← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-srw.111 · 记录 #1
Reference-Free Schema Generation for Literature Review Tables via Multi-Faceted Rewards
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 21:41
摘要
To accelerate scientific knowledge acquisition, LLMs are increasingly used to synthesize multiple papers into structured tables by inferring schemas and values. While value generation within a fixed schema can often be reduced to extractive question answering, the schema generation problem, determining which dimensions to compare a set of documents, lacks a formal mapping to standard NLP tasks. In this work, we formulate schema generation as a reinforcement learning problem and investigate whether these dimensions can be induced without access to gold-standard schemas. We design a multi-faceted reward framework capturing schema coverage, non-redundancy, relevance, and format, and train a small language model on a literature review dataset. Our approach yields consistent improvements over the untuned base model across intrinsic, reference-based, and LLM-judge metrics, and remains competitive with supervised fine-tuned models at 5\times the parameter count on structural and diversity dimensions. All code, results and prompts are available in the GitHub repository: https://github.com/sinjoysaha/rl-schema-generation
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Reference-Free Schema Generation for Literature Review Tables via Multi-Faceted Rewards
To accelerate scientific knowledge acquisition, LLMs are increasingly used to synthesize multiple papers into structured tables by inferring schemas and values. While value generation within a fixed schema can often be reduced to extractive question answering, the schema generation problem, determining which dimensions to compare a set of documents, lacks a formal mapping to standard NLP tasks. In this work, we formulate schema generation as a reinforcement learning problem and investigate whether these dimensions can be induced without access to gold-standard schemas. We design a multi-faceted reward framework capturing schema coverage, non-redundancy, relevance, and format, and train a small language model on a literature review dataset. Our approach yields consistent improvements over the untuned base model across intrinsic, reference-based, and LLM-judge metrics, and remains competitive with supervised fine-tuned models at 5\times the parameter count on structural and diversity dimensions. All code, results and prompts are available in the GitHub repository: https://github.com/sinjoysaha/rl-schema-generation
查看此版本解读 →查看此版本原文 ↗