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.
arXiv:2607. 26298v1 Announce Type: new Abstract: We built and evaluated a self-serve entity resolution (ER) system on six benchmarks spanning 864 to 5M records, and three lessons emerged that are absent from existing ER literature.
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.
arXiv:2606. 20359v1 Announce Type: new Abstract: Self-represented tenants, landlords, and help-desk staff need to be pointed at the provision of law that actually governs a question, with a correct statutory citation.
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.
arXiv:2608. 10644v1 Announce Type: new Abstract: Extraction produces candidate entities and relationships; writing them into a graph is where identity is decided, and identity decisions are destructive in a way extraction errors are not.
arXiv:2607. 12520v1 Announce Type: new Abstract: What a frontier model recalls about a person or tool from its own weights -- before any retrieval step -- often shapes the first description a human sees, making that parametric corpus presence a measurement problem.
OpenSanctions Pairs is the first large‑scale public benchmark for entity matching on sanctions and OSINT data, comprising 755,540 expert‑labeled pairs drawn from over 1 million entities across 293 source datasets and 45 jurisdictions. The dataset spans multiple languages and writing systems, inconsistent structures, and time‑varying provenance, making it far more heterogeneous than prior benchmarks. Baseline experiments show a rule‑based matcher achieving 91.3 % F1, GPT‑4o reaching 99.0 % F1, and a locally deployable open‑source model scoring 98.2 % F1, with complementary failure modes that highlight the need to focus on downstream pipeline components.
arXiv:2606. 10388v2 Announce Type: replace-cross Abstract: Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent.
Organizations that cannot send data to a cloud API increasingly ask: how good is Text-to-SQL if the model must run on-premises on open weights, and which popular accuracy "recipes" are worth their compute? We answer with an honest, fully reproducible benchmark on the BIRD development split (n=1534, Execution Accuracy), evaluating three open model families across two generations -- Qwen2.
The study introduces a four‑stage pipeline to detect internal contradictions—termed privacy washing—in privacy policies. Applied to two corpora (123 policies from 2026 and 115 from 2015), the pipeline identifies contradictions in 12.2% of the newer policies and 36.5% of the older ones, with third‑party sharing conflicts being the most common. A stability re‑run confirms similar prevalence rates and shows that the majority of contradictions are consistent across different model configurations.
arXiv:2606. 10388v1 Announce Type: cross Abstract: Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution assumptions to an agent.
arXiv:2603. 26815v3 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems for financial document QA typically follow a chunk-based paradigm: documents are split into fragments, embedded, and retrieved by similarity.