arXiv:2607. 19678v1 Announce Type: cross Abstract: AI-generated answers in high-stakes domains are often fluent but difficult to verify, especially when they contain multi-step reasoning rather than a single final answer.
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 AI.
arXiv:2609.12822v2 Announce Type: replace Abstract: Blinded physician evaluation has been considered by many to be the gold standard for assessing clinical reasoning in large language models (LLMs)....
arXiv:2605. 24902v2 Announce Type: replace-cross Abstract: Reasoning-enabled LLMs perform strongly on medical reasoning benchmarks, but it remains unclear whether these gains transfer to structured clinical documentation; we investigate this question using SOAP note generation from clinical dialogue in a source-aware benchmark spanning OMI Health, ACI-Bench, and PriMock57.
The paper introduces a method for generating multilingual reasoning traces for medical question answering using large language models. It creates 500,000 reasoning traces in English, Italian, and Spanish by retrieving medical information from Wikipedia and applies them to MedQA and MedMCQA datasets extended into Italian and Spanish. The approach improves performance in both few‑shot in‑context learning and supervised fine‑tuning, achieving state‑of‑the‑art results for 8B‑parameter LLMs and releasing all resources for further research.
MedRAGChecker is a claim-level verification framework designed for biomedical retrieval‑augmented generation (RAG). It decomposes generated answers into atomic claims and assesses each claim’s support by combining evidence‑grounded natural language inference with biomedical knowledge‑graph consistency signals. The aggregated claim decisions provide diagnostics that distinguish retrieval and generation failures, such as faithfulness, under‑evidence, contradiction, and safety‑critical errors, and the system is distilled into compact models for scalable evaluation.
The paper investigates why retrieval‑based open‑ended evaluation fails in medical fact verification. By creating two detailed taxonomies—one for retrieval‑stage errors across five quality dimensions and another for verifier‑reasoning errors across six steps—the authors automatically label evidence quality and reasoning errors using an LLM‑as‑Judge pipeline. Their large‑scale stress tests across multiple retrieval methods and verifier models show that increasing model size, reasoning effort, source breadth, or medical fine‑tuning does not eliminate these failure modes, indicating fundamental limits of the retrieve‑then‑verify paradigm in open‑ended medical contexts.
arXiv:2504. 07385v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly used for question-answering (QA), relying on static, pre-annotated references for evaluation poses significant challenges in cost, scalability, and completeness.