跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19900 · v1

Attribute or Abstain: Evaluating Evidence-Grounded Retrieval on the Low-Resource African Business Web

首次提交 2026-11-15 17:29
版本更新 2026-11-15 17:29
雷达观测 2026-11-17 12:06
arXiv ↗PDF ↗

摘要

Retrieval-augmented systems that research companies are judged by how much they find, yet in markets where public evidence is sparse, a confident answer without support costs more than no answer. We introduce AfriBizClaims, a benchmark of 150 company-research queries across six African markets in English, French and Portuguese, including queries about fictitious companies that a correct system must decline. Each claim a system makes is judged against the page it cites by an AI judge, checked against a second AI judge from another model family and against two human annotators, and abstentions are scored against answerability labels. We compare BM25 over a pooled corpus, standard web retrieval-augmented generation, and a multi-step agent pipeline (Konexium V1), all using the same language model. The two simple baselines are well attributed: 98% of their judged claims are supported by the page they cite, and they decline every field of every fictitious company. Counting claims about a company other than the one asked about as errors, the agent pipeline's per-query precision is 68%, and it never answers a question about a named company correctly: it substitutes other firms, including for 5 of the 24 fictitious names, and it is the least stable between runs and the most expensive. In the pipeline we evaluated, more steps between the query and the evidence did not buy more grounded answers. We will release the queries, system outputs, labels and short evidence excerpts.

作者备注:8 pages, 3 figures, 4 tables

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-15 17:29 · 最新观测版本

Attribute or Abstain: Evaluating Evidence-Grounded Retrieval on the Low-Resource African Business Web

Retrieval-augmented systems that research companies are judged by how much they find, yet in markets where public evidence is sparse, a confident answer without support costs more than no answer. We introduce AfriBizClaims, a benchmark of 150 company-research queries across six African markets in English, French and Portuguese, including queries about fictitious companies that a correct system must decline. Each claim a system makes is judged against the page it cites by an AI judge, checked against a second AI judge from another model family and against two human annotators, and abstentions are scored against answerability labels. We compare BM25 over a pooled corpus, standard web retrieval-augmented generation, and a multi-step agent pipeline (Konexium V1), all using the same language model. The two simple baselines are well attributed: 98% of their judged claims are supported by the page they cite, and they decline every field of every fictitious company. Counting claims about a company other than the one asked about as errors, the agent pipeline's per-query precision is 68%, and it never answers a question about a named company correctly: it substitutes other firms, including for 5 of the 24 fictitious names, and it is the least stable between runs and the most expensive. In the pipeline we evaluated, more steps between the query and the evidence did not buy more grounded answers. We will release the queries, system outputs, labels and short evidence excerpts.

查看此版本解读 →查看此版本原文 ↗