The paper investigates how conversational Retrieval-Augmented Generation (RAG) benchmarks that rely on relevance judgments to determine context sufficiency can be misleading. By re‑running official baselines on the RETECO track and evaluating with both large‑language‑model judges and a blind audit, the authors show that stronger retrievers produce a higher proportion of contexts lacking gold documents yet still containing the answer, leading to a sharp drop in shortcut precision from 0.68 to 0.10. The study demonstrates that many false misses arise from hard negatives, gold content from other turns, or neighboring chunks, and that using retrieval scores alone as a sufficiency detector can underestimate answerability by up to 0.19 in AUROC.
By Ivan Kochergin, Vasily Konovalov
arXiv:2609.18154v1 Announce Type: cross
Abstract: We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite th...
By Aaditya Chauhan
arXiv:2609.38021v1 Announce Type: cross
Abstract: We evaluate an auditable long-term memory system on LongMemEval-S. Its retrieval chain uses hybrid candidate retrieval, cross-encoder reranking, cove...
By Christopher J. Chanhnourack
arXiv:2609.24885v1 Announce Type: new
Abstract: When a language model answers from a curated corpus via graph-based retrieval, a large grounding uplift does not establish reasoning over the retrieved...
By John J. O'Hare
arXiv:2610.25964v2 Announce Type: replace-cross
Abstract: We set out to reproduce a recent hallucination-mitigation result on the POPE benchmark. The LLaVA-1.5-7B baseline we measured, 82.21 F1 on th...
By Kesav Kumar Jayakumar, Karthigeyan Thilak
TRACE is a system designed to bridge the grounding contract gap in LitTraceQA by combining target-aware retrieval, independent typed evidence localization, multimodal table extraction, and schema-driven table construction. It indexes 27,487 papers using multiple representations while preserving question targets, predicts observation units for tables, and assembles rows with evaluator-compatible key normalization. On the official test set, TRACE achieves a 0.760613 overall score, with high paper F1, evidence F1, and multiple-choice accuracy, though table-row and macro cell performance remain lower.
By Sachin Gupta, Divya Godara
The paper proposes a training‑free detector that uses sentence‑level context sensitivity to identify unsupported content in retrieval‑augmented generation (RAG) answers. By re‑scoring each sentence with full context, no context, and each chunk removed, the method flags the chunk whose removal most reduces a sentence’s likelihood as the likely source. Evaluated on RAGTruth, TofuEval, and RAGBench, the detector outperforms answer‑level faithfulness scores, achieving AUCs up to 0.745 and matching per‑chunk fact‑checkers while using only a fraction of the compute required by large‑language‑model judges.
By Mohamed Aly Bouke
arXiv:2610. 29052v1 Announce Type: cross Abstract: A typed decision maps evidence, a question and a fixed set of options to a probability for every option, computed in one forward pass, by reading a language model's logits or a small head over its hidden states, instead of generating and parsing text.
By Yuchuan Weng, Chi Liu, Xin Chen, Srinivasan Manoharan
Re:CAP is a reference‑free audit loop for retrieval‑augmented generation (RAG) pipelines that probes for missing documents instead of enumerating all relevant ones. It identifies covered topics, generates probing questions, retrieves candidate documents, and uses an LLM judge to keep only those that add new information. On several benchmarks, Re:CAP recovers a significant portion of gold documents that flat BM25 or hybrid retrieval misses, and human evaluation shows most of these documents add new information.
By Aviral Joshi, Hanoz Bhathena, Max Nelson, Saket Sharma
The report audits a long‑term‑memory retrieval chain on 500 LongMemEval‑S development questions, evaluating reader performance under an adapted GPT‑4o rubric. Scores vary widely across reader lanes (93–479), with the strongest lanes scoring 479 and 475, and re‑judging the same pass‑1 answers changes three labels, yielding 478. Fixed‑answer knowledge‑update re‑scoring achieves 70/72 or 69/72 depending on the template, and a different‑family reader scores 474, just 1.0 percentage point below the headline pass. The study also reports that live reader request bodies were not retained, that 18 of 23 gains occurred where baseline packets lacked evidence, and that a negative control rejects a verifier that repairs some wrong drafts but breaks many correct ones. Overall, the findings do not establish a new leaderboard leader or a transferable memory advantage, and the released artifacts support packet inspection and re‑scoring but do not reconstruct the method.
By Christopher J. Chanhnourack
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.
By Ali Asaria, Tony Salomone, Deep Gandhi
The paper introduces an audit layer for vision‑language model benchmarks that reuses per‑question artifacts from evaluation runs to assess the benchmark itself. Six detectors analyze saved outputs, and an additional text‑only rerun removes visual inputs to produce per‑question reports and aggregate statistics, including permutation‑null excess and interval estimates. Applying this method to the MMStar benchmark reveals that 20.2% of its questions show no accuracy gain from images, with a small but significant excess in mathematics and science categories, and identifies questions where all models chose the same non‑gold option.
By Denis Degtiarev, Anna Gromova, Sergey Katkov, Artem Mikhailin, Safina Mukhamedshina, Albert Nasybullin, Karina Shaikhutdinova, Artem Tuzov