← Back to all news
arXiv Machine Learning By Harshit Gupta

Corporate-Family Resolution Is Not a String-Matching Problem: A Public Benchmark Stratified by Name Visibility

Read the original on arXiv Machine Learning →

The paper introduces CorpFam, a public benchmark for corporate-family resolution comprising 54,864 candidate pairs across 10,307 families derived from 6.6 million US federal award records. It shows that traditional entity-matching methods perform poorly on pairs where name visibility is low, with the best matcher recovering only 4.2% of such invisible links and blocking schemes failing to identify most of them. The study argues that the real challenge lies in candidate generation rather than ranking, and validates the benchmark’s links against SEC subsidiary schedules, confirming their authenticity.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Jul 1

RARE: Redundancy-Aware Retrieval Evaluation Framework for High-Similarity Corpora

arXiv:2604. 19047v2 Announce Type: replace-cross Abstract: Existing QA benchmarks typically assume distinct documents with minimal overlap, yet real-world retrieval-augmented generation (RAG) systems operate on corpora such as financial reports, legal codes, and patents, where information is highly redundant and documents exhibit strong inter-document similarity.

By Hanjun Cho, Jay-Yoon Lee
llmsragbenchmarks
More like this →
arXiv AI
Sep 7

Does the Selected Object Reach the Reader? Auditing Identity Handoffs in Grounded Language-Model Pipelines

The paper investigates whether the object selected in a grounded language‑model pipeline actually reaches the reader, a failure that can break the handoff between stages. By auditing 600 HybridQA questions across three selector families, the authors find that exact key lookup and title matching recover the selected object in all 1,463 resolvable records, but body‑only BM25 omits it in 26.6% of cases at cutoff five, while hybrid retrieval with reranking omits it only 1.0%. The study also shows that misalignment between selected and retrieved objects can reduce exact match scores by up to 31 points, and introduces the Returned‑Object Profile (ROP) as a tool for reproducible auditing.

By Siddharth Vohra, Runmin Jiang, Xiaomo Li, Min Xu
ragbenchmarks
More like this →