思维路径：多方向思考用于长文本个性化问答
Pathways of Thoughts: Multi-Directional Thinking for Long-form Personalized Question Answering
AI总结：
本文提出PoT方法，通过多方向思考生成个性化问答响应，实验证明其在长文本问答任务中表现优异。
摘要：
个性化在搜索和推荐中已被广泛研究，但个性化问答仍因从长、嘈杂、隐含的上下文中推断偏好和生成既准确又符合用户期望的响应而面临挑战。为此，我们提出了思维路径（PoT），一种在推理阶段应用的通用方法，适用于任何大语言模型（LLM），无需特定任务微调。PoT将思考建模为一个迭代决策过程，模型动态选择多种认知操作，如推理、修订、个性化和澄清。这使模型能够探索多种推理路径，生成多样化的候选响应，以捕捉不同的视角。PoT随后根据推断出的用户偏好聚合并重新加权这些候选，最终生成一个受益于多样化推理路径互补优势的个性化响应。在LaMP-QA基准测试中，PoT在多个指标上均优于竞争基线，达到最高10.8%的相对提升。人工评估进一步验证了这些改进，注释员在66%的情况下更喜欢PoT，相比表现最佳的基线，并在15%的情况下报告平局。
英文摘要：
Personalization is well studied in search and recommendation, but personalized question answering remains underexplored due to challenges in inferring preferences from long, noisy, implicit contexts and generating responses that are both accurate and aligned with user expectations. To address this, we propose Pathways of Thoughts (PoT), an inference-stage method that applies to any large language model (LLM) without task-specific fine-tuning. PoT models the thinking as an iterative decision process, where the model dynamically selects among cognitive operations such as reasoning, revision, personalization, and clarification. This enables exploration of multiple reasoning trajectories, producing diverse candidate responses that capture different perspectives. PoT then aggregates and reweights these candidates according to inferred user preferences, yielding a final personalized response that benefits from the complementary strengths of diverse reasoning paths. Experiments on the LaMP-QA benchmark show that PoT consistently outperforms competitive baselines, achieving up to a 10.8\% relative improvement. Human evaluation further validates these improvements, with annotators preferring PoT in 66\% of cases compared to the best-performing baseline and reporting ties in 15\% of cases.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
