arXiv cs.CL· Misha Andreev·· 10 小时前AI 评分18
Semantic Chains：从可及事实到有据可依的答案
Semantic Chains: From Reachable Facts to Justified Answers
AI 导读
该论文将上下文建模为逻辑事实图，提出"语义链"方法：从问题中的对象出发搜索可到达的根事实，并覆盖所选展开中的每个事实，使根事实生成一段文本，将问题与完整答案连接并为其提供依据。对于包含多个环节的链，论文给出了指定类别内候选顺序的完整枚举，并明确了各环节文本何时共同保持论证的正当性并支撑每一次过渡。全文共 31 页、10 幅图。
正文 · 原文
Abstract:How can the facts that justify an answer be found from a question and presented as a sequence of connected statements? This paper models a context as a graph of logical facts and takes as given which expressions represent each fact. A parent fact can express a relation among its subfacts, and a preserving edge allows the content of a subfact to be recovered within a full representation of its parent. Suppose a root fact justifies the full answer and a path of preserving edges leads from that root to a fact that designates an object shared by the question and the answer. Under the conditions of the model, a search starting from the objects in the question reaches the root and covers every fact in the selected expansion. The root then admits a text that forms a single link connecting the question to the full answer and justifying it. For chains with several links, the paper gives a complete enumeration of candidate orders within the stated class and specifies when the link texts jointly preserve the justification and support every transition.
| Comments: | 31 pages, 10 figures |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.14252 [cs.CL] |
| (or arXiv:2611.14252v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14252 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Misha Andreev [view email]
[v1]
Tue, 10 Nov 2026 16:01:11 UTC (587 KB)
来源：arXiv cs.CL · arxiv.org