias without Manual Test Sets: A Concept Representation Perspective for LLMs
by: Gao, Lang, et al.
Published: (2025)

Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic Insights
by: Chen, Yi, et al.
Published: (2026)

Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond
by: Wang, Zhiyuan, et al.
Published: (2024)

The Why Behind the Action: Unveiling Internal Drivers via Agentic Attribution
by: Qian, Chen, et al.
Published: (2026)

Farther the Shift, Sparser the Representation: Analyzing OOD Mechanisms in LLMs
by: Jin, Mingyu, et al.
Published: (2026)

Beyond Benchmark: LLMs Evaluation with an Anthropomorphic and Value-oriented Roadmap
by: Wang, Jun, et al.
Published: (2025)

Polysemantic Dropout: Conformal OOD Detection for Specialized LLMs
by: Gupta, Ayush, et al.
Published: (2025)