The paper investigates how open‑book scoring evaluates document‑level LoRA adapters by training one adapter per Wikipedia article on Llama‑3.1‑8B‑Instruct. Results show that open‑book scores largely reflect a shared reading behaviour: a random adapter can recover most of a specialist’s advantage when the document is provided, but only a negligible fraction when the document is omitted in a cloze probe. While specialists improve cloze recall and their weight updates align with the documents they read, selecting adapters by weight‑space proximity or text embedding does not outperform random choice, and merged adapters recover most of the open‑book advantage but only a small portion of the cloze advantage. The study also documents four silent errors that yielded clean but incorrect results.
arXiv:2610.19848v1 Announce Type: new Abstract: We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench conta...
arXiv:2610.28957v1 Announce Type: new Abstract: Scanning every passage in a long document seems thorough, but does it preserve more useful evidence or produce better answers? We compare 11 retrieval...
arXiv:2608. 02112v1 Announce Type: new Abstract: Embedding benchmarks measure standalone model quality, but they do not establish whether a low-cost retriever contributes complementary ranking information once lexical and transformer-based retrieval are already combined.
KnowForge is a modular pipeline for open‑domain multimodal document question answering that separates retrieval, judging, and reading into distinct agents. It uses a hybrid‑retrieval knowledge‑point index, a Locator agent for searching, a Bridge Judge to enforce a second hop, a Deep Reader that handles text, images, and tables, and a synthesizer with format checking. On the M3DocVQA benchmark it achieves an F1 of 47.5, outperforming prior systems by 11 points, and shows strong gains on MultiHop‑RAG and MMLongBench‑Doc as well.
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...
The paper presents a system for the MedReason 2026 challenge that tackles both multiple‑choice and open‑ended medical visual question answering using offline, containerized inference. Key findings include that comparing answer semantics rather than labels boosts retrieval‑only accuracy from 20.0 % to 57.5 % on a 200‑case holdout, and that varying the number of in‑prompt retrieved examples has minimal impact on final accuracy (93.5 %–94.0 %). The final system achieves 94.0 % MCQ accuracy on the development set and 93.20 % on the official pre‑evaluation, far surpassing the off‑the‑shelf baseline. "whyItMatters":"The results demonstrate that semantic‑aware retrieval and careful adapter tuning can dramatically improve medical VQA performance, offering a practical approach for high‑accuracy, offline inference in clinical settings."
arXiv:2602. 09616v2 Announce Type: replace-cross Abstract: Reliable retrieval-augmented generation (RAG) systems depend fundamentally on the retriever's ability to find relevant information.
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.
arXiv:2509. 16780v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise as educational aids but often lack alignment with specific course materials.
arXiv:2609.01182v1 Announce Type: new Abstract: Flagship language models appear saturated on benchmarks like MMLU (Hendrycks et al., 2021), scoring above 90% - yet benchmarks test only what the exper...
The paper introduces a penalty‑aware evaluation framework for Retrieval‑Augmented Generation (RAG) systems that uses asymmetric scoring, knowledge‑gap canaries, and a failure‑attribution pipeline. Applying this framework to three commercial RAG products and a baseline on SimpleQA‑Verified, the authors find that while overall accuracy is similar across systems, canary violation rates vary dramatically, showing that systems differ more in when they answer than in what they answer. The study demonstrates that penalty‑aware scoring can reorder system rankings and is robust across different penalty settings.
arXiv:2609.22939v1 Announce Type: cross Abstract: Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for...