SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cheng, Jiale, Liu, Xiao, Wang, Cunxiang, Gu, Xiaotao, Lu, Yida, Zhang, Dan, Dong, Yuxiao, Tang, Jie, Wang, Hongning, Huang, Minlie
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LongSafety: Evaluating Long-Context Safety of Large Language Models
by: Lu, Yida, et al.
Published: (2025)

AutoDetect: Towards a Unified Framework for Automated Weakness Detection in Large Language Models
by: Cheng, Jiale, et al.
Published: (2024)

LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Models
by: Gui, Jiayi, et al.
Published: (2024)

HPSS: Heuristic Prompting Strategy Search for LLM Evaluators
by: Wen, Bosi, et al.
Published: (2025)

VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
by: Cheng, Jiale, et al.
Published: (2025)

Black-Box Prompt Optimization: Aligning Large Language Models without Model Training
by: Cheng, Jiale, et al.
Published: (2023)

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation
by: Wen, Bosi, et al.
Published: (2026)

StepMathAgent: A Step-Wise Agent for Evaluating Mathematical Processes through Tree-of-Error
by: Yang, Shu-Xun, et al.
Published: (2025)

IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation
by: Wen, Bosi, et al.
Published: (2025)

HoWToBench: Holistic Evaluation for LLM's Capability in Human-level Writing using Tree of Writing
by: Feng, Andrew Zhuoer, et al.
Published: (2026)

Benchmarking Complex Instruction-Following with Multiple Constraints Composition
by: Wen, Bosi, et al.
Published: (2024)

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
by: Feng, Andrew Zhuoer, et al.
Published: (2026)

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation
by: Ke, Pei, et al.
Published: (2023)

AlignBench: Benchmarking Chinese Alignment of Large Language Models
by: Liu, Xiao, et al.
Published: (2023)

ChatGLM-RLHF: Practices of Aligning Large Language Models with Human Feedback
by: Hou, Zhenyu, et al.
Published: (2024)

Does RLHF Scale? Exploring the Impacts From Data, Model, and Method
by: Hou, Zhenyu, et al.
Published: (2024)

Glyph: Scaling Context Windows via Visual-Text Compression
by: Cheng, Jiale, et al.
Published: (2025)

Training Language Model to Critique for Better Refinement
by: Yu, Tianshu, et al.
Published: (2025)

MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models
by: Hong, Wenyi, et al.
Published: (2025)

Trust-Region Adaptive Policy Optimization
by: Su, Mingyu, et al.
Published: (2025)

Agent-SafetyBench: Evaluating the Safety of LLM Agents
by: Zhang, Zhexin, et al.
Published: (2024)

Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning
by: Wen, Jiaxin, et al.
Published: (2024)

ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
by: Zhang, Dan, et al.
Published: (2024)

Data Selection via Optimal Control for Language Models
by: Gu, Yuxian, et al.
Published: (2024)

Data-Efficient RLVR via Off-Policy Influence Guidance
by: Zhu, Erle, et al.
Published: (2025)

Language Model Decoding as Direct Metrics Optimization
by: Ji, Haozhe, et al.
Published: (2023)

AutoRE: Document-Level Relation Extraction with Large Language Models
by: Xue, Lilong, et al.
Published: (2024)

From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks
by: Zhang, Zhexin, et al.
Published: (2024)

SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
by: Zhang, Dan, et al.
Published: (2024)

Extensive Self-Contrast Enables Feedback-Free Language Model Alignment
by: Liu, Xiao, et al.
Published: (2024)

Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization
by: Zhang, Zhexin, et al.
Published: (2023)

SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning
by: Do, Dai, et al.
Published: (2025)

Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous Constraints
by: Yang, Junxiao, et al.
Published: (2025)

ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs
by: Cui, Shiyao, et al.
Published: (2025)

Think Socially via Cognitive Reasoning
by: Zhou, Jinfeng, et al.
Published: (2025)

Towards Efficient Exact Optimization of Language Model Alignment
by: Ji, Haozhe, et al.
Published: (2024)

NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Prompts
by: Zhang, Shudan, et al.
Published: (2024)

Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models
by: Sun, Haoran, et al.
Published: (2024)

RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis
by: Feng, Andrew Zhuoer, et al.
Published: (2026)

CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
by: Zheng, Wendi, et al.
Published: (2024)