ArgHiTZ at ArchEHR-QA 2025: A Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality

• URL: http://arxiv.org/abs/2506.12886v1
• Date: Sun, 15 Jun 2025 15:32:49 GMT
• Title: ArgHiTZ at ArchEHR-QA 2025: A Two-Step Divide and Conquer Approach to Patient Question Answering for Top Factuality
• Abstract summary: This work presents three different approaches to address the ArchEHR-QA 2025 Shared Task on automated patient question answering.<n>We introduce an end-to-end prompt-based baseline and two two-step methods to divide the task, without utilizing any external knowledge.<n>Our best run achieved an overall score of 0.44, ranking 8th out of 30 on the leaderboard, securing the top position in overall factuality.
• Score: 0.9917494440952518
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This work presents three different approaches to address the ArchEHR-QA 2025 Shared Task on automated patient question answering. We introduce an end-to-end prompt-based baseline and two two-step methods to divide the task, without utilizing any external knowledge. Both two step approaches first extract essential sentences from the clinical text, by prompt or similarity ranking, and then generate the final answer from these notes. Results indicate that the re-ranker based two-step system performs best, highlighting the importance of selecting the right approach for each subtask. Our best run achieved an overall score of 0.44, ranking 8th out of 30 on the leaderboard, securing the top position in overall factuality.

Related papers

• Neural at ArchEHR-QA 2026: One Method Fits All: Unified Prompt Optimization for Clinical QA over EHRs [2.7732306355664753]
  We present our method for the ArchEHR-QA 2026 shared task at CL4Health@LREC 2026.<n>Our approach decouples the task into independent, modular stages and employs DSPy"s MIPROv21.5 to automatically discover high-performing prompts.
  arXiv  Detail & Related papers  (2026-05-11T17:27:30Z)
• QU-NLP at ArchEHR-QA 2026: Two-Stage QLoRA Fine-Tuning of Qwen3-4B for Patient-Oriented Clinical Question Answering and Evidence Sentence Alignment [1.0152838128195467]
  We present a unified system addressing both Subtask 3 (answer generation) and Subtask 4 (evidence sentence alignment) of the ArchEHR-QA Shared Task.<n>For Subtask 3, we apply two-stage Quantised Low-Rank Adaptation (QLoRA) to Qwen3-4B loaded in 4-bit NF4 quantisation.<n>For Subtask 4, we develop a weighted ensemble of three retrieval methods - BM25 with relative thresholding, TF-IDF cosine similarity, and a fine-tuned cross-encoder.
  arXiv  Detail & Related papers  (2026-03-26T11:24:13Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think [51.0691253204425]
  We analyze intermediate reasoning steps, termed subthoughts, to answer two questions: Does the final answer reliably represent the model's optimal conclusion?<n>Our approach involves segmenting a reasoning trace into sequential subthoughts based on linguistic cues.<n>We find that aggregating these answers by selecting the most frequent one (the mode) often yields significantly higher accuracy compared to relying solely on the answer derived from the original complete trace.
  arXiv  Detail & Related papers  (2025-04-29T12:39:07Z)
• Active Ranking of Experts Based on their Performances in Many Tasks [72.96112117037465]
  We consider the problem of ranking n experts based on their performances on d tasks. We make a monotonicity assumption stating that for each pair of experts, one outperforms the other on all tasks.
  arXiv  Detail & Related papers  (2023-06-05T06:55:39Z)
• When and What to Ask Through World States and Text Instructions: IGLU NLP Challenge Solution [6.36729066736314]
  In collaborative tasks, effective communication is crucial for achieving joint goals. We aim to develop an intelligent builder agent to build structures based on user input through dialogue.
  arXiv  Detail & Related papers  (2023-05-09T20:23:17Z)
• Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems [71.33737787564966]
  End-to-end (E2E) task-oriented dialogue (ToD) systems are prone to fall into the so-called 'likelihood trap' We propose a reranking method which aims to select high-quality items from the lists of responses initially overgenerated by the system. Our methods improve a state-of-the-art E2E ToD system by 2.4 BLEU, 3.2 ROUGE, and 2.8 METEOR scores, achieving new peak results.
  arXiv  Detail & Related papers  (2022-11-07T15:59:49Z)
• Double Retrieval and Ranking for Accurate Question Answering [120.69820139008138]
  We show that an answer verification step introduced in Transformer-based answer selection models can significantly improve the state of the art in Question Answering. The results on three well-known datasets for AS2 show consistent and significant improvement of the state of the art.
  arXiv  Detail & Related papers  (2022-01-16T06:20:07Z)
• Adaptive Information Seeking for Open-Domain Question Answering [61.39330982757494]
  We propose a novel adaptive information-seeking strategy for open-domain question answering, namely AISO. According to the learned policy, AISO could adaptively select a proper retrieval action to seek the missing evidence at each step. AISO outperforms all baseline methods with predefined strategies in terms of both retrieval and answer evaluations.
  arXiv  Detail & Related papers  (2021-09-14T15:08:13Z)
• IIE-NLP-Eyas at SemEval-2021 Task 4: Enhancing PLM for ReCAM with Special Tokens, Re-Ranking, Siamese Encoders and Back Translation [8.971288666318719]
  This paper introduces our systems for all three subtasks of SemEval-2021 Task 4: Reading of Abstract Meaning. We well-design many simple and effective approaches adapted to the backbone model (RoBERTa) Experimental results show that our approaches achieve significant performance compared with the baseline systems.
  arXiv  Detail & Related papers  (2021-02-25T10:51:48Z)
• Hierarchical Ranking for Answer Selection [19.379777219863964]
  We propose a novel strategy for answer selection, called hierarchical ranking. We introduce three levels of ranking: point-level ranking, pair-level ranking, and list-level ranking. Experimental results on two public datasets, WikiQA and TREC-QA, demonstrate that the proposed hierarchical ranking is effective.
  arXiv  Detail & Related papers  (2021-02-01T07:35:52Z)
• MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering [0.0]
  This paper introduces MIX, a multi-task deep learning approach to solve open-ended question-answering.<n>We design our system as a multi-stage pipeline of 3 building blocks: a BM25-based Retriever to reduce the search space, a RoBERTa-based Scorer, and an Extractor to rank retrieved paragraphs and extract relevant text spans.<n>Our system is on par with state-of-the-art performances on the squad-open benchmark while being simpler conceptually.
  arXiv  Detail & Related papers  (2020-12-17T17:22:30Z)
• A Study on Efficiency, Accuracy and Document Structure for Answer Sentence Selection [112.0514737686492]
  In this paper, we argue that by exploiting the intrinsic structure of the original rank together with an effective word-relatedness encoder, we can achieve competitive results. Our model takes 9.5 seconds to train on the WikiQA dataset, i.e., very fast in comparison with the $sim 18$ minutes required by a standard BERT-base fine-tuning.
  arXiv  Detail & Related papers  (2020-03-04T22:12:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.