Kongzi:一种事实增强的历史大语言模型
Kongzi: A Historical Large Language Model with Fact Enhancement
AI总结:
针对当前大语言模型在历史推理中存在的事实不准确问题,提出专为历史分析设计的Kongzi模型,通过整合高质量历史数据和事实强化学习策略,在历史问答等任务中事实准确性和推理深度优于现有模型。
摘要:
最新大语言模型(LLMs)的能力已从纯自然语言理解扩展到复杂推理任务。然而,当前推理模型在较长推理链中常出现事实不准确问题,这对历史推理构成挑战,限制了LLMs在复杂、知识密集型任务中的潜力。历史研究不仅需要准确呈现事实信息,还需具备建立跨时间关联、从碎片化且常模糊的来源中得出连贯结论的能力。为应对这些挑战,我们提出Kongzi,一种专为历史分析设计的大语言模型。通过整合精选的高质量历史数据和新颖的事实强化学习策略,Kongzi展现出强大的事实对齐性和复杂的推理深度。在历史问答和叙事生成等任务上的大量实验表明,Kongzi在事实准确性和推理深度方面均优于现有模型。通过有效应对历史文本中的独特挑战,Kongzi为专业领域准确可靠LLMs的发展树立了新标准。
英文摘要:
Large Language Models (LLMs) can exhibit factual inaccuracies during long-chain reasoning or under misleading prompts, limiting their reliability in historical analysis. We propose Kongzi, a language model for historical understanding and reasoning that combines continued pre-training on historical corpora, supervised fine-tuning, and fact-enhanced reinforcement learning. Its factuality reward compares entities and relations extracted from generated responses with historical references through knowledge-graph similarity. We evaluate 0.5B and 7B models on historical question answering and counterfactual reasoning, using reported ratings from three LLM judges, and on CMMLU-Chinese-History. Kongzi-7B receives the highest historical-accuracy ratings among the compared models under all three judges. Reinforcement learning improves the mean answer scores of both model sizes and their CMMLU-Chinese-History accuracy, although Kongzi-7B remains below the strongest reported baselines on that benchmark. These descriptive results support further study of factuality rewards for historical language models.
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。