CAR: Query-Guided Confidence-Aware Reranking for Retrieval-Augmented Generation
School of Computer Science and Technology, Dalian University of Technology（大连理工大学计算机科学与技术学院）；School of Information Engineering, Dalian Ocean University（大连海洋大学信息工程学院）；School of Information Engineering, Liaodong University（辽东学院信息工程学院）；Information Technology Center, Qinghai University（青海大学信息技术中心）；College of Health-Preservation and Wellness, Dalian Medical University（大连医科大学养生与健康学院）；Tencent（腾讯）
Retrieval-augmented generation (RAG) relies on evidence ranking to determine what information is exposed to the generator, yet existing retrieval and reranking methods primarily estimate query--document relevance. Relevance, however, is not equivalent to generator-side usefulness: a relevant passage may introduce ambiguity or distraction, whereas a lower-ranked passage may stabilize the generator's answer. We present CAR (Confidence-Aware Reranking), a training-free rank-correction framework that uses query-only answer stability as a control and measures each candidate by the change it induces in sampled-answer semantic stability. This controlled contrast estimates a document's marginal contribution to generator behavior without treating semantic stability as relevance or calibrated correctness. CAR converts these confidence changes into coarse precedence constraints and returns the feasible ranking with minimum Kendall distance from the baseline, preserving existing pairwise preferences unless generator-side evidence supports reversing them. Experiments on NQ, HotpotQA and FEVER across sparse and dense retrievers, seven ranking methods and three generator families show robust improvements. In the BM25-centered main analysis, CAR achieves a \textbf{+5.53\% mean relative NDCG@5 gain}; on the fixed NQ-answerable downstream evaluation, it improves token-level F1 by \textbf{+0.43 points}, with ranking and generation gains strongly aligned across rankers ($ρ= 0.93$). These results position CAR as a deployment-friendly, generator-aware correction layer that complements relevance while preserving informative prior rankings. CAR requires neither task-specific training nor access to model internals such as logits or hidden states, making it applicable to black-box LLMs through generated outputs alone.
This paper presents a novel reranking method to better choose the optimal query graph, a sub-graph of knowledge graph, to retrieve the answer for an input question in Knowledge Base Question Answering (KBQA). Existing methods suffer from a severe problem that there is a significant gap between top-1 performance and the oracle score of top-n results. To address this problem, our method divides the choosing procedure into two steps: query graph ranking and query graph reranking. In the first step, we provide top-n query graphs for each question. Then we propose to rerank the top-n query graphs b…
Technische Hochschule Nürnberg Georg Simon Ohm（纽伦堡乔治·西蒙·欧姆应用科学大学）
The CrisisFACTS Track aims to tackle challenges such as multi-stream fact-finding in the domain of event tracking; participants' systems extract important facts from several disaster-related events while incorporating the temporal order. We propose a combination of retrieval, reranking, and the well-known Integer Linear Programming (ILP) and Maximal Marginal Relevance (MMR) frameworks. In the former two modules, we explore various methods including an entity-based baseline, pre-trained and fine-tuned Question Answering systems, and ColBERT. We then use the latter module as an extractive summar…
PankRAG: Enhancing Graph Retrieval via Globally Aware Query Resolution and Dependency-Aware Reranking Mechanism
College of Computer Science, Beijing university of technology, Beijing, China（北京理工大学计算机科学学院）；Department of Computer Science and Engineering, Bologna University, Bologna, Italy（博洛尼亚大学计算机科学与工程系）
5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
University of Information Technology, Ho Chi Minh City, Vietnam（信息技术大学，胡志明市，越南）；Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam（越南胡志明市国家大学，胡志明市，越南）
GRADA: Graph-based Reranking against Adversarial Documents Attack
University of Melbourne（墨尔本大学）；University of Edinburgh（爱丁堡大学）；University College London（伦敦大学学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Macquarie University（麦觉里大学）
LUMIA Lab, Shanghai Jiao Tong University（上海交通大学LUMIA实验室）；Tiansuan Lab, Ant Group Co., Ltd.（蚂蚁集团天算实验室）；SJTU Paris Elite Institute of Technology（上海交通大学巴黎精英理工学院）
Artificial Intelligence Application Research Center, Huawei Technologies（华为技术有限公司人工智能应用研究中心）
Query expansion with pseudo-relevance feedback (PRF) is a powerful approach to enhance the effectiveness in information retrieval. Recently, with the rapid advance of deep learning techniques, neural text generation has achieved promising success in many natural language tasks. To leverage the strength of text generation for information retrieval, in this article, we propose a novel approach which effectively integrates text generation models into PRF-based query expansion. In particular, our approach generates augmented query terms via neural text generation models conditioned on both the ini…
ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning
Chalmers University of Technology, Sweden（瑞典查尔姆斯理工大学）；University of Leeds, United Kingdom（英国利兹大学）；Carl von Ossietzky University of Oldenburg, Germany（德国奥尔登堡卡尔·冯·奥西特齐大学）
Beyond Top-$k$ Skill Retrieval: Diversity-Aware Skill Routing for LLM Agents
Virginia Tech（弗吉尼亚理工大学）；University of Southern California（南加州大学）；Adobe Research（Adobe研究院）；Dolby Labs（杜比实验室）；Texas A&M University（德克萨斯A&M大学）；Arizona State University（亚利桑那州立大学）
Information retrieval (IR) for precision medicine (PM) often involves looking for multiple pieces of evidence that characterize a patient case. This typically includes at least the name of a condition and a genetic variation that applies to the patient. Other factors such as demographic attributes, comorbidities, and social determinants may also be pertinent. As such, the retrieval problem is often formulated as ad hoc search but with multiple facets (e.g., disease, mutation) that may need to be incorporated. In this paper, we present a document reranking approach that combines neural query-do…
This paper challenges a cross-genre document retrieval task, where the queries are in formal writing and the target documents are in conversational writing. In this task, a query, is a sentence extracted from either a summary or a plot of an episode in a TV show, and the target document consists of transcripts from the corresponding episode. To establish a strong baseline, we employ the current state-of-the-art search engine to perform document retrieval on the dataset collected for this work. We then introduce a structure reranking approach to improve the initial ranking by utilizing syntacti…
The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark---and can be considered to be an efficient (but slightly less effective) alternative to BERT-based ranking models. In this work, we extend the TK architecture to the full retrieval setting by incorporating the query term independence assumption. Furthermore, to reduce the memory complexity of the Transformer layers with respect to the input sequence length, we propose a new Conformer layer. We show that the Conformer's GPU memory requirement scales linearly with input sequence le…
A Systematic Study of Retrieval Pipeline Design for Retrieval-Augmented Medical Question Answering
Department of Mechatronics & Industrial Engineering, Chittagong University of Engineering & Technology（吉大港工程与技术大学机电与工业工程系）；Department of Mechanical Engineering, Chittagong University of Engineering & Technology（吉大港工程与技术大学机械工程系）
Hong Kong Baptist University（香港浸会大学）；University of Perugia（佩鲁贾大学）
In this work several semantic approaches to concept-based query expansion and reranking schemes are studied and compared with different ontology-based expansion methods in web document search and retrieval. In particular, we focus on concept-based query expansion schemes, where, in order to effectively increase the precision of web document retrieval and to decrease the users browsing time, the main goal is to quickly provide users with the most suitable query expansion. Two key tasks for query expansion in web document retrieval are to find the expansion candidates, as the closest concepts in…
University of Glasgow（格拉斯哥大学）；Microsoft Research（微软研究院）；Carnegie Mellon University（卡内基梅隆大学）
The Conversational Assistance Track (CAsT) is a new track for TREC 2019 to facilitate Conversational Information Seeking (CIS) research and to create a large-scale reusable test collection for conversational search systems. The document corpus is 38,426,252 passages from the TREC Complex Answer Retrieval (CAR) and Microsoft MAchine Reading COmprehension (MARCO) datasets. Eighty information seeking dialogues (30 train, 50 test) are an average of 9 to 10 questions long. Relevance assessments are provided for 30 training topics and 20 test topics. This year 21 groups submitted a total of 65 runs …
LegalMALR:Multi-Agent Query Understanding and LLM-Based Reranking for Chinese Statute Retrieval
Faculty of Data Science（数据科学学院）；City University of Macau（澳门城市大学）；Shenzhen Key Laboratory for High Performance Data Mining（深圳高性能数据挖掘重点实验室）；Shenzhen Institutes of Advanced Technology（深圳先进技术研究所）；Chinese Academy of Sciences（中国科学院）；Southern University of Science and Technology（南方科技大学）；Artificial Intelligence Research Institute（人工智能研究院）；Shenzhen University of Advanced Technology（深圳大学先进技术学院）
