Cover Image

Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jiang, Chunyang, Zhang, Yonggang, Cai, Yiyang, Chan, Chi-Min, Liu, Yulong, Chen, Mingming, Xue, Wei, Guo, Yike
Format:	Preprint
Published:	2025
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

Graceful Forgetting in Generative Language Models
by: Jiang, Chunyang, et al.
Published: (2025)

Importance Weighting Can Help Large Language Models Self-Improve
by: Jiang, Chunyang, et al.
Published: (2024)

Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge
by: Cai, Yiyang, et al.
Published: (2024)

Self-Resolving Prediction Markets for Unverifiable Outcomes
by: Srinivasan, Siddarth, et al.
Published: (2023)

Bootstrapping Task Spaces for Self-Improvement
by: Jiang, Minqi, et al.
Published: (2025)

J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge
by: Chan, Chi-Min, et al.
Published: (2025)

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems
by: Cai, Qianshu, et al.
Published: (2026)

S-Agents: Self-organizing Agents in Open-ended Environments
by: Chen, Jiaqi, et al.
Published: (2024)

Scaling Multi-Hop Training Data via Graph-Constrained Path Selection
by: Chen, Pengyu, et al.
Published: (2026)

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems
by: Chan, Chi-Min, et al.
Published: (2024)

Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
by: Deng, Shijian, et al.
Published: (2024)

Semantic Voting: Execution-Grounded Consensus for LLM Code Generation
by: Jiang, Shan, et al.
Published: (2026)

CLEV: LLM-Based Evaluation Through Lightweight Efficient Voting for Free-Form Question-Answering
by: Badshah, Sher, et al.
Published: (2025)

Impact of Cyberchondria on Unverified Health Information Sharing: A Moderated Mediation Approach
by: Qian Xiao, et al.
Published: (2025)

Self-Equivalent Voting Rules
by: Hermida-Rivera, Héctor
Published: (2025)

Direct Reasoning Optimization: Token-Level Reasoning Reflectivity Meets Rubric Gates for Unverifiable Tasks
by: Xu, Yifei, et al.
Published: (2025)

Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
by: Liu, Zewen, et al.
Published: (2026)

SOE: Sample-Efficient Robot Policy Self-Improvement via On-Manifold Exploration
by: Jin, Yang, et al.
Published: (2025)

Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
by: Wang, Jianyu, et al.
Published: (2025)

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text
by: Lu, Ximing, et al.
Published: (2026)

PEARL: Geometry Aligns Semantics for Training-Free Open-Vocabulary Semantic Segmentation
by: Pei, Gensheng, et al.
Published: (2026)

Binary Self-Selective Voting Rules
by: Hermida-Rivera, Héctor, et al.
Published: (2025)

Self-Duality and Transfer in Voting Games
by: Abe, Takaaki
Published: (2026)

Binary Self‐Selective Voting Rules
by: Héctor Hermida‐Rivera, et al.
Published: (2025)

A Survey on LLM Inference-Time Self-Improvement
by: Dong, Xiangjue, et al.
Published: (2024)

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling
by: Ding, Yiwen, et al.
Published: (2024)

Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
by: Huang, Chengyu, et al.
Published: (2026)

Self-Improvement of Large Language Models: A Technical Overview and Future Outlook
by: Yang, Haoyan, et al.
Published: (2026)

A Curriculum-style Self-training Approach for Source-Free Semantic Segmentation
by: Wang, Yuxi, et al.
Published: (2021)

Better Private Distribution Testing by Leveraging Unverified Auxiliary Data
by: Aliakbarpour, Maryam, et al.
Published: (2025)

Scaling Unverifiable Rewards: A Case Study on Visual Insights
by: Gan, Shuyu, et al.
Published: (2025)

A Semantic-Aware Layer-Freezing Approach to Computation-Efficient Fine-Tuning of Language Models
by: Gu, Jian, et al.
Published: (2024)

LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting
by: Yang, Yu-Jie, et al.
Published: (2026)

Computing Voting Rules with Improvement Feedback
by: Micha, Evi, et al.
Published: (2025)

Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended Tasks
by: Shen, William F., et al.
Published: (2026)

A Training-Free Regeneration Paradigm: Contrastive Reflection Memory Guided Self-Verification and Self-Improvement
by: Li, Yuran, et al.
Published: (2026)

RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
by: Yu, Zhaoning, et al.
Published: (2025)

Vote-Tree-Planner: Optimizing Execution Order in LLM-based Task Planning Pipeline via Voting
by: Zhang, Chaoyuan, et al.
Published: (2025)

Sample Efficient Generative Molecular Optimization with Joint Self-Improvement
by: Korkmaz, Serra, et al.
Published: (2026)

Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
by: Wang, Yuanfu, et al.
Published: (2026)