Cover Image

Multi-turn Training with Basic Human Feedback Helps Little on LLM Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Qiang, Song, Wuganjing, Lin, Zhenzhou, Chen, Feifan, Cai, Qiaolong, Li, Chen, Sui, Yongduo
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Information Theory Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SearchRAG: Can Search Engines Be Helpful for LLM-based Medical Question Answering?
by: Shi, Yucheng, et al.
Published: (2025)

CodeGraph: Enhancing Graph Reasoning of LLMs with Code
by: Cai, Qiaolong, et al.
Published: (2024)

Learning is Forgetting: LLM Training As Lossy Compression
by: Conklin, Henry C., et al.
Published: (2026)

A Training-free Method for LLM Text Attribution
by: Radvand, Tara, et al.
Published: (2025)

From Tokens to Thoughts: How LLMs and Humans Trade Compression for Meaning
by: Shani, Chen, et al.
Published: (2025)

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG
by: Wang, Xihang, et al.
Published: (2026)

A Little Confidence Goes a Long Way
by: Scoville, John, et al.
Published: (2024)

Pistis-RAG: Enhancing Retrieval-Augmented Generation with Human Feedback
by: Bai, Yu, et al.
Published: (2024)

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
by: Cheng, Yiruo, et al.
Published: (2024)

Unleashing the Power of Large Language Model for Denoising Recommendation
by: Wang, Shuyao, et al.
Published: (2025)

Quantification and Validation for Degree of Understanding in M2M Semantic Communications
by: Xia, Linhan, et al.
Published: (2024)

Explainable Recommendation with Simulated Human Feedback
by: Tang, Jiakai, et al.
Published: (2025)

Optimal Multi-bit Generative Watermarking Schemes Under Worst-Case False-Alarm Constraints
by: Huang, Yu-Shin, et al.
Published: (2026)

On the Reasoning Capacity of AI Models and How to Quantify It
by: Radha, Santosh Kumar, et al.
Published: (2025)

FDD CSI Feedback under Finite Downlink Training: A Rate-Distortion Perspective
by: Chen, Shuao, et al.
Published: (2026)

Cost-aware LLM-based Online Dataset Annotation
by: Elumar, Eray Can, et al.
Published: (2025)

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
by: Yong, Xixian, et al.
Published: (2025)

Multi-Head Finite-State Dimension
by: Huang, Xiang, et al.
Published: (2025)

Efficient Learned Data Compression via Dual-Stream Feature Decoupling
by: Ma, Huidong, et al.
Published: (2026)

LogitScope: A Framework for Analyzing LLM Uncertainty Through Information Metrics
by: Ahmed, Farhan, et al.
Published: (2026)

JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability
by: Wang, Junda, et al.
Published: (2024)

HILL: Hierarchy-aware Information Lossless Contrastive Learning for Hierarchical Text Classification
by: Zhu, He, et al.
Published: (2024)

Measuring Grammatical Diversity from Small Corpora: Derivational Entropy Rates, Mean Length of Utterances, and Annotation Invariance
by: Martin, Fermin Moscoso del Prado
Published: (2024)

Language Evolution for Evading Social Media Regulation via LLM-based Multi-agent Simulation
by: Cai, Jinyu, et al.
Published: (2024)

An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding
by: Hu, Dou, et al.
Published: (2025)

HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation
by: Liu, Hao, et al.
Published: (2025)

MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression
by: Elias, Noel, et al.
Published: (2024)

In-Context Learning with Representations: Contextual Generalization of Trained Transformers
by: Yang, Tong, et al.
Published: (2024)

Little Giants: Synthesizing High-Quality Embedding Data at Scale
by: Chen, Haonan, et al.
Published: (2024)

Reasoning and Tools for Human-Level Forecasting
by: Hsieh, Elvis, et al.
Published: (2024)

Joint Localization and Orientation with Triple-Beam Fingerprints in Massive MIMO-OFDM
by: Zhao, Yu, et al.
Published: (2026)

MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety
by: Song, Jialin, et al.
Published: (2026)

LLM Reasoning Engine: Specialized Training for Enhanced Mathematical Reasoning
by: Chen, Shuguang, et al.
Published: (2024)

Integrating Pre-Trained Language Model with Physical Layer Communications
by: Lee, Ju-Hyung, et al.
Published: (2024)

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification
by: Wang, Zhensheng, et al.
Published: (2026)

How Much Can RAG Help the Reasoning of LLM?
by: Liu, Jingyu, et al.
Published: (2024)

On Polar Coding with Feedback
by: Liu, Ling, et al.
Published: (2026)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
by: Català, Mar Gonzàlez I, et al.
Published: (2026)

On Secrecy Capacity of Binary Beampointing Channels with Block Memory and Feedback
by: Li, Siyao, et al.
Published: (2025)

Clarifying orthography: Orthographic transparency as compressibility
by: Torres, Charles J., et al.
Published: (2025)