Copertina

Prefix-Safe Bayesian Belief Tracking for LLM Reasoning Reliability:Separating Calibration from Ranking

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Song, Zhenghan, Li, Yunyi, Liu, Yulong
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Your Simulation Runs but Solves the Wrong Physics: PDE-Grounded Intent Verification for LLM-Generated Multiphysics Simulation Code
di: Song, Zhenghan, et al.
Pubblicazione: (2026)

PrefixLLM: LLM-aided Prefix Circuit Design
di: Xiao, Weihua, et al.
Pubblicazione: (2024)

PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State Tracking
di: Zhu, Wang Bill, et al.
Pubblicazione: (2026)

The Path of Least Resistance: Guiding LLM Reasoning Trajectories with Prefix Consensus
di: Jindal, Ishan, et al.
Pubblicazione: (2026)

PrefixMemory-Tuning: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention
di: Wang, Haonan, et al.
Pubblicazione: (2025)

Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence
di: Lu, Yuyin, et al.
Pubblicazione: (2026)

Well Begun, Half Done: Reinforcement Learning with Prefix Optimization for LLM Reasoning
di: Sun, Yiliu, et al.
Pubblicazione: (2025)

PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization
di: Zuo, Dongsheng, et al.
Pubblicazione: (2025)

SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
di: Chen, Yulong, et al.
Pubblicazione: (2025)

Bias-Restrained Prefix Representation Finetuning for Mathematical Reasoning
di: Liang, Sirui, et al.
Pubblicazione: (2025)

BaRDa: A Belief and Reasoning Dataset that Separates Factual Accuracy and Reasoning Ability
di: Clark, Peter, et al.
Pubblicazione: (2023)

Fast and Effective On-policy Distillation from Reasoning Prefixes
di: Zhang, Dongxu, et al.
Pubblicazione: (2026)

X-RAY: Mapping LLM Reasoning Capability via Formalized and Calibrated Probes
di: Tianxi, Gao, et al.
Pubblicazione: (2026)

RadReason: Radiology Report Evaluation Metric with Reasons and Sub-Scores
di: Li, Yingshu, et al.
Pubblicazione: (2025)

Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking
di: Zhang, Yunyi, et al.
Pubblicazione: (2025)

Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward
di: Liu, Zikang, et al.
Pubblicazione: (2025)

Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
di: Jin, Gaojie, et al.
Pubblicazione: (2026)

Calibrating LLM Judges: Linear Probes for Fast and Reliable Uncertainty Estimation
di: Radharapu, Bhaktipriya, et al.
Pubblicazione: (2025)

Deliberative Reasoning Network: An Uncertainty-Driven Paradigm for Belief-Tracked Inference with Pretrained Language Models
di: Xu, Anran, et al.
Pubblicazione: (2025)

Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
di: Shirokikh, Mikhail, et al.
Pubblicazione: (2026)

Detecting Prefix Bias in LLM-based Reward Models
di: Kumar, Ashwin, et al.
Pubblicazione: (2025)

Aligning Probabilistic Beliefs under Informative Missingness: LLM Steerability in Clinical Reasoning
di: Kobayashi, Yuta, et al.
Pubblicazione: (2025)

Reliable Reasoning Path: Distilling Effective Guidance for LLM Reasoning with Knowledge Graphs
di: Xiao, Yilin, et al.
Pubblicazione: (2025)

SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation
di: Wang, Xinyu, et al.
Pubblicazione: (2026)

AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents
di: Wang, Haoyu, et al.
Pubblicazione: (2025)

Bayesian Calibration of Win Rate Estimation with LLM Evaluators
di: Gao, Yicheng, et al.
Pubblicazione: (2024)

PrefixGuard: From LLM-Agent Traces to Online Failure-Warning Monitors
di: Huang, Xinmiao, et al.
Pubblicazione: (2026)

RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation
di: Liu, Jun, et al.
Pubblicazione: (2025)

Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
di: Zou, Deyu, et al.
Pubblicazione: (2025)

Causal Strengths and Leaky Beliefs: Interpreting LLM Reasoning via Noisy-OR Causal Bayes Nets
di: Dettki, Hanna
Pubblicazione: (2025)

DeLo: Dual Decomposed Low-Rank Experts Collaboration for Continual Missing Modality Learning
di: Liu, Xiwei, et al.
Pubblicazione: (2026)

Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use
di: Pang, Renning, et al.
Pubblicazione: (2026)

Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks
di: Deng, Wentao, et al.
Pubblicazione: (2025)

Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller
di: Cai, Min, et al.
Pubblicazione: (2024)

Towards Infinite-Long Prefix in Transformer
di: Liang, Yingyu, et al.
Pubblicazione: (2024)

AdvPrefix: An Objective for Nuanced LLM Jailbreaks
di: Zhu, Sicheng, et al.
Pubblicazione: (2024)

PABU: Progress-Aware Belief Update for Efficient LLM Agents
di: Jiang, Haitao, et al.
Pubblicazione: (2026)

Parallel Prefix Verification for Speculative Generation
di: Yao, Yuncheng, et al.
Pubblicazione: (2026)

GSCE: A Prompt Framework with Enhanced Reasoning for Reliable LLM-driven Drone Control
di: Wang, Wenhao, et al.
Pubblicazione: (2025)

Demystifying the Roles of LLM Layers in Retrieval, Knowledge, and Reasoning
di: Song, Xinyuan, et al.
Pubblicazione: (2025)