Buchumschlag

Towards Understanding Multi-Round Large Language Model Reasoning: Approximability, Learnability and Generalizability

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Xu, Chenhui, Liu, Dancheng, Li, Jiajie, Nassereldine, Amir, Li, Zhaohui, Xiong, Jinjun
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Artificial Intelligence Computation and Language Machine Learning
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Towards Pretraining Robust ASR Foundation Model with Acoustic-Aware Data Augmentation
von: Liu, Dancheng, et al.
Veröffentlicht: (2025)

Large Language Models have Intrinsic Self-Correction Ability
von: Liu, Dancheng, et al.
Veröffentlicht: (2024)

Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemble
von: Liu, Dancheng, et al.
Veröffentlicht: (2024)

Driving Through Uncertainty: Risk-Averse Control with LLM Commonsense for Autonomous Driving under Perception Deficits
von: Hu, Yuting, et al.
Veröffentlicht: (2025)

FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
von: Xu, Chenhui, et al.
Veröffentlicht: (2025)

PI-Whisper: Designing an Adaptive and Incremental Automatic Speech Recognition System for Edge Devices
von: Nassereldine, Amir, et al.
Veröffentlicht: (2024)

Automating Intervention Discovery from Scientific Literature: A Progressive Ontology Prompting and Dual-LLM Framework
von: Hu, Yuting, et al.
Veröffentlicht: (2024)

Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices
von: Qin, Ruiyang, et al.
Veröffentlicht: (2024)

Chain-of-Adaptation: Surgical Vision-Language Adaptation with Reinforcement Learning
von: Li, Jiajie, et al.
Veröffentlicht: (2026)

Towards Atoms of Large Language Models
von: Hu, Chenhui, et al.
Veröffentlicht: (2025)

KidSpeak: A General Multi-purpose LLM for Kids' Speech Recognition and Screening
von: Sharma, Rohan, et al.
Veröffentlicht: (2025)

Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models
von: Qiu, Xihe, et al.
Veröffentlicht: (2024)

Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
von: Xu, Fengli, et al.
Veröffentlicht: (2025)

Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation
von: Sun, Zhouhao, et al.
Veröffentlicht: (2024)

MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
von: Yang, Kailai, et al.
Veröffentlicht: (2024)

Tiny-Align: Bridging Automatic Speech Recognition and Large Language Model on the Edge
von: Qin, Ruiyang, et al.
Veröffentlicht: (2024)

FASA: a Flexible and Automatic Speech Aligner for Extracting High-quality Aligned Children Speech Data
von: Liu, Dancheng, et al.
Veröffentlicht: (2024)

Language Lives in Sparse Dimensions: Toward Interpretable and Efficient Multilingual Control for Large Language Models
von: Zhong, Chengzhi, et al.
Veröffentlicht: (2025)

Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models
von: Wang, Teng, et al.
Veröffentlicht: (2025)

Route-and-Reason: Scaling Large Language Model Reasoning with Reinforced Model Router
von: Shao, Chenyang, et al.
Veröffentlicht: (2025)

ProtRLSearch: A Multi-Round Multimodal Protein Search Agent with Large Language Models Trained via Reinforcement Learning
von: Liu, Congying, et al.
Veröffentlicht: (2026)

CausalEval: Towards Better Causal Reasoning in Language Models
von: Yu, Longxuan, et al.
Veröffentlicht: (2024)

Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability
von: Huang, Fan, et al.
Veröffentlicht: (2026)

ReaRAG: Knowledge-guided Reasoning Enhances Factuality of Large Reasoning Models with Iterative Retrieval Augmented Generation
von: Lee, Zhicheng, et al.
Veröffentlicht: (2025)

Towards Compositionally Generalizable Semantic Parsing in Large Language Models: A Survey
von: Mannekote, Amogh
Veröffentlicht: (2024)

LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
von: Bai, Yushi, et al.
Veröffentlicht: (2024)

TInR: Exploring Tool-Internalized Reasoning in Large Language Models
von: Xu, Qiancheng, et al.
Veröffentlicht: (2026)

Benchmarking Multi-National Value Alignment for Large Language Models
von: Shi, Weijie, et al.
Veröffentlicht: (2025)

Large Language and Reasoning Models are Shallow Disjunctive Reasoners
von: Khalid, Irtaza, et al.
Veröffentlicht: (2025)

Toward Adaptive Reasoning in Large Language Models with Thought Rollback
von: Chen, Sijia, et al.
Veröffentlicht: (2024)

DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues
von: Jang, Kyochul, et al.
Veröffentlicht: (2025)

Reason from Fallacy: Enhancing Large Language Models' Logical Reasoning through Logical Fallacy Understanding
von: Li, Yanda, et al.
Veröffentlicht: (2024)

Automatic Screening for Children with Speech Disorder using Automatic Speech Recognition: Opportunities and Challenges
von: Liu, Dancheng, et al.
Veröffentlicht: (2024)

Mixture of Reasonings: Teach Large Language Models to Reason with Adaptive Strategies
von: Xiong, Tao, et al.
Veröffentlicht: (2025)

PEToolLLM: Towards Personalized Tool Learning in Large Language Models
von: Xu, Qiancheng, et al.
Veröffentlicht: (2025)

TabularMath: Understanding Math Reasoning over Tables with Large Language Models
von: Tian, Shi-Yu, et al.
Veröffentlicht: (2025)

Towards Reasoning-Preserving Unlearning in Multimodal Large Language Models
von: Li, Hongji, et al.
Veröffentlicht: (2025)

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
von: Hong, Junyuan, et al.
Veröffentlicht: (2023)

Reasoning Factual Knowledge in Structured Data with Large Language Models
von: Huang, Sirui, et al.
Veröffentlicht: (2024)

Towards More Accurate US Presidential Election via Multi-step Reasoning with Large Language Models
von: Yu, Chenxiao, et al.
Veröffentlicht: (2024)