ModeX: Evaluator-Free Best-of-N Selection for Open-Ended Generation

ACL ARR 2026 January Submission2068 Authors

Keywords: large language models, best-of-n, open-ended text generation

Abstract: Selecting a single high-quality output from multiple stochastic generations remains a fundamental challenge for large language models (LLMs), particularly in open-ended tasks where no canonical answer exists. While Best-of-$N$ and self-consistency methods show that aggregating multiple generations can improve performance, existing approaches typically rely on external evaluators, reward models, or exact string-match voting, limiting their applicability and efficiency. We propose Mode Extraction (ModeX), an evaluator-free Best-of-$N$ selection framework that generalizes majority voting to open-ended text generation by identifying the modal output representing the dominant semantic consensus among generated texts. ModeX constructs a similarity graph over candidate generations and recursively applies spectral clustering to select a representative centroid, without requiring additional inference or auxiliary models. We further instantiate this selection principle as ModeX Decoding, a drop-in decoding scheme with early pruning for efficiency. Across open-ended tasks---including text summarization, code generation, and mathematical reasoning---our approaches consistently outperform standard single- and multi-path baselines, providing a computationally efficient, drop-in solution for robust open-ended text generation.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: Language Modeling, Generation, Machine Learning for NLP

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 2068