Answer Probing-Guided Search for Diverse Solution Exploration of LLMs

2026-08-31

AI Summary

为解决大型语言模型在生成多样化解决方案时的局限性，本文提出了一种基于答案探查指导的树搜索方法（APTS），通过探测潜在答案的隐藏状态和困惑度来提高解路径的多样性。

Abstract

Generating multiple diverse and high-quality solutions is valuable for many applications, such as code-test generation and drug discovery. However, Large Language Models (LLMs) tend to converge on a single high-confidence solution during inference, limiting exploration of alternative valid solution paths. Existing test-time methods promote diversity through tree-like search and prune semantically similar branches using response-level semantic embeddings. However, we find that such embeddings are easily confounded by linguistic and stylistic similarities, making it difficult to distinguish genuinely distinct solution paths. To address this, we introduce Answer Probing, which probes the potential answer an LLM would reach from an intermediate reasoning path. We demonstrate that the hidden states of probed answers more effectively differentiate distinct solution paths than semantic embeddings, and the perplexity of probed answers serves as a practical proxy for reasoning correctness. Based on these findings, we propose Answer Probing-Guided Tree Search (APTS), which guides the tree search by the probed answers' hidden state similarity and perplexity. Experiments on three reasoning tasks across two LLMs show that APTS consistently enhances solution diversity, demonstrating its effectiveness and robustness.

Problem

• Large Language Models
• Diverse Solutions
• Solution Exploration
• Semantic Embeddings
• Reasoning Paths

Innovation

• Answer Probing
• hidden state similarity
• perplexity
• solution diversity
• tree search