RETRIEVAL-AUGMENTED GENERATION

A Grounded Preference Model for LLM Alignment (2024.findings-acl)

Challenge:	Existing methods for retrieval-augmented generation focus on text rather than video.
Approach:	They propose a benchmark to generate Wikipedia-style articles from multiple videos . they propose 'collaborative article generation' that leverages an r1-style reasoning model and a VideoLLM to draw higher-level inferences about the target event than is possible with VideoLLms alone.
Outcome:	The proposed method outperforms existing methods in oracle retrieval and RAG settings while suggesting promising avenues for future work.

Copied to clipboard

Tahira Naseem, Guangxuan Xu, Sarathkrishna Swaminathan, Asaf Yehudai, Subhajit Chaudhury, Radu Florian, Ramón Astudillo, Asim Munawar

Benchmarking LLM’s Capability in Reasoning over Conflicting Web References (2026.acl-long)

Challenge:	Large Language Models (LLMs) suffer from factual inconsistency and hallucination despite recent advances . training a preference model requires substantial human annotation, which is expensive and labor-intensive.
Approach:	They propose to generate synthetic grounded preference data and train a Grounded Preference Model to assess the overall quality of grounded responses.
Outcome:	The proposed model can generate much better grounded responses as judged by GPT4 and achieves the TRUE faithfulness Benchmark.

Copied to clipboard

Yizhen Yuan, Rui Kong, Dongze Li, Yuanchun Li, Yunxin Liu

Marcel: A Lightweight and Open-Source Conversational Agent for University Student Support (2025.emnlp-demos)

Challenge:	Large language models (LLMs) integrated with retrieval-augmented generation (RAG) are a dominant framework for building intelligent assistants.
Approach:	They propose a benchmark to evaluate LLMs' reasoning capability over real-world conflicting documents retrieved from the web.
Outcome:	The proposed benchmark evaluates LLMs' reasoning capability over real-world conflicting documents retrieved from the web.

Copied to clipboard

Jan Trienes, Anastasiia Derzhanskaia, Roland Schwarzkopf, Markus Mühling, Jörg Schlötterer, Christin Seifert

MuRAR: A Simple and Effective Multimodal Retrieval and Answer Refinement Framework for Multimodal Question Answering (2025.coling-demos)

Challenge:	Existing systems that provide contextually relevant information are difficult to deploy in a university setting . a number of universities are developing or using chatbots to support prospective students .
Approach:	They propose a conversational agent called Marcel that uses retrieval-augmented generation to provide contextually relevant information.
Outcome:	The proposed system is designed to provide fast and personalized responses while reducing workload.

Copied to clipboard

Zhengyuan Zhu, Daniel Lee, Hong Zhang, Sai Sree Harsha, Loic Feujio, Akash Maharaj, Yunyao Li

MIRAGE-Bench: Automatic Multilingual Benchmark Arena for Retrieval-Augmented Generation Systems (2025.naacl-long)

Challenge:	Recent advances in retrieval-augmented generation have demonstrated impressive performance on the question-answering task.
Approach:	They propose a retrieval-augmented generation framework that generates an initial text answer and retrieves multimodal data relevant to the snippets of the initial text.
Outcome:	The proposed framework can be easily integrated into an enterprise chatbot to produce multimodal answers with minimal modifications.

Copied to clipboard

Nandan Thakur, Suleman Kazi, Ge Luo, Jimmy Lin, Amin Ahmad

Multilinguality

Challenge:	Traditional retrieval-augmented generation benchmarks use heuristics as the ground truth for evaluation, but require an expensive large language model (LLM) as a judge for a reliable evaluation.
Approach:	They propose to use large language models as a judge for retrieval-augmented generation benchmarks . they use heuristic metrics as input and a large language model as heuriistic input .
Outcome:	The proposed method couples heuristic features with large language models as judge for evaluation.

Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs (2024.emnlp-main)

Copied to clipboard

Oded Ovadia, Menachem Brief, Moshik Mishaeli, Oren Elisha

Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA (2026.eacl-srw)

Challenge:	Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights.
Approach:	They compare unsupervised fine-tuning and retrieval-augmented generation approaches to learning new factual information.
Outcome:	The proposed models outperform unsupervised fine-tuning and retrieval-augmented generation (RAG) on knowledge-intensive tasks across different topics.

Copied to clipboard

Klejda Alushi, Jan Strich, Chris Biemann, Martin Semmann

Rankify: A Comprehensive Python Toolkit for Retrieval, Re-Ranking, and Retrieval-Augmented Generation (2026.acl-demo)

Challenge:	Existing studies evaluate RAG methods in isolation and focus on single-turn settings.
Approach:	They compare retrieval-augmented generation methods for multi-turn conversational QA with those that use dialogue history and coreference to ground large language models.
Outcome:	The proposed methods outperform vanilla RAG and advanced methods fail to yield gains and can even degrade performance below the No-RAG baseline.

Copied to clipboard

Abdelrahman Abdallah, Bhawna Piryani, Jamshid Mozafari, Andreas Herzinger, Jamie Holdcroft, Adam Jatowt

ReproEvalCard: A Reporting Standard for Reproducible Evaluation of LLM Pipelines (2026.acl-short)

Challenge:	Rankify unifies retrieval-augmented generation (RAG) and retrieval based question answering systems.
Approach:	They propose an open-source Python toolkit that unifies retrieval-augmented generation in a single modular framework.
Outcome:	The proposed framework unifies retrieval-augmented generation (RAG) tools in a single modular framework.

Copied to clipboard

Priyaranjan Pattnayak, Apoorv Bhatia

DSRAG: A Double-Stream Retrieval-Augmented Generation Framework for Countless Intent Detection (2025.naacl-industry)

Challenge:	Existing evaluation standards for multistage pipelines are inconsistent, leaving the reproducibility and independent validation of published evaluations unclear.
Approach:	They propose a lightweight reporting standard that specifies the minimum artifacts required to reproduce and validate LLM evaluations.
Outcome:	The proposed standard audits 55 pipeline-based LLM papers published between 2022 and 2025 and quantifies the availability of reproducibility-critical evaluation artifacts.

Copied to clipboard

Pei Guo, Enjie Liu, Ruichao Zhong, Mochi Gao, Yunzhi Tan, Bo Hu, Zang Li

On Improving Repository-Level Code QA for Large Language Models (2024.acl-srw)

Challenge:	Current intent detection work experiments with minor intent categories.
Approach:	They propose a retrieval-augmented generation framework that uses query-to-query and query- to-metadata approaches to retrieve intents from metadata.
Outcome:	The proposed framework improves on query-to-query (Q2Q) and query- to-metadata (Q 2M) approaches.

Copied to clipboard

Jan Strich, Florian Schneider, Irina Nikishina, Chris Biemann

Towards Practical and Knowledgeable LLMs for a Multilingual World: A Thesis Proposal (2025.naacl-srw)

Challenge:	Commercial AI-assisted programming Chatbots may generate incorrect information when requests go beyond the model training data or require additional knowledge.
Approach:	They propose to implement different self-alignment processes and retrieval-augmented generation pipelines to improve the copilot performance.
Outcome:	The proposed model improves the copilot performance on repository-level semantics, dependency between files, and meta-information about the repository.

Copied to clipboard

Bryan Li

Multilinguality

Challenge:	a proposed thesis examines the role that multilinguality occupies in the development of practical and knowledgeable LLMs.
Approach:	They propose to use multilingual knowledge to improve LLM performance on NLP tasks . they extend the territorial disputes benchmark to retrieval-augmented generation setting .
Outcome:	The proposed methods improve LLMs' performance on standard natural language processing tasks by leveraging their existing multilingual knowledge.

Chronocept: Instilling a Sense of Time in Machines (2026.eacl-srw)

Copied to clipboard

Krish Goel, Sanskar Pandey, KS Mahadevan, Harsh Kumar, Vishesh Khadaria

QuackIR: Retrieval in DuckDB and Other Relational Database Management Systems (2025.emnlp-industry)

Challenge:	Human cognition is deeply intertwined with a sense of time, known as Chronoception, which allows us to judge how long facts remain valid and when knowledge becomes outdated.
Approach:	They propose a model that captures nuanced patterns of emergence, decay, and peak relevance using skew-normal curves fitted along semantically decomposed temporal axes.
Outcome:	The proposed model captures nuanced patterns of emergence, decay, and peak relevance in two datasets.

Copied to clipboard

Yijun Ge, Zijian Chen, Jimmy Lin

Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent Improvement (2026.eacl-industry)

Challenge:	Existing vector databases for RAG are needed for large language models, but there are no alternatives.
Approach:	They propose to leverage existing relational databases for retrieval-augmented generation . they use duckDB, SQLite, and PostgreSQL integrations to demonstrate their effectiveness .
Outcome:	The proposed approach is comparable to existing IR tools.

Copied to clipboard

Aaditya Shukla, Sidney Knowles, Meenakshi Madugula, David Farris, Ryan Angilly, Santiago Pombo, Lu An, Anbang Xu, Abhinav Balasubramanian, Tan Yu, Jiaxiang Ren, Rama Akkiraju

Benchmarking Deep Search over Heterogeneous Enterprise Data (2025.emnlp-industry)

Challenge:	NVInfo AI is a generative AI agent that can be deployed in production without full-scale retraining or infrastructure overhauls.
Approach:	They propose to implement a retrieval-augmented generation (RAG)-driven data flywheel in NVInfo AI, a mixture-of-experts knowledge assistant, for 30,000 employees.
Outcome:	The proposed system addresses failures in retrieval-augmented generation pipelines and enables continuous learning.

Copied to clipboard

Prafulla Kumar Choubey, Xiangyu Peng, Shilpa Bhagavath, Kung-Hsiang Huang, Caiming Xiong, Chien-Sheng Wu

NEST: Nested Evidence Survival for Retrieval (2026.acl-industry)

Challenge:	Existing methods struggle to conduct deep searches and retrieve all necessary evidence.
Approach:	They propose a benchmark for evaluating deep search, a retrieval-augmented generation that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.
Outcome:	The proposed benchmarks show that even the best-performing agentic RAG methods achieve an average performance score of 32.96 on the benchmark.

Copied to clipboard

Akshay Verma, Siddharth Pillai, Prateek Sircar, Deepak Gupta

Assessing and Mitigating Medical Knowledge Drift and Conflicts in Large Language Models (2025.findings-emnlp)

Challenge:	Existing approaches to retrieval-augmented generation (RAG) rely on rigid heuristics or computational overhead.
Approach:	They propose a lightweight, training-free RAG framework that separates recall amplification from precision selection.
Outcome:	Evaluated on WebQuestions, HotpotQA and internalQA benchmarks, NEST outperforms strong adaptive RAG baselines.

Copied to clipboard

Weiyi Wu, Xinwen Xu, Chongyang Gao, Xingjian Diao, Siting Li, Lucas A. Salas, Jiang Gui

Live Football Commentary System Providing Background Information (2025.acl-demo)

Challenge:	Rapid medical concept drift can lead LLMs to provide incorrect or outdated advice.
Approach:	They propose to evaluate how large language models manage knowledge conflicts in clinical guidelines.
Outcome:	The proposed benchmark evaluates how LLMs manage varied knowledge conflicts in clinical guidelines.

Copied to clipboard

Yuichiro Mori, Chikara Tanaka, Aru Maekawa, Satoshi Kosugi, Tatsuya Ishigaki, Kotaro Funakoshi, Hiroya Takamura, Manabu Okumura

Challenge:	Existing studies on sports commentary generation focus on describing major events in the video, but real-world commentary often includes background information.
Approach:	They developed an audio commentary system that generates utterances with background information and play-by-play commentary for football matches.
Outcome:	The proposed system generates utterances with background information and play-by-play commentary for football matches.

ESG-KG: A Multi-modal Knowledge Graph System for Automated Compliance Assessment (2026.eacl-demo)

Copied to clipboard

Li-Yang Chang, Chih-Ming Chen, Hen-Hsen Huang, Ming-Feng Tsai, An-Zi Yen, Chuan-Ju Wang

Exploring Fine-Tuning for In-Context Retrieval and Efficient KV-Caching in Long-Context Language Models (2026.eacl-short)

Challenge:	Existing methods for ESG compliance assessment rely on fact-based retrieval methods.
Approach:	They propose a multi-modal information extraction pipeline to extract, structure, and evaluate sustainability reports.
Outcome:	The proposed system extracts, structures, and evaluates ESG-related content from text, tables, figures, and infographics.

Copied to clipboard

Francesco Maria Molfese, Momchil Hardalov, Rexhina Blloshmi, Bill Byrne, Adrià de Gispert

AIDA-SEAT: Towards Reliable AI Doctor Assistant via State-Evaluation-Action Tree Enhanced LLMs in Online Hospital (2026.acl-industry)

Challenge:	Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative to retrieval-augmented generation (RAG).
Approach:	They propose to use LCLMs to encode documents with context windows of millions of tokens to improve their performance.
Outcome:	The proposed training strategies improve long-context performance and their robustness under compression techniques.

Copied to clipboard

Lianxin Sun, Xiaoying Ying, Guangya Yu, Weiyan Zhang, Chenhao Guan, Hao He, Mingxi Shang, Jianhua Li, ChunMing Wang, Tong Ruan

Implementing Retrieval Augmented Generation Technique on Unstructured and Structured Data Sources in a Call Center of a Large Financial Institution (2025.naacl-industry)

Challenge:	Existing systems rely on large language models or retrieval-augmented generation (RAG) but these methods lack the explicit logical pathways essential for multi-step reasoning.
Approach:	They propose an AIDA-SEAT framework to provide reliable clinical decision-making support by transforming and modifying medical documents and doctors' state-evaluation-action trees.
Outcome:	The proposed framework achieves 1.01% higher than current state-of-the-art (SOTA) baselines across five departments, including common RAG-based methods.

Copied to clipboard

Syed Shariyar Murtaza, Yifan Nie, Elias Avan, Utkarsh Soni, Wanyu Liao, Adam Carnegie, Cyril John Mathias, Junlin Jiang, Eugene Wen

ConfReady: A RAG based Assistant and Dataset for Conference Checklist Responses (2025.emnlp-demos)

Challenge:	generative AI models can extract accurate facts from external unstructureddata sources.
Approach:	They propose to use data embeddings to enhance RAG for retrieving facts from structured data sources, achieving low latency and high reliability.
Outcome:	The proposed model achieves low latency and high reliability and average response time of 7.33 seconds.

Copied to clipboard

Michael Galarnyk, Rutwik Routu, Vidhyakshaya Kannan, Kosha Bheda, Prasun Banerjee, Agam Shah, Sudheer Chava

Granite Guardian: Comprehensive LLM Safeguarding (2025.naacl-industry)

Challenge:	ARR Responsible NLP Research checklist is designed to encourage best practices for responsible research . previous research has shown that self-reported checklist responses don't always accurately represent papers .
Approach:	They propose a retrieval-augmented generation application that can be used to assist authors with conference checklists.
Outcome:	The proposed application can be used to help authors with conference checklists and review their work.

Copied to clipboard

Inkit Padhi, Manish Nagireddy, Giandomenico Cornacchia, Subhajit Chaudhury, Tejaswini Pedapati, Pierre Dognin, Keerthiram Murugesan, Erik Miehling, Martín Santillán Cooper, Kieran Fraser, Giulio Zizzo, Muhammad Zaid Hameed, Mark Purcell, Michael Desmond, Qian Pan, Inge Vejsbjerg, Elizabeth M. Daly, Michael Hind, Werner Geyer, Ambrish Rawat, Kush R. Varshney, Prasanna Sattigeri

OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking (2025.emnlp-main)

Challenge:	a suite of advanced models is designed to detect and mitigate risks associated with prompts and responses.
Approach:	a team of researchers develop a model family to detect and mitigate risks associated with prompts and responses. the model family is based on the Granite 3.0 language models.
Outcome:	a new model family is designed to detect and mitigate risks associated with prompts and responses.

Copied to clipboard

Zekun Xi, Wenbiao Yin, Jizhan Fang, Jialong Wu, Runnan Fang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang

PathBuilder: A Quality-Controlled LLM System for Personalized Learning Pathways (2026.acl-demo)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated remarkable progress in machine writing such as open domain long-form generation.
Approach:	They propose a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection to improve the knowledge density of generated articles.
Outcome:	The proposed framework improves the knowledge density of generated articles without compromising metrics such as coherence and depth.

Copied to clipboard

Jasper Meynard Arana, John Andrew Mañacop, John Allen Manacop, Roy Andrew Garcia, Keith Rick Piniera, Kristine Ann M. Carandang, Ethan Robert Casin, Christian Alis, Christopher Monterola

ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking (2026.findings-acl)

Challenge:	Large language models (LLMs) enable scalable content generation for personalized learning, but reliability and pedagogical alignment remain open challenges.
Approach:	They propose a web-based system that integrates expert-validated assessment, retrieval-augmented generation (RAG), and an LLM-as-a-Judge validation loop within a closed instructional pipeline.
Outcome:	The proposed system achieves a gain of 37.9 percentage points and a large effect size in a real-world deployment with 179 registered users.

Copied to clipboard

Xianming LI, Aamir Shakir, Rui Huang, Julius Lipp, Benjamin Clavié, Jing Li

An Automatic Method to Estimate Correctness of RAG (2025.coling-industry)

Challenge:	Recent Large Language Models (LLMs) have demonstrated remarkable performance in document reranking tasks.
Approach:	They propose a two-stage training approach for document reranking using reinforcement learning and fine-grained score learning.
Outcome:	The proposed approach outperforms open-source and proprietary reranking models on BEIR benchmark.

Copied to clipboard

Chi Zhang, Vivek V. Datla, Aditya Shrivastava, Alfy Samuel, Zhiqi Huang, Anoop Kumar, Daben Liu

Challenge:	Existing methods to assess the correctness of RAG models fail to capture the model’s internal state during answer generation.
Approach:	They propose a method to predict the correctness of RAG models by modeling the model’s uncertainty on quantified perturbations of input.
Outcome:	Extensive experiments across multiple large language models show that the proposed approach quantifies RAG robustness by aligning predictions with ground truth with a MSE 0.002 while offering flexibility for diverse qualitative metrics.

CarExpert: Leveraging Large Language Models for In-Car Conversational Question Answering (2023.emnlp-industry)

Copied to clipboard

Md Rashad Al Hasan Rony, Christian Suess, Sinchana Ramakanth Bhat, Viju Sudhi, Julia Schneider, Maximilian Vogel, Roman Teucher, Ken Friedl, Soumya Sahoo

An Information Bottleneck Perspective for Effective Noise Filtering on Retrieval-Augmented Generation (2024.acl-long)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance by following natural language instructions without fine-tuning them on domain-specific tasks and data.
Approach:	They propose an in-car retrieval-augmented conversational question-answering system that uses large language models to generate natural, safe and domain-specific answers.
Outcome:	The proposed system outperforms state-of-the-art LLMs in generating safe and domain-specific answers.

Copied to clipboard

Kun Zhu, Xiaocheng Feng, Xiyuan Du, Yuxuan Gu, Weijiang Yu, Haotian Wang, Qianglong Chen, Zheng Chu, Jingchang Chen, Bing Qin

Language Models “Grok” to Copy (2025.naacl-short)

Challenge:	Experimental results show that retrieval-augmented generation improves accuracy and relevance of large language models.
Approach:	They propose to introduce the information bottleneck theory into retrieval-augmented generation by maximizing mutual information between compression and ground output while minimizing mutual information .
Outcome:	The proposed approach improves accuracy and correctness of answer generation and conciseness with 2.5% compression rate.

Copied to clipboard

Ang Lv, Ruobing Xie, Xingwu Sun, Zhanhui Kang, Rui Yan

CORD: Balancing COnsistency and Rank Distillation for Robust Retrieval-Augmented Generation (2025.naacl-short)

Challenge:	We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context.
Approach:	They propose that Transformer-based language models develop copying abilities similarly to grokking . they argue that the connection between groking and context copying can improve in-context performance.
Outcome:	The proposed model development is similar to grokking, but the speed is independent of tokens trained.

Copied to clipboard

Youngwon Lee, Seung-won Hwang, Daniel F Campos, Filip Graliński, Zhewei Yao, Yuxiong He

AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Framework (2024.lrec-main)

Challenge:	Existing methods to ground large language models fail to adequately attend to all contexts . position bias is hindered by retrieval-augmented generation, which requires constant attention .
Approach:	They propose to augment and distill training instances with their perturbed positions to encourage consistent predictions . they also propose to balance COnsistency and Rank Distillation by combining noise-controlled perturbations with augmentation and distillation.
Outcome:	The proposed method outperforms existing methods in diverse RAG benchmarks.

Copied to clipboard

Xiang Li, Zhenyu Li, Chen Shi, Yong Xu, Qing Du, Mingkui Tan, Jun Huang

What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations (2026.acl-short)

Challenge:	Currently, ML&DL methods fail to provide reasons for stock trend predictions, lacking interpretability and reasoning processes. large language models (LLMs) suffer from hallucinations and are unable to keep up with the latest information.
Approach:	They develop a method to train large language models to handle financial analysis tasks . they use AlphaFin datasets to compare performance with traditional methods .
Outcome:	The proposed method improves stock trend prediction and financial question answering tasks.

Copied to clipboard

Yujie Luo, Zhuoyun Yu, Xuehai Wang, Yuqi Zhu, Ningyu Zhang, Lanning Wei, Lun Du, Da Zheng, Huajun Chen

SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generation (2024.findings-emnlp)

Challenge:	Existing approaches to replicate AI research are limited by insufficient background knowledge and the limitations of retrieval-augmented generation methods.
Approach:	They propose a pluggable, paper-centric knowledge base that integrates code snippets and technical insights extracted from scientific literature into a verifiable, executable representation.
Outcome:	The proposed knowledge base shows significant performance gains on paperBench when integrated into three agent frameworks with two different LLMs.

Copied to clipboard

Minda Hu, Licheng Zong, Hongru Wang, Jingyan Zhou, Jingjing Li, Yichen Gao, Kam-Fai Wong, Yu Li, Irwin King

MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation (2025.acl-industry)

Challenge:	Existing retrieval-augmented approaches to large language models face performance limitations due to the lack of publicly available training data.
Approach:	They propose a plug-and-play LLM-based retrieval method called Self-Rewarding Tree Search based on Monte Carlo Tree Search and a self-rewarding paradigm to address these limitations.
Outcome:	The proposed method improves the performance of the BM25 retriever and surpasses the baseline of self-reflection in both efficiency and scalability.

Copied to clipboard

Hsin-Ling Hsu, Cong-Tinh Dao, Luning Wang, Zitao Shuai, Thao Nguyen Minh Phan, Jun-En Ding, Chun-Chieh Liao, Pengfei Hu, Xiaoxue Han, Chih-Ho Hsu, Dongsheng Luo, Wen-Chih Peng, Feng Liu, Fang-Ming Hung, Chenwei Wu

SchemaRAG: Dynamic Large Schema Reduction for LLM-driven Structured Information Extraction (2026.acl-industry)

Challenge:	Existing systems focus primarily on assessment rather than treatment planning.
Approach:	They propose a framework that structures LLM reasoning to align with real-life workflows.
Outcome:	The proposed framework outperforms baseline approaches in assessment accuracy and treatment plan quality.

Copied to clipboard

Sin Yu Bonnie Ho, Arlie Coles, Erik Larsson, Eric Marshall, Nathan Bodenstab, Paul Vozila

Information Extraction & Text Mining

Challenge:	Structured information extraction (IE) pairs values from unstructured text with schema-defined keys.
Approach:	They propose a retrieval-augmented generation framework that prunes the output schema space for schema-conditioned information extraction tasks by leveraging schema metadata and few-shot examples.
Outcome:	The proposed framework can achieve up to 8.8% increase in micro-F1, 47% reduction in latency, and 48% reduction in token costs on real-world healthcare and e-commerce datasets.

Pointwise Mutual Information as a Performance Gauge for Retrieval-Augmented Generation (2025.naacl-long)

Copied to clipboard

Tianyu Liu, Jirui Qi, Paul He, Arianna Bisazza, Mrinmaya Sachan, Ryan Cotterell

DQA: Diagnostic Question Answering for IT Support (2026.acl-industry)

Challenge:	Existing methods to improve language models' performance do not exploit this phenomenon .
Approach:	They propose to use contextual information to select and construct prompts that improve model performance.
Outcome:	The proposed methods show that the mutual information between a context and a question is an effective gauge for language model performance.

Copied to clipboard

Vishaal Kapoor, Mariam Dundua, Evren Yortucboylu, Sarthak Ahuja, Neda Kordjazi, Yiming Li, Vaibhavi padala, Derek Ho, Jennifer Whitted, Rebecca Steinert

Learning to Explore and Select for Coverage-Conditioned Retrieval-Augmented Generation (2025.findings-naacl)

Challenge:	a diagnostic question-answering framework maintains persistent diagnostic state and aggregates retrieved cases at the level of root causes rather than individual documents.
Approach:	They propose a diagnostic question-answering framework that maintains persistent diagnostic state . it aggregates retrieved cases at the level of root causes rather than individual documents .
Outcome:	The framework achieves a 78.7% success rate under trajectory-level success criterion compared to a multi-turn RAG baseline . the framework reduces average turns from 8.4 to 3.9, compared with a single-turn baseline crim.

Copied to clipboard

Takyoung Kim, Kyungjae Lee, Young Rok Jang, Ji Yong Cho, Gangwoo Kim, Minseok Cho, Moontae Lee

SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs (2025.naacl-long)

Challenge:	Recent advances of large language models (LLMs) have enabled them to provide long and detailed responses by leveraging their parametric knowledge.
Approach:	They introduce a dataset of 10K hierarchical sets of information-seeking subqueries that define structured boundaries for outline creation and evaluation in C2 scenarios.
Outcome:	The proposed model generates higher-quality outlines that better fulfill diverse user needs when trained with alignment techniques like DPO.

Copied to clipboard

Zhichao Shi, Shaoling Jing, Yi Cheng, Hao Zhang, Yuanzhuo Wang, Jie Zhang, Huawei Shen, Xueqi Cheng

Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding (2024.acl-long)

Challenge:	Large Language Models (LLMs) have been used to evaluate the safety of their users . however, evaluation questions in current benchmarks are too straightforward and difficult to update with practical relevance due to their lack of correlation with real-world events.
Approach:	They propose a question-generation framework to evaluate the safety of LLMs in the Chinese context.
Outcome:	The proposed framework reduces decline rate while maintaining similar attack success rate.

Copied to clipboard

Zhihan Zhang, Yixin Cao, Chenchen Ye, Yunshan Ma, Lizi Liao, Tat-Seng Chua

Utility-Focused LLM Annotation for Retrieval and Retrieval-Augmented Generation (2025.emnlp-main)

Challenge:	Existing research in complex event analysis has made significant strides but is constrained by inadequate natural language processing techniques.
Approach:	They propose a novel approach using Large Language Models to extract and analyze the event chain within TCE, characterized by their key points and timestamps.
Outcome:	The proposed model performs comparable to models with long context window and retrieval-augmented generation method in three distinct tasks .

Copied to clipboard

Hengran Zhang, Minghao Tang, Keping Bi, Jiafeng Guo, Shihao Liu, Daiting Shi, Dawei Yin, Xueqi Cheng

Static Models, Dynamic World: A Unified Perspective on Temporal Perception in Large Language Models (2026.findings-acl)

Challenge:	Existing studies on large language models for document utility annotations have shown that they improve retrieval performance and RAG outcomes compared to models trained on human annotations.
Approach:	They propose a model that maximizes their summed marginal likelihood to annotate document utility on multiple positive samples per query.
Outcome:	The proposed model maximizes the marginal likelihood of multiple positive samples per query.

Copied to clipboard

Chenhao Li, Dandan Song, Changzhi Zhou, Jun Yang, Yuhang Tian, Huipeng Ma, Guangyuan Feng, Luan Zhang, Xudong Li, Ke Duan

EXPLAIN: Enhancing Retrieval-Augmented Generation with Entity Summary (2025.acl-industry)

Challenge:	Large language models are trained on static corpora but deployed in a dynamic world . a foundational tension remains between time and the ability to understand it .
Approach:	They formalize temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers.
Outcome:	The proposed framework formalizes temporal queries in an information-theoretic framework based on parametric reachability of temporal premises and answers . the framework induces four temporal information regimes corresponding to internal reasoning, answer recency, premise anchoring, and genuine world indeterminacy .

Copied to clipboard

Yaozhen Liang, Xiao Liu, Jiajun Yu, Zhouhua Fang, Qunsheng Zou, Linghan Zheng, Yong Li, Zhiwei Liu, Haishuai Wang

Explainability & Interpretability in NLP

Challenge:	Existing document question answering methods reduce inference costs and input tokens.
Approach:	They propose a retrieval-augmented generation method that automatically extracts useful entities and generates summaries from documents.
Outcome:	The proposed method surpasses baseline retrieval-augmented generation (RAG) and long-context question answering (LC) methods achieve higher accuracy by processing entire documents, but at the cost of increased computational Corresponding authors.

RAC: Retrieval-augmented Conversation Dataset for Open-domain Question Answering in Conversational Settings (2024.emnlp-industry)

Copied to clipboard

Bonggeun Choi, JeongJae Park, Yoonsung Kim, Jaehyun Park, Youngjoong Ko

Self-Bootstrapped Visual-Language Model for Knowledge Selection and Question Answering (2024.emnlp-main)

Challenge:	Existing studies constrain questions and answers within predefined contexts, excluding the retrieval process.
Approach:	They present a retrieval-augmented conversation dataset that addresses key challenges . they propose a system that combines query rewriting and retrieval with reranking .
Outcome:	The proposed system improves query rewriting, retrieval, reranking, and response generation performance.

Copied to clipboard

Dongze Hao, Qunbo Wang, Longteng Guo, Jie Jiang, Jing Liu

MMSearch-R1: Incentivizing LMMs to Search (2026.acl-long)

Challenge:	a framework that leverages the visual-language model to select key knowledge retrieved by DPR and answer questions improves performance of the baseline on the open-domain Knowledge-based VQA benchmark, OK-VQA.
Approach:	They propose a framework that leverages visual-language models to retrieve related knowledge . they use dense passage retrieval to retrieve knowledge related to visual-linguistics .
Outcome:	The proposed framework significantly improves the baseline on the open-domain Knowledge-based VQA benchmark, OK-VQA.

Copied to clipboard

Jinming Wu, Zihao Deng, Wei Li, Yiding Liu, Bo You, Bo Li, Zejun MA, Ziwei Liu

CLaMP 3: Universal Music Information Retrieval Across Unaligned Modalities and Unseen Languages (2025.findings-acl)

Challenge:	Existing approaches to deploying large multimodal models rely on rigid pipelines . Existing methods such as retrieval-augmented generation and prompt engineered search rely only on rigid knowledge sources.
Approach:	They propose a framework that enables LMMs to perform on-demand, multi-turn search in real-world Internet environments.
Outcome:	The proposed model outperforms existing models while reducing search calls by over 30%.

Copied to clipboard

Shangda Wu, Guo Zhancheng, Ruibin Yuan, Junyan Jiang, SeungHeon Doh, Gus Xia, Juhan Nam, Xiaobing Li, Feng Yu, Maosong Sun

Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts (2024.findings-emnlp)

Challenge:	Music information retrieval (MIR) is a field that aims at developing computational tools for processing, organizing, and accessing music data.
Approach:	They propose a framework that aligns music modalities with multilingual text in a shared representation space.
Outcome:	Experiments show CLaMP 3 performs state-of-the-art on multiple MIR tasks . it surpasses baselines and shows excellent generalization in multimodal and multilingual contexts .

Copied to clipboard

Youna Kim, Hyuhng Joon Kim, Cheonbok Park, Choonghyun Park, Hyunsoo Cho, Junyeob Kim, Kang Min Yoo, Sang-goo Lee, Taeuk Kim

EvoR: Evolving Retrieval for Code Generation (2024.findings-emnlp)

Challenge:	Recent research has been developed to amplify contextual knowledge over parametric knowledge of large language models (LLMs) in knowledge-intensive tasks such as open-domain question-answering .
Approach:	They propose to amplify contextual knowledge over parametric knowledge of large language models (LLMs) by contrastive decoding to leverage contextual influence effectively.
Outcome:	The proposed approach improves open-domain question answering tasks especially in robustness by remaining undistracted by noisy contexts in retrieval-augmented generation.

Copied to clipboard

Hongjin Su, Shuyang Jiang, Yuhang Lai, Haoyuan Wu, Boao Shi, Che Liu, Qian Liu, Tao Yu

Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RL (2025.findings-emnlp)

Challenge:	Existing pipelines for retrieval-augmented code generation (RACG) use static knowledge bases with a single source, limiting adaptation capabilities of Large Language Models (LLMs) Extensive experiments demonstrate that EVOR achieves two to four times of execution accuracy compared to other methods such as Reflexion.
Approach:	They propose a retrieval-augmented code generation pipeline that employs the synchronous evolution of queries and diverse knowledge bases.
Outcome:	The proposed pipeline achieves two to four times of execution accuracy compared to other methods.

Copied to clipboard

Xiaoying Song, Anirban Saha Anik, Dibakar Barua, Pengcheng Luo, Junhua Ding, Lingzi Hong

Tagging-Augmented Generation: Assisting Language Models in Finding Intricate Knowledge In Long Contexts (2025.emnlp-industry)

Challenge:	Existing approaches produce uniform responses, ignoring that health literacy levels affect the accessibility and effectiveness of counterspeech.
Approach:	They propose a Controlled-Literacy framework that generates counterspeech adapted to different health literacy levels.
Outcome:	The proposed framework outperforms baselines by generating more accessible counterspeech to health misinformation.

Copied to clipboard

Anwesan Pal, Karen Hovsepian, Tinghao Guo, Mengnan Zhao, Somendra Tripathi, Nikos Kanakaris, George Mihaila, Sumit Nigam

Syntactic Text Processing

Challenge:	Recent studies into effective context lengths of flagship large language models (LLMs) have revealed major limitations in effective question answering (QA) and reasoning over long and complex contexts for even the largest and most impressive cadre of models.
Approach:	They propose a lightweight data augmentation strategy that boosts LLM performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents.
Outcome:	The proposed strategy boosts performance in long-context scenarios without degrading and altering the integrity and composition of retrieved documents.

MedEureka: A Medical Domain Benchmark for Multi-Granularity and Multi-Data-Type Embedding-Based Retrieval (2025.findings-naacl)

Copied to clipboard

Yongqi Fan, Nan Wang, Kui Xue, Jingping Liu, Tong Ruan

SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Embedding-based retrieval (EBR) is a mainstream approach in information retrieval.
Approach:	They propose an enriched benchmark to evaluate retrieval capabilities of embedding models . they use four levels of granularity and six types of medical texts to prompt instruction-fine-tuned embeddable models.
Outcome:	The proposed benchmark evaluates the retrieval capabilities of embedding models with multi-granularity and multi-data types.

Copied to clipboard

Yuzheng Cai, Zhenyue Guo, YiWen Pei, WanRui Bian, Weiguo Zheng

MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answering (2025.findings-emnlp)

Challenge:	Recent advances in large language models (LLMs) have shown impressive versatility across various tasks.
Approach:	They propose a retrieval-augmented generation method that integrates LLMs with external knowledge sources to produce grounded outputs.
Outcome:	The proposed method outperforms state-of-the-art KG-driven methods in question answering and fact verification.

Copied to clipboard

Siyue Zhang, Yuxiang Xue, Yiming Zhang, Xiaobao Wu, Anh Tuan Luu, Chen Zhao

Token-Level Precise Attack on RAG: Searching for the Best Alternatives to Mislead Generation (2026.findings-eacl)

Challenge:	Existing methods for answering time-sensitive questions lack temporal reasoning . existing methods struggle with these time-intensive questions, authors say .
Approach:	They propose a temporal-based question-answering framework that integrates temporal perturbations and gold evidence labels into a question processing framework.
Outcome:	The proposed framework outperforms baseline retrieval methods in retrieval performance.

Copied to clipboard

Zizhong Li, Haopeng Zhang, Jiawei Zhang

CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models (2025.findings-emnlp)

Challenge:	Existing approaches to attack large language models rely heavily on retrieval and generation stages, limiting their effectiveness in black-box scenarios.
Approach:	They propose a retrieval-augmented generation framework that leverages a white-box LLM as an attacker to generate and iteratively optimize malicious passages at the token level.
Outcome:	The proposed framework outperforms existing approaches in retrieval-stage and end-to-end attacks on black-box RAG systems.

Copied to clipboard

Feiyang Li, Peng Fang, Zhan Shi, Arijit Khan, Fang Wang, Weihao Wang, null Zhangxin-hw, Cui Yongjian

Language Modeling with Editable External Knowledge (2025.findings-naacl)

Challenge:	Chain-of-thought reasoning has two key limitations: lack of reliability when solely relying on LLM-generated reasoning chains and interference from natural language reasoning steps with the models’ inference logic.
Approach:	They propose a chain-of-thought reasoning framework with three key designs to address these issues.
Outcome:	The proposed framework improves the performance of large language models on complex tasks by incorporating knowledge graphs and learnable knowledge case-aware RAG.

Copied to clipboard

Belinda Z. Li, Emmy Liu, Alexis Ross, Abbas Zeitoun, Graham Neubig, Jacob Andreas

AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages (2026.eacl-long)

Challenge:	Continual learning methods tackle the problem of a changing world by incrementally training on new information.
Approach:	They propose a retrieval-augmented generation approach that incrementally deletes or rewrites other entries in the knowledge base each time a document is added.
Outcome:	The proposed model improves accuracy relative to conventional retrieval-augmented generation by 7-13% and 6-10% absolute.

Copied to clipboard

Kosei Uemura, Miaoran Zhang, David Ifeoluwa Adelani

CodeRAG-Bench: Can Retrieval Augment Code Generation? (2025.findings-naacl)

Challenge:	Text embeddings are an essential building component of several NLP tasks.
Approach:	They propose a regional expansion of MTEB covering 59 languages, 14 tasks, and 38 datasets, including six newly added datasets.
Outcome:	The proposed model outperforms baselines and mE5 in hate speech detection, intent detection, and emotion classification tasks.

Copied to clipboard

Zora Zhiruo Wang, Akari Asai, Xinyan Velocity Yu, Frank F. Xu, Yiqing Xie, Graham Neubig, Daniel Fried

Quality Assessment of Tabular Data using Large Language Models and Code Generation (2025.emnlp-industry)

Challenge:	Language models excel at generating code, but many programs are difficult to generate using only parametric knowledge.
Approach:	They propose a retrieval-augmented code generation benchmark that provides reproducible evaluations on retrieval and end-to-end code generation performance.
Outcome:	The proposed benchmark covers programming, open-domain, and repository-level tasks and provides reproducible evaluations on retrieval and end-to-end code generation performance.

Copied to clipboard

Ashlesha Akella, Akshar Kaul, Krishnasuri Narayanam, Sameep Mehta

RATSD: Retrieval Augmented Truthfulness Stance Detection from Social Media Posts Toward Factual Claims (2025.findings-naacl)

Challenge:	Data quality is vital for business decisions; poor data quality costs organizations an average of $12.9 million annually.
Approach:	They propose a framework that combines statistical inliner detection with LLM-driven rule and code generation.
Outcome:	The proposed framework produces semantically valid quality rules and validates them with retrieval-augmented generation (RAG) Extensive evaluations on benchmark datasets confirm the effectiveness of the proposed framework.

Copied to clipboard

Zhengyuan Zhu, Zeyu Zhang, Haiqi Zhang, Chengkai Li

Sentiment Analysis

Challenge:	Social media provides a valuable lens for assessing public perceptions and opinions.
Approach:	They propose a method that leverages large language models with retrieval-augmented generation to analyze tweets in relation to claims.
Outcome:	The proposed method outperforms state-of-the-art methods on a new dataset . it shows that it outperformed existing methods and achieves a significant increase in Macro-F1 score on TSD-CT.

GEAR: A Scalable and Interpretable Evaluation Framework for RAG-Based Car Assistant Systems (2025.emnlp-industry)

Copied to clipboard

Niloufar Beyranvand, Hamidreza Dastmalchi, Aijun An, Heidar Davoudi, Winston Chan, Ron DiCarlantonio

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) increasingly power car assistants, but evaluating response quality remains a challenge.
Approach:	They propose a framework that uses large language models as evaluators to compare assistant responses against ground-truth counterparts.
Outcome:	The proposed framework compares assistant responses against ground-truth counterparts, assessing coverage, correctness, and other dimensions of answer quality.

Tailoring Memory Granularity for Multi-Hop Reasoning over Long Contexts (2026.findings-eacl)

Copied to clipboard

Peijun Qing, Xingjian Diao, Chiyu Ma, Saeed Hassanpour, Soroush Vosoughi

Retrieval as Generation: A Unified Framework with Self-Triggered Information Planning (2026.acl-long)

Challenge:	Extensive experiments on long-context multi-hop question answering benchmarks show TAG achieves state-of-the-art performance.
Approach:	They propose a framework that prestructures memory into diverse granularities and employs a reward-guided navigator to adaptively compose hybrid memory tailored to each query.
Outcome:	Experiments on long-context multi-hop question answering show that the framework achieves state-of-the-art performance.

Copied to clipboard

Bo Li, Mingda Wang, Gexiang Fang, Shikun Zhang, Wei Ye

Learning to Ask: Multi-Decoder Fine-Tuning for Multi-Hop Visual Question Generation with External Knowledge (2026.findings-eacl)

Challenge:	Existing models that ground retrieval on external evidence are limited in their ability to implement retrieval-augmented generation.
Approach:	They propose a retrieval-augmented generation model that embeds retrieval control directly into generation.
Outcome:	The proposed model surpasses strong RAG baselines and uses substantially fewer parameters.

Copied to clipboard

Arpan Phukan, Manish Gupta, Asif Ekbal

Huatuo-26M, a Large-scale Chinese Medical QA Dataset (2025.findings-naacl)

Challenge:	Traditional supervised QG methods rely on tokenlevel alignment with fixed gold labels struggle to capture diverse valid question formulations.
Approach:	They propose a model-agnostic framework that integrates multimodal inputs with a multi-decoder architecture to optimize for multiple labels per sample.
Outcome:	The proposed framework improves fluency, reasoning depth, and relevance of visual questions.

Copied to clipboard

Xidong Wang, Jianquan Li, Shunian Chen, Yuxuan Zhu, Xiangbo Wu, Zhiyi Zhang, Xiaolong Xu, Junying Chen, Jie Fu, Xiang Wan, Anningzhe Gao, Benyou Wang

QAEncoder: Towards Aligned Representation Learning in Question Answering Systems (2025.acl-long)

Challenge:	Large Language Models are a powerful tool for medical research, but the data is a bottleneck.
Approach:	They propose to use the largest ever medical Question Answering dataset with 26 Million QA pairs as a fine-tuning data for training large language models.
Outcome:	The proposed dataset demonstrates that it can be used to train large language models and improves zero-shot performance on other datasets.

Copied to clipboard

Zhengren Wang, Qinhan Yu, Shida Wei, Zhiyu Li, Feiyu Xiong, Xiaoxing Wang, Simin Niu, Hao Liang, Wentao Zhang

DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking (2025.acl-long)

Challenge:	Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses, but the inherent gap between user queries and relevant documents hinders precise matching.
Approach:	They propose a retrieval-augmented generation (RAG)-based approach to bridge this gap by attaching document fingerprints to the embedding to estimate the expectation of potential queries.
Outcome:	Experiments across diverse datasets, languages, and embedding models confirm the proposed solution is simple-yet-effective with zero additional index storage, retrieval latency, training costs, or catastrophic forgetting and hallucination issues.

Copied to clipboard

Zhuoqun Li, Haiyang Yu, Xuanang Chen, Hongyu Lin, Yaojie Lu, Fei Huang, Xianpei Han, Yongbin Li, Le Sun

Challenge:	Existing studies in retrieval-augmented generation (RAG) do not sufficiently address the design of complex engineering solutions.
Approach:	They propose a retrieval-augmented generation system that leverages tree-based exploration and bi-point thinking mechanism to generate reliable solutions.
Outcome:	Experiments show that the proposed system achieves state-of-the-art (SOTA) performance on the SolutionBench, highlighting its potential to enhance the automation and reliability of complex engineering solution design in real-world applications.

SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)

Copied to clipboard

Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Zhaoxin Fan, Bo Tang, Jihao Zhao, Jiawei Yang, Shichao Song, Mengwei Wang

Intuitive or Dependent? Investigating LLMs’ Behavior Style to Conflicting Prompts (2024.acl-long)

Challenge:	Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs .
Approach:	They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service .
Outcome:	The proposed benchmark evaluates the security of RAG against 14 representative RAG components.

Copied to clipboard

Jiahao Ying, Yixin Cao, Kai Xiong, Long Cui, Yidong He, Yongbin Liu

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression (2025.acl-long)

Challenge:	Extensive experiments with seven Large Language Models reveal their varying behaviors.
Approach:	They investigate the behaviors of Large Language Models when faced with conflicting prompts versus their internal memory.
Outcome:	Extensive experiments with seven LLMs reveal their varying behaviors.

Copied to clipboard

Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Xinting Huang, Dong Yu, Zhicheng Dou

Challenge:	gist-based context compression methods can achieve only slight performance loss on tasks like retrieval-augmented generation and long-document QA, but it faces challenges in tasks like synthetic recall.
Approach:	They propose two strategies to improve gist-based context compression in large language models.
Outcome:	The proposed methods can achieve only slight performance loss on retrieval-augmented generation and long-document QA tasks, but they face challenges in tasks like synthetic recall.

Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation (2025.naacl-long)

Copied to clipboard

Satyapriya Krishna, Kalpesh Krishna, Anhad Mohananey, Steven Schwarcz, Adam Stambler, Shyam Upadhyay, Manaal Faruqui

Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimization (2025.emnlp-main)

Challenge:	Recent advances in Large Language Models (LLMs) have significantly enhanced their capabilities across various cognitive tasks.
Approach:	They propose a high-quality evaluation dataset to test LLMs' ability to provide factual responses, assess retrieval capabilities, and evaluate the reasoning required to generate final answers.
Outcome:	The proposed framework improves performance in end-to-end RAG scenarios.

Copied to clipboard

Yutao Zhu, Jiajie Jin, Hongjin Qian, Zheng Liu, Zhicheng Dou, Ji-Rong Wen

Investigating Context Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Style (2025.findings-acl)

Challenge:	Existing studies have optimized retrieval-augmented generation (RAG) across sub-tasks, but integrating these optimizations into a unified framework remains challenging.
Approach:	They propose a unified retrieval-augmented generation framework that optimizes role-specific tokens for multi-task processing.
Outcome:	The proposed framework achieves efficient multi-task processing through role-specific token optimization.

Copied to clipboard

Yuepei Li, Kang Zhou, Qiao Qiao, Bach Nguyen, Qing Wang, Qi Li

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Retrieval-augmented generation improves Large Language Models (LLMs) by integrating external information into the response generation process.
Approach:	They investigate the impact of memory strength and evidence presentation on LLMs’ receptiveness to external evidence by measuring the divergence in LLM responses to different paraphrases of the same question.
Outcome:	The proposed method improves Large Language Models (LLMs) by integrating external information into the response generation process.

Copied to clipboard

Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song, SeungYoon Han, Jong C. Park

LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization (2025.emnlp-main)

Challenge:	Current retrieval-augmented generation systems struggle when retrieval models fail to rank the most relevant documents . existing extractive methods reduce latency but rely on independent, non-adaptive sentence selection .
Approach:	They introduce an extractive context compression framework that enhances retrieval-augmented generation in question answering.
Outcome:	EXIT surpasses existing compression methods and uncompressed baselines in QA accuracy . the framework reduces inference time and token count while preserving contextual dependencies .

Copied to clipboard

Qi Zhang, Shouqing Yang, Lirong Gao, Hao Chen, Xiaomeng Hu, Jinglei Chen, Jiexiang Wang, Sheng Guo, Bo Zheng, Haobo Wang, Junbo Zhao

GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMs (2025.findings-emnlp)

Challenge:	Recent research focuses on integrating reasoning capabilities into the realm of retrieval-augmented generation (RAG) via outcome-supervised reinforcement learning (RL).
Approach:	They propose a process-level reward module to mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.
Outcome:	The proposed framework can boost LLMs’ reasoning ability by integrating external knowledge sources through retrieval-augmented generation (RAG) The proposed model can mitigate the unawareness of intermediate reasoning steps in outcome-level supervision without additional annotation.

Copied to clipboard

Xuebing Liu, Shanbao Qiao, Seung-Hoon Na

RoD-TAL: A Benchmark for Answering Questions in Romanian Driving License Exams (2026.findings-eacl)

Challenge:	GenPoE is a passage-level mixture of experts for enhancing knowledge of large language models.
Approach:	They propose a novel “generative” passage-level mixture of experts (MoEs) that takes in-context retrieved passages and generates their “expert” parameters.
Outcome:	The proposed system is based on a novel hypernetwork which takes in-context retrieved passages and generates their "expert'' parameters.

Copied to clipboard

Andrei Vlad Man, Răzvan-Alexandru Smădu, Cristian-George Craciun, Dumitru-Clementin Cercel, Florin Pop, Mihaela-Claudia Cercel

SciRAG: Adaptive, Citation-Aware, and Outline-Guided Retrieval and Synthesis for Scientific Literature (2026.eacl-long)

Challenge:	a growing need for tools that support legal education, especially in under-resourced languages such as Romanian . we evaluate the capabilities of large language models and vision-language models in legal education .
Approach:	They evaluate the capabilities of Large Language Models and Vision-Language Models in Romanian driving law through textual and visual question-answering tasks.
Outcome:	The proposed model improves retrieval performance and QA accuracy in Romanian driving tests.

Copied to clipboard

Hang Ding, Yilun Zhao, Tiansheng Hu, Zihang Wang, Manasi Patwardhan, Arman Cohan

Developing a Pragmatic Benchmark for Assessing Korean Legal Language Understanding in Large Language Models (2024.findings-emnlp)

Challenge:	Existing retrieval-augmented generation methods overlook citation graph structure, adapt poorly to complex queries, and yield fragmented, hard-to-verify syntheses.
Approach:	They propose a retrieval-augmented generation framework that addresses these gaps by combining adaptive retrieval and symbolic reasoning.
Outcome:	Extensive experiments show that SciRAG outperforms prior systems in factual accuracy and synthesis quality.

Copied to clipboard

Kimyeeun Kimyeeun, Choi Youngrok, Eunkyung Choi, JinHwan Choi, Hai Park, Wonseok Hwang

REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering (2024.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance in the legal domain, with GPT-4 even passing the Uniform Bar Exam in the U.S. However their efficacy remains limited for non-standardized tasks and tasks in languages other than English.
Approach:	They propose a benchmark for assessing the Korean legal language understanding of LLMs consisting of 7 legal knowledge tasks and 4 legal reasoning tasks.
Outcome:	The proposed model passes the Uniform Bar Exam in the U.S. but its performance is limited for non-standardized tasks and tasks in languages other than English.

Copied to clipboard

Yuhao Wang, Ruiyang Ren, Junyi Li, Xin Zhao, Jing Liu, Ji-Rong Wen

TriageAgent: Towards Better Multi-Agents Collaborations for Large Language Model-Based Clinical Triage (2024.findings-emnlp)

Challenge:	Existing methods to extend knowledge scope of large language models (LLMs) lack internal parametric knowledge, resulting in misusing external knowledge.
Approach:	They propose a retrieval-augmented approach that provides LLMs with potentially relevant documents through a module.
Outcome:	The proposed approach outperforms existing methods on four open-domain QA tasks.

Copied to clipboard

Meng Lu, Brandon Ho, Dennis Ren, Xuan Wang

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation (2024.emnlp-main)

Challenge:	escalation in emergency department patient visits poses challenges to efficient clinical management . Currently, hospitals rely on human experts to review clinical notes and determine case urgency .
Approach:	a team of researchers develop a multi-agent framework to enhance collaborative decision-making in clinical triage.
Outcome:	The proposed framework outperforms state-of-the-art LLM-based methods on three clinical triage test sets.

Copied to clipboard

Jirui Qi, Gabriele Sarti, Raquel Fernández, Arianna Bisazza

Synthetic Paths to Integral Truth: Mitigating Hallucinations Caused by Confirmation Bias with Synthetic Data (2025.coling-main)

Challenge:	Recent research has shown that self-citing large language models (LLMs) fail to faithfully reflect their context usage throughout the generation process.
Approach:	They propose a plug-and-play approach using model internals for faithful answer attribution in RAG applications that detects context-sensitive answer tokens and pairs them with retrieved documents contributing to their prediction.
Outcome:	The proposed approach achieves citation quality and efficiency comparable to self-citation while allowing for a finer-grained control of attribution parameters.

Copied to clipboard

Changwon Ok, Eunkyeong Lee, Dongsuk Oh

Personalized Text Generation with Contrastive Activation Steering (2025.acl-long)

Challenge:	Existing methods to mitigate confirmation bias-induced hallucination in large language models (LLMs) however, they still exhibit issues such as confirmation bias, which remains unexplored in current research.
Approach:	They propose a method to mitigate confirmation bias-induced hallucination in large language models by using a synthetic data construction pipeline and direct preference optimization (DPO) training.
Outcome:	The proposed method improves response accuracy and reduced hallucination on natural questions open and halubench.

Copied to clipboard

Jinghao Zhang, Yuting Liu, Wenjie Wang, Qiang Liu, Shu Wu, Liang Wang, Tat-Seng Chua

ILSIC: Corpora for Identifying Indian Legal Statutes from Queries by Laymen (2026.findings-eacl)

Challenge:	Existing approaches to personalized text generation rely on retrieval-augmented generation and parameter-efficient fine-tuning.
Approach:	They propose a training-free framework that disentangles and represents personalized writing style as a vector in LLM’s activation-space.
Outcome:	The proposed framework achieves 8% relative improvement in personalized generation while reducing storage requirements by 1700 over PEFT method.

Copied to clipboard

Shounak Paul, Raghav Dogra, Pawan Goyal, Saptarshi Ghosh

Challenge:	Existing studies have focused on the use of court judgments as input for legal Statute Identification (LSI) however, there is little research to explore the differences between court and laypeople data for LSI.
Approach:	They create a corpus of laypeople queries covering 500+ statutes from Indian law . they use court case judgements to compare between the two datasets .
Outcome:	The proposed corpus of laypeople queries covers 500+ statutes from Indian law . the results show that models trained on court judgements are ineffective .

Adapting General-Purpose Embedding Models to Private Datasets Using Keyword-based Retrieval (2025.findings-acl)

Copied to clipboard

Yubai Wei, Jiale Han, Yi Yang

Representation Learning

Challenge:	Text embedding models show strong performance on generic benchmarks, but their effectiveness diminishes when applied to private datasets.
Approach:	They propose a method for adapting general-purpose text embedding models to private datasets . they construct supervisory signals from the ranking of keyword-based retrieval results .
Outcome:	The proposed method improves retrieval performance across domains, datasets, and models.

FinGEAR: Financial Mapping-Guided Enhanced Answer Retrieval (2025.findings-emnlp)

Copied to clipboard

Ying Li, Mengyu Wang, Miguel de Carvalho, Sotirios Sabanis, Tiejun Ma

Large Language Models are Good Relational Learners (2025.acl-long)

Challenge:	FinGEAR provides a retrieval framework tailored to financial documents . standard retrieval-augmented generation models underuse financial disclosures .
Approach:	FinGEAR combines a finance lexicon for Item-level guidance and hierarchical indices for within-Item search.
Outcome:	FinGEAR improves accuracy and accuracy on 10-Ks with a FinQA dataset.

Copied to clipboard

Fang Wu, Vijay Prakash Dwivedi, Jure Leskovec

PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements (2025.emnlp-main)

Challenge:	Existing approaches to serialize large language models disregard critical relational structures and creates redundancies.
Approach:	They propose a graph neural network encoder to create structured relational prompts for large language models within a retrieval-augmented generation framework.
Outcome:	The proposed architecture preserves relational structure of databases while enabling LLMs to process and reason over complex entity relationships.

Copied to clipboard

Raptopoulos Petros, Giorgos Filandrianos, Maria Lymperaiou, Giorgos Stamou

Iterative Knowledge Graph Refinement and Integration for Medical Question Answering (2026.findings-acl)

Challenge:	Contract review is a complex and time-intensive task that typically requires legal expertise.
Approach:	a new open-source contract review framework is designed to handle complexities of contract analysis . PAKTON is a retrieval-augmented generation framework with plug-and-play capabilities .
Outcome:	The open-source framework outperforms models in predictive accuracy, retrieval performance, explainability, completeness, and grounded justifications.

Copied to clipboard

Haochen Zou, Yongli Wang

Structured Data in NLP

Challenge:	Existing graph-based RAG methods heuristically retrieve and refine question-relevant subgraphs, potentially introducing redundant and noisy factual information that is difficult for LLMs to process.
Approach:	They propose to integrate knowledge graphs (KGs) through retrieval-augmented generation methods to improve LLM reasoning by incorporating external trustworthy knowledge resources.
Outcome:	The proposed framework achieves state-of-the-art against baseline competitors on three medical QA benchmark datasets.

Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG (2026.findings-acl)

Copied to clipboard

Agam Goyal, Koyel Mukherjee, Apoorv Saxena, Anirudh Phukan, Eshwar Chandrasekharan, Hari Sundaram

Unanswerability Evaluation for Retrieval Augmented Generation (2025.acl-long)

Challenge:	Query enhancement techniques are now standard in retrieval-augmented generation systems, yet their impact on these biases remains unexplored.
Approach:	They evaluate query enhancement techniques that improve retrieval quality . they find that simple rewriting reduces bias through increased score variance . no technique uniformly addresses all biases, and effects vary substantially across retrievers .
Outcome:	The proposed method achieves strongest aggregate reduction, but fails under adversarial conditions where multiple biases combine.

Copied to clipboard

Xiangyu Peng, Prafulla Kumar Choubey, Caiming Xiong, Chien-Sheng Wu

Position Engineering: Boosting Large Language Models through Positional Information Manipulation (2024.emnlp-main)

Challenge:	Existing evaluation frameworks for retrieval-augmented generation (RAG) systems focus on answerable queries, but ignore the importance of appropriately rejecting unanswerable requests.
Approach:	They propose a framework to evaluate whether retrieval-augmented generation systems handle unanswerable queries specific to a given knowledge base.
Outcome:	The proposed framework synthesizes diverse and challenging queries for any given knowledge base and evaluates them with unanswered ratio and acceptable ratio metrics.

Copied to clipboard

Zhiyuan He, Huiqiang Jiang, Zilong Wang, Yuqing Yang, Luna Qiu, Lili Qiu

Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Recent advances in Large Language Models (LLMs) have demonstrated significant strides towards achieving artificial general intelligence.
Approach:	They propose a technique termed position engineering which alters the positional information in the prompt without modifying the text itself.
Outcome:	The proposed technique significantly improves on the baseline in retrieval-augmented generation and in-context learning scenarios.

Copied to clipboard

Sheng Liang, Hang Lv, Zhihao Wen, Yaxiong Wu, Yongyue Zhang, Hao Wang, Yong Liu

Information Extraction & Text Mining

Challenge:	Event extraction is a task in natural language processing that involves identifying and extracting event information from unstructured text.
Approach:	They propose a paradigm that combines schema paraphrasing with schema retrieval-augmented generation.
Outcome:	The proposed paradigm retrieves paraphrased schemas and accurately generates targeted structures.

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs (2025.findings-emnlp)

Copied to clipboard

Xiabin Zhou, Wenbin Wang, Minyan Zeng, Jiaxian Guo, Xuebo Liu, Li Shen, Min Zhang, Liang Ding

Challenge:	Existing KV cache compression methods enforce a fixed pattern, neglecting task-specific characteristics, which hampers the effective retention of essential information while discarding less important tokens.
Approach:	They propose a Task-Aware KV cache mechanism that dynamically adjusts the KV caching size across different layers based on the characteristics of the tasks.
Outcome:	The proposed method surpasses state-of-the-art methods by 11% on the LongBench dataset even under extreme compression (0.9%)

IRUEX: A Study on Large Language Models Problem-Solving Skills in Iran’s University Entrance Exam (2025.coling-main)

Copied to clipboard

Hamed Khademi Khaledi, Heshaam Faili

Candidate-Aware Retrieval and Reranking for Multiple-Choice Question Answering: Arabic as a Case Study (2026.findings-acl)

Challenge:	Recent advances in Large Language Models (LLMs) have profound implications for education.
Approach:	They present a novel multiple-choice educational resource specifically designed to evaluate the performance of Large Language Models (LLMs) they use a dataset that contains 868 questions and 36,485 additional questions .
Outcome:	The IRUEX dataset contains 868 questions and 36,485 additional questions.

Copied to clipboard

Yassine Bouziane, Youness Moukafih, Mounir Ghogho

Benchmarking and Learning Real-World Customer Service Dialogue (2026.acl-long)

Challenge:	Large language models (LLMs) have recently achieved impressive results on multiple-choice question answering (MCQA) despite advances in English, LLMs continue to underperform in Arabic due to gaps in data coverage, linguistic transfer, and evaluation design.
Approach:	They propose a method that jointly models the relevance of both the question and its candidate answers when selecting contextual passages.
Outcome:	The proposed approach outperforms standard RAG baselines and reranker baselines while remaining competitive with considerably larger models.

Copied to clipboard

Tianhong Gao, Jundong Shen, Jiapeng Wang, Bei Shi, Ying Ju, Junfeng Yao, Huiyu Yu

Dialogue Systems & Conversational Agents

Challenge:	Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) focus on task completion and tool correctness.
Approach:	They propose a benchmark-to-optimization loop that bridges offline gains to deployment . they propose OlaMind, which distills reusable reasoning patterns from expert dialogues .
Outcome:	The proposed benchmark surpasses GPT-5.2 and Gemini 3 Pro on OlaBench . it delivers an average +23.67% issue resolution and -6.6% human transfer rate versus baseline .

CLERC: A Dataset for U. S. Legal Case Retrieval and Retrieval-Augmented Analysis Generation (2025.findings-naacl)

Copied to clipboard

Abe Bohan Hou, Orion Weller, Guanghui Qin, Eugene Yang, Dawn Lawrie, Nils Holzenberger, Andrew Blair-Stanek, Benjamin Van Durme

NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLM (2025.findings-acl)

Challenge:	a dataset of case law is used to train and evaluate models for writing legal analyses . current approaches struggle to find relevant cases and generate legal analyses, authors say .
Approach:	They build a dataset of case law to support information retrieval and retrieval-augmented generation.
Outcome:	The proposed dataset supports two important backbone tasks: retrieval (IR) and retrieval-augmented generation (RAG).

Copied to clipboard

Zihan Wang, Yaohui Zhu, Gim Hee Lee, Yachun Fan

Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning (2024.emnlp-main)

Challenge:	High-performance vision-and-language navigation models require large amounts of training data, the high cost of manual annotating has seriously hindered this field.
Approach:	They propose a retrieval-augmented generation framework that generates user demand instructions for vision-and-language navigation.
Outcome:	The proposed model achieves SOTA performance on the REVERIE benchmark.

Copied to clipboard

Zhili Shen, Pavlos Vougiouklis, Chenxin Diao, Kaustubh Vyas, Yuanyi Ji, Jeff Pan

MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	Existing methods for text-to-SQL semantic parsing are limited to retrieving schemata based on a single query.
Approach:	They propose a text-to-sql semantic parser that uses abstract syntax trees to select few-shot examples for retrieval-augmented generation.
Outcome:	The proposed model can generate approximated versions of SQL queries in parallel, and shows improvements over state-of-the-art benchmarks.

Copied to clipboard

Jungyeon Lee, Lee Kangmin, Taeuk Kim

Structured Data in NLP

Challenge:	Existing benchmarks for investigating knowledge conflict have notable limitations, including a narrow focus on the question answering setup, heavy reliance on entity substitution techniques, and a restricted range of conflict types.
Approach:	They propose a knowledge graph-based framework that generates varied and subtle conflicts between two similar yet distinct contexts while ensuring interpretability through the explicit relational structure of KGs.
Outcome:	The proposed framework generates varied and subtle conflicts between two similar yet distinct contexts while ensuring interpretability through the explicit relational structure of KGs.

Does Your Voice Assistant Remember? Analyzing Conversational Context Recall and Utilization in Voice Interaction Models (2025.findings-acl)

Copied to clipboard

Heeseung Kim, Che Hyun Lee, Sangkwon Park, Jiheum Yeom, Nohil Park, Sangwon Yu, Sungroh Yoon

Speech & Audio in NLP

Challenge:	Recent advances in multi-turn voice interaction models have improved user-model communication, but whether open-source models share this ability remains unexplored.
Approach:	They propose to use ContextDialog to evaluate open-source interaction models' ability to recall past utterances to identify key limitations.
Outcome:	The proposed model retains and recalls past utterances better than closed-source models, but still struggles with questions about past . findings highlight key limitations in open-source model and suggest ways to improve memory retention and retrieval robustness.

Does Context Matter? ContextualJudgeBench for Evaluating LLM-based Judges in Contextual Settings (2025.acl-long)

Copied to clipboard

Austin Xu, Srijan Bansal, Yifei Ming, Semih Yavuz, Shafiq Joty

Challenge:	Contextual evaluation is challenging for state-of-the-art judge models . evaluation criteria are often conditional and dependent on practitioner priorities .
Approach:	They propose a judge benchmark that evaluates large language models as judges in contexts . they use human annotations and model-based perturbations to build the benchmark .
Outcome:	The proposed benchmark aims to evaluate large language models in contexts with 2,000 challenging response pairs.

MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation (2026.findings-acl)

Copied to clipboard

Xingchen Xiao, Heyan Huang, Runheng Liu, Jincheng Xie

AGRaME: Any-Granularity Ranking with Multi-Vector Embeddings (2024.emnlp-main)

Challenge:	Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) when retrieved contexts are noisy, incomplete, or heterogeneous, a single generation process often struggles to reconcile evidence effectively.
Approach:	They propose a multi-agent synthesis approach to retrieval-augmented generation that structures evidence processing into multiple role-specialized agents.
Outcome:	Experiments on four benchmarks show that MASS-RAG consistently improves performance over strong RAG baselines.

Copied to clipboard

Revanth Gangi Reddy, Omar Attia, Yunyao Li, Heng Ji, Saloni Potdar

Representation Learning

Challenge:	Existing ranking algorithms restrict granularity to full passages or require a specific dense index for each desired level of granules.
Approach:	They propose a multi-vector ranking approach that leverages multi-vctor embeddings to rank at varying levels of granularity while maintaining encoding at a single (coarser) level of grail.
Outcome:	The proposed method surpasses prompt-driven citation generation by incorporating proposition-level ranking to post-hoc citation addition.

MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents (2024.emnlp-main)

Copied to clipboard

Liyan Tang, Philippe Laban, Greg Durrett

Efficient Integration of External Knowledge to LLM-based World Models via Retrieval-Augmented Generation and Reinforcement Learning (2025.findings-emnlp)

Challenge:	Current methods for fact-checking are based on verifying each piece of a model against potential evidence using an LLM.
Approach:	They propose a method that builds small fact-checking models that have GPT-4-level performance but 400x lower cost.
Outcome:	The proposed model outperforms other models and reaches GPT-4 accuracy.

Copied to clipboard

Chang Yang, Xinrun Wang, Qinggang Zhang, Qi Jiang, Xiao Huang

RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion (2026.findings-acl)

Challenge:	Existing attempts to enhance LLM-based world models through prompting or fine-tuning approaches are either requiring human knowledge or computationally extensive.
Approach:	They propose a framework that leverages retrieval-augmented generation to integrate external knowledge to LLM-based world models.
Outcome:	The proposed framework outperforms baseline models and exhibits strong generalizability.

Copied to clipboard

Yu Huo, Kun Zeng, Siyu Zhang, Yuquan LU, Cheng Yang, Yifu Guo, Xiaoying Tang

Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach (2025.acl-long)

Challenge:	Large language models have strong reasoning, coding, and generation capabilities, but retrieval-augmented generation remains difficult under fixed context budgets.
Approach:	They propose a coalition-aware context filtering framework supervised by Shapley-style marginal contributions that captures sign effects via teacher-forced probing and computes exact Shaply values for small retrieval sets.
Outcome:	Experiments show that RepoShapley improves completion quality while reducing harmful context and unnecessary retrieval.

Copied to clipboard

Shenglai Zeng, Pengfei He, Kai Guo, Tianqi Zheng, Hanqing Lu, Yue Xing, Hui Liu

PRISM: Efficient Long-Range Reasoning With Short-Context LLMs (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) enhanced with external contexts face challenges in handling imperfect evidence.
Approach:	They propose a framework that can balance internal knowledge with external contexts . they propose gating mechanisms and low-rank representation adapters to adjust hidden representations based on a lightweight intervention function .
Outcome:	The proposed model can effectively balance internal knowledge with external context, similar to human cognitive processes.

Copied to clipboard

Dulhan Jayalath, James Bradley Wendt, Nicholas Monath, Sandeep Tata, Beliz Gunel

PERC: Plan-As-Query Example Retrieval for Underrepresented Code Generation (2025.coling-main)

Challenge:	Existing solutions to long-range language tasks require large compute budgets and complex task-specific design choices.
Approach:	They propose an in-context method that uses structured schemas to generate short-contemporary outputs.
Outcome:	a new in-context method outperforms baselines on diverse tasks with 4x shorter contexts . it scales down to tiny contexts without increasing costs or sacrificing quality .

Copied to clipboard

Jaeseok Yoo, Hojae Han, Youngwon Lee, Jaejin Kim, Seung-won Hwang

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World (2026.findings-acl)

Challenge:	Using large language models to generate code has shown significant promise, but selecting effective examples to improve generation quality remains a challenging task.
Approach:	They propose a framework that utilizes algorithmic plans to identify and retrieve effective examples.
Outcome:	The proposed framework outperforms the state-of-the-art RAG methods in code generation even when the source and target languages match or differ.

Copied to clipboard

Hanbing Liu, Lang Cao, Yang Li

From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations (2025.emnlp-main)

Challenge:	Existing methods to update or supplement large language models struggle under continuous knowledge drift.
Approach:	They propose a dynamic event benchmark and time-aware retrieval baseline that captures how knowledge evolves over time.
Outcome:	The proposed method enables systematic evaluation of model adaptation under continuous knowledge drift.

Copied to clipboard

Benlu Wang, Iris Xia, Yifan Zhang, Junda Wang, null Feiyun Ouyang, Shuo Han, Arman Cohan, Hong Yu, Zonghai Yao

HyKGE: A Hypothesis Knowledge Graph Enhanced RAG Framework for Accurate and Reliable Medical LLMs Responses (2025.acl-long)

Challenge:	Existing benchmarks assess only the final answer with a wide numerical tolerance, overlooking systematic reasoning failures and potentially causing serious clinical misjudgments.
Approach:	They propose a new step-by-step evaluation pipeline that assesses formula selection, entity extraction, and arithmetic computation.
Outcome:	The proposed method improves the accuracy of large language models on medical benchmarks from 16.35% to 53.19%.

Copied to clipboard

Xinke Jiang, Ruizhe Zhang, Yongxin Xu, Rihong Qiu, Yue Fang, Zhiyuan Wang, Jinyi Tang, Hongxin Ding, Xu Chu, Junfeng Zhao, Yasha Wang

Knowledge Representation

Challenge:	Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization.
Approach:	They propose a retrieval-augmented generation framework which leverages LLMs’ powerful reasoning capacity to compensate for the incompleteness of user queries.
Outcome:	The proposed framework improves the accuracy and reliability of Large Language Models (LLMs) by combining the rich knowledge of LLMs with Hypothesis Outputs.

GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understanding (2025.acl-long)

Copied to clipboard

Yukun Cao, Shuo Han, Zengyi Gao, Zezhong Ding, Xike Xie, S Kevin Zhou

HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple Devices (2025.acl-long)

Challenge:	Large language models struggle with comprehending graphical structure information through prompts of graph description sequences, especially as the graph size increases.
Approach:	They propose a framework to improve LLMs’ comprehension of both macro- and micro-level graphical information by placing critical graphical data in positions where LLM's exhibit stronger memory performance.
Outcome:	The proposed framework outperforms all other graph description methods in understanding graph structures of varying sizes.

Copied to clipboard

Silin Li, Yuhang Guo, Jiashu Yao, Zeming Liu, Haifeng Wang

Challenge:	Existing state-of-the-art LLMs cannot perform well in situations where instructions are invalid or multiple devices are involved.
Approach:	They propose to integrate large language models into smart home assistants by enhancing their ability to accurately understand user needs and respond appropriately.
Outcome:	The proposed dataset is the first with valid and invalid instructions across devices . it achieves only 0.0% success rate in the scenario of invalid multi-device instructions .

SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context (2025.findings-emnlp)

Copied to clipboard

Hairu Wang, Yuan Feng, Yukun Cao, Xike Xie, S Kevin Zhou

ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator (2024.emnlp-main)

Challenge:	Large language models incur high inference costs during deployment, causing hallucination . no dedicated routing methods exist for RAG, and existing training-based routers face challenges scaling to this domain .
Approach:	They propose a plug-and-play routing framework that optimizes performance and cost . the framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x .
Outcome:	The proposed framework delivers over 3x higher routing effectiveness while reducing runtime to less than 0.001x compared to existing methods.

Copied to clipboard

Junda Zhu, Lingyong Yan, Haibo Shi, Dawei Yin, Lei Sha

ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals (2026.findings-acl)

Challenge:	Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) due to noisy and fabricating content, it is inevitable that RAG systems are vulnerable to these noises and prone to respond incorrectly.
Approach:	They propose to optimize retrieval-augmented generation (RGG) with an Adversarial Tuning Multi-agent system (ATM) ATM steers the Generator to have a robust perspective of useful documents for question answering with the help of an auxiliary Attacker agent.
Outcome:	The proposed system improves the retrieval-augmented generator with an auxiliary Attacker agent and can discriminate useful documents amongst fabrications.

Copied to clipboard

Yihao Wang, Zijian He, Jie Ren, Keze Wang

Domain Adaptation for Conversational Query Production with the RAG Model Feedback (2023.findings-emnlp)

Challenge:	Historical research often focuses on finding exact record for a specific regnal month . classical Chinese sources are a canonical example of evidence-centric retrieval .
Approach:	They propose a time-keyed retrieval benchmark that organizes records by month-level reign keys . they propose 'CTD', a dual-encoder that combines absolute context with offset biasing .
Outcome:	The proposed benchmark organizes records by month-level reign keys and includes chrono-near confounders that mimic real retrieval failures.

Copied to clipboard

Ante Wang, Linfeng Song, Ge Xu, Jinsong Su

Dialogue Systems & Conversational Agents

Challenge:	Existing studies have focused on human-annotated search queries but they can not cover conversations of various domains.
Approach:	They propose a domain adaptation framework that uses retrieval-augmented generation to improve the model's robustness.
Outcome:	The proposed model is more robust and performs significantly better in a more challenging setting over strong baselines.

Evaluating Robustness of Generative Search Engine on Adversarial Factoid Questions (2024.findings-acl)

Copied to clipboard

Xuming Hu, Xiaochuan Li, Junzhe Chen, Yinghui Li, Yangning Li, Xiaoguang Li, Yasheng Wang, Qun Liu, Lijie Wen, Philip Yu, Zhijiang Guo

Mitigating Legal Hallucinations via Symbolic Constraints and Analogical Precedents (2026.acl-long)

Challenge:	Existing large language models (LLMs)-backed generative search engines may not always be accurate.
Approach:	They propose to evaluate the robustness of retrieval-augmented generation in a realistic and high-risk setting where adversaries have only black-box system access.
Outcome:	The proposed model exhibits higher susceptibility to factual errors compared to LLMs without retrieval.

Copied to clipboard

Zixuan Huang, Yanxiang Ma, Luhan Wang, Yunke Wang, Duo Shi, Chang Xu

Rationale-Guided Retrieval Augmented Generation for Medical Question Answering (2025.naacl-long)

Challenge:	Existing methods for finetuning and retrieval-augmented generation suffer from hallucination risk and semantic drift.
Approach:	They propose a framework for a dual-retriever based on the legal syllogism and the nature of different legal data.
Outcome:	The proposed framework mitigates hallucinations while improving explainability of legal reasoning.

Copied to clipboard

Jiwoong Sohn, Yein Park, Chanwoong Yoon, Sihyeon Park, Hyeon Hwang, Mujeen Sung, Hyunjae Kim, Jaewoo Kang

Improve Dense Passage Retrieval with Entailment Tuning (2024.emnlp-main)

Challenge:	Large language models (LLMs) struggle with hallucinations and outdated knowledge.
Approach:	They propose a retrieval-augmented generation framework for enhancing the reliability of RAG in biomedical contexts.
Outcome:	The proposed framework outperforms the previous best medical RAG model by up to 5.6% across three medical question-answering benchmarks.

Copied to clipboard

Lu Dai, Hao Liu, Hui Xiong

Semantic Geometry of Sentence Embeddings (2025.findings-emnlp)

Challenge:	Existing methods for dense retrieval have demonstrated remarkable performance in IR tasks.
Approach:	They propose a method to improve the embedding of dense retrievers by using existence claim as a bridge.
Outcome:	The proposed method can be plugged into current dense retrieval methods and the results are published in the journal Nature.

Copied to clipboard

Matthieu Tehenan

CLaw: Benchmarking Chinese Legal Knowledge in Large Language Models - A Fine-grained Corpus and Reasoning Analysis (2025.findings-emnlp)

Challenge:	Sentence embeddings are central to natural language processing, but their internal features are not interpretable and users lack fine-grained control for downstream tasks.
Approach:	They propose a formal framework to characterize the organization of features in sentence embeddings . they show how they can be composed to capture richer semantic structures .
Outcome:	The proposed method can be used to capture richer semantic structures.

Copied to clipboard

Xinzhe Xu, Liang Zhao, Hongshen Xu, null Chenchenc

Efficient OpAmp Adaptation for Zoom Attention to Golden Contexts (2025.acl-long)

Challenge:	a new benchmark is designed to evaluate LLMs on Chinese legal knowledge and its application in reasoning . general pre-training that ingests legal texts without specialized focus compromises reliability of LLM responses . achieving trustworthy legal reasoning in LLM requires a robust synergy of accurate knowledge retrieval and strong general reasoning capabilities.
Approach:	They propose a benchmark specifically engineered to evaluate LLMs on Chinese legal knowledge and its application in reasoning.
Outcome:	The proposed benchmark evaluates LLMs on Chinese legal knowledge and its application in reasoning.

Copied to clipboard

Haoyuan Wu, Rui Ming, Haisheng Zheng, Zhuolun He, Bei Yu

MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search (2025.findings-emnlp)

Challenge:	Large language models have shown significant promise in question-answering tasks . noisy reference documents hinder performance of LLMs, causing disproportionate attention to irrelevant content .
Approach:	They propose an adaptive large language model that allocates disproportionate attention to irrelevant documents . they use transformers to train the model and integrate it into pre-trained Transformer blocks .
Outcome:	The proposed model outperforms state-of-the-art models on noisy-context benchmarks.

Copied to clipboard

Yunhai Hu, Yilun Zhao, Chen Zhao, Arman Cohan

Idola Tribus of AI: Large Language Models tend to perceive order where none exists (2025.findings-emnlp)

Challenge:	MCTS-RAG combines structured reasoning with adaptive retrieval . compared to conventional MCTLs, MCTR-RAg relies on internal model knowledge without external facts .
Approach:	a new approach integrates retrieval-augmented generation and Monte Carlo Tree Search to enhance reasoning capabilities of small language models.
Outcome:	MCTS-RAG integrates retrieval-augmented generation and Monte Carlo Tree Search to improve reasoning paths.

Copied to clipboard

Shin-nosuke Ishikawa, Masato Todo, Taiki Ogihara, Hirotsugu Ohba

FaithLens: Detecting and Explaining Faithfulness Hallucination (2026.findings-acl)

Challenge:	a tendency of large language models to generate absurd patterns is observed . authors say this is a limitation of the models' ability to perform complex tasks .
Approach:	We present a tendency of large language models to generate absurd patterns . authors conducted an experiment to evaluate logical consistency and self-coherence of LLMs .
Outcome:	a recent study shows that large language models generate absurd patterns despite their inadequacy . the model over-recognized patterns that were inconsistent with the given numbers, the study finds .

Copied to clipboard

Shuzheng Si, Qingyi Wang, Haozhe Zhao, Yuzhuo Bai, Guanqiao Chen, Kangyang Luo, Gang Chen, Fanchao Qi, Minjia Zhang, Baobao Chang, Maosong Sun

BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning (2026.findings-acl)

Challenge:	Recent progress in large language models (LLMs) has revolutionized text generation.
Approach:	They propose a faithfulness hallucination detection model that can provide binary predictions and corresponding explanations to improve trustworthiness.
Outcome:	The proposed model outperforms advanced models on 12 diverse tasks.

Copied to clipboard

Jia-Chen Gu, Junyi Zhang, Di Wu, Yuankai Li, Kai-Wei Chang, Nanyun Peng

ChartM3: A Multi-Stage Code-Driven Pipeline for Constructing Multi-Dimensional and Multi-Step Visual Reasoning Data in Chart Comprehension (2025.findings-emnlp)

Challenge:	Experiments show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models.
Approach:	They propose a universal, lightweight compressor that distills relevant evidence from retrieved documents into a concise summary for seamless integration into in-context RAG.
Outcome:	Experiments on four open-domain multi-hop question-answering datasets show that BRIEF-Pro generates more concise and relevant summaries, enhancing performance across small, large, and proprietary language models.

Copied to clipboard

Duo Xu, Hao Cheng, Xin Lin, Zhen Xie, Hao Henry Wang

The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systems (2025.findings-acl)

Challenge:	Currently, research on complex chart understanding tasks is limited . a pipeline for visual reasoning datasets addresses these limitations .
Approach:	They propose a code-driven pipeline for generating visual reasoning datasets . pipeline integrates retrieval-augmented generation to retrieve professional chart templates .
Outcome:	The proposed pipeline enhances chart diversity and data quality through model-based evaluation.

Copied to clipboard

Hongru Song, Yu-An Liu, Ruqing Zhang, Jiafeng Guo, Jianming Lv, Maarten de Rijke, Xueqi Cheng

LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understanding (2026.acl-long)

Challenge:	Existing studies have focused on corpus poisoning, but there are no studies on adversarial attacks on RAG systems.
Approach:	They propose a novel imperceptible retrieve-to-generate attack against RAG systems . they propose regenerative reinforcement learning framework that tracks interactions between attacker and target RAG .
Outcome:	The proposed framework outperforms existing attacks on factual and non-factual RAG systems with small imperceptible text perturbations.

Copied to clipboard

Zhivar Sourati, Zheng Wang, Marianne Menglin Liu, Yazhe Hu, Mengqing Guo, Sujeeth Bharadwaj, Kyu J. Han, Tao Sheng, Sujith Ravi, Morteza Dehghani, Dan Roth

KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases (2025.findings-emnlp)

Challenge:	Conventional retrieval-augmented generation (RAG) methods encode content in isolated chunks during ingestion, losing structural and cross-page dependencies, and retrieve a fixed number of pages at inference.
Approach:	They propose a Layout-Aware Dynamic RAG framework that encodes content in isolated chunks during ingestion and retrieves a fixed number of pages at inference.
Outcome:	Experiments on MMLongBench-Doc, LongDocURL, DUDE, and MP-DoxVQA show that LAD-RAG improves retrieval, achieving over 90% perfect recall on average without any top-k tuning, and outperforming baseline retrievers by up to 20% in recall at comparable noise levels.

Copied to clipboard

Zheni Zeng, Yuxuan Chen, Shi Yu, Ruobing Wang, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun

DynamicER: Resolving Emerging Mentions to Dynamic Entities for RAG (2024.emnlp-main)

Challenge:	Existing methods for retrieval-augmented generation (RAG) are limited and fine-tuning incurs prohibitive costs of external signals.
Approach:	They propose a self-supervised framework that enhances RAG systems through efficient model adaptation.
Outcome:	The proposed framework achieves 90% of the performance gain obtained through GPT-4-supervised adaptation while relying entirely on self-annotation of much smaller models.

Copied to clipboard

Jinyoung Kim, Dayoon Ko, Gunhee Kim

Knowledge Representation

Challenge:	Existing entity linking models struggle to link new expressions to entities in the dynamic nature of human language.
Approach:	They propose a task to resolve emerging mentions to dynamic entities and a benchmark to evaluate their model's adaptability to new expressions.
Outcome:	The proposed method outperforms baselines on QA task with resolved mentions and improves retrieval-augmented generation performance.

PAT-Questions: A Self-Updating Benchmark for Present-Anchored Temporal Question-Answering (2024.findings-acl)

Copied to clipboard

Jannat Meem, Muhammad Rashid, Yue Dong, Vagelis Hristidis

Token-level Preference Self-Alignment Optimization for Multi-style Outline Controllable Generation (2025.findings-acl)

Challenge:	Existing work on Temporal Question Answering (TQA) has focused on questions anchored to specific timestamps or events.
Approach:	They introduce a benchmark to address present-anchored temporal QA (PATQA) which includes single and multi-hop temporal questions.
Outcome:	The proposed model can be automatically refreshed by re-running SPARQL queries on a knowledge graph.

Copied to clipboard

Zihao Li, Xuekong Xu, Ziyao Chen, Lixin Zou, Ethanhjwu Ethanhjwu, Qiang Chen, Chenliang Li

Challenge:	Existing attempts to outline generation are limited by response pair requirements and substantial computation costs.
Approach:	They propose a token-level preference self-alignment optimization for outline controllable generation that extends the Bradley-Terry model from pair-wise to list-wise comparison.
Outcome:	The proposed method outperforms existing methods by 19.28% in performance while requiring only 56.25% training time.

KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrieval (2025.emnlp-main)

Copied to clipboard

Chi Minh Bui, Ngoc Mai Thieu, Vinh Van Nguyen, Jason J. Jung, Khac-Hoai Nam Bui

DYNAMICQA: Tracing Internal Knowledge Conflicts in Language Models (2024.findings-emnlp)

Challenge:	Existing methods that address corpus-level context loss focus on query enrichment through structured relation representations.
Approach:	They propose a framework for Contextual Query Retrieval that enriches queries with contextual representations derived from a corpus-centric KG.
Outcome:	The proposed framework outperforms strong baselines on RAGBench and MultiHop-RAG datasets in terms of retrieval effectiveness.

Copied to clipboard

Sara Marjanovic, Haeun Yu, Pepa Atanasova, Maria Maistro, Christina Lioma, Isabelle Augenstein

Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition (2025.findings-emnlp)

Challenge:	LMs are useful in a variety of downstream applications from summarization to fact-checking, often relying on factual knowledge memorized during pre-training.
Approach:	They use two knowledge conflict measures and a novel dataset DYNAMICQA to examine the effect of intra-memory conflict on LMs' ability to accept contextual knowledge.
Outcome:	The proposed model can accept contextual knowledge with a higher degree of accuracy than models with fewer truth values.

Copied to clipboard

Yi Liu, Xiangrong Zhu, Xiangyu Liu, Wei Wei, Wei Hu

Found in the middle: Calibrating Positional Attention Bias Improves Long Context Utilization (2024.findings-acl)

Challenge:	Existing methods for knowledge editing fail to work in multi-hop question answering due to 'edit skipping' edit skipping occurs due to the mismatch between the granularity of LLMs in problem-solving and the facts in the edited memory.
Approach:	They propose a retrieval-augmented generation-based method that edits knowledge without modifying parameters without retraining LLMs.
Outcome:	The proposed method outperforms state-of-the-art methods for KE in multi-hop question answering.

Copied to clipboard

Cheng-Yu Hsieh, Yung-Sung Chuang, Chun-Liang Li, Zifeng Wang, Long Le, Abhishek Kumar, James Glass, Alexander Ratner, Chen-Yu Lee, Ranjay Krishna, Tomas Pfister

Challenge:	Large language models struggle to capture relevant information located in the middle of their input.
Approach:	They propose a calibration mechanism that allows the model to attend to contexts faithfully according to their relevance even when they are in the middle.
Outcome:	The proposed calibration mechanism mitigates this positional bias and improves retrieval-augmented generation performance.

DAVIS: Planning Agent with Knowledge Graph-Powered Inner Monologue (2025.findings-emnlp)

Copied to clipboard

Minh Pham Dinh, Michael G Yankoski, Munira Syed, Trenton W. Ford

Knowledge Representation

Challenge:	Existing approaches to designing a generalist scientific agent fail to address multifaceted requirements of scientific tasks.
Approach:	DAVIS is a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers.
Outcome:	DAVIS performs better on ScienceWorld benchmarks compared to previous approaches on 8 out of 9 elementary science subjects.

FoodSafeSum: Enabling Natural Language Processing Applications for Food Safety Document Summarization and Analysis (2025.findings-emnlp)

Copied to clipboard

Juli Bakagianni, Korbinian Randl, Guido Rocchietti, Cosimo Rulli, Franco Maria Nardini, Salvatore Trani, Aron Henriksson, Anna Romanova, John Pavlopoulos

Information Extraction & Text Mining

Challenge:	a lack of structured datasets hinders natural language processing research . a new dataset of food safety documents and related metadata is presented .
Approach:	They present a dataset of human-written and Large Language Model (LLM)-generated food safety documents . they evaluate their utility on three NLP tasks directly reflecting food safety practices .
Outcome:	The proposed dataset performs comparably or better than human summaries on three NLP tasks . it also shows clustering of summary for event tracking and compliance monitoring .

Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citation (2025.findings-acl)

Copied to clipboard

Jiajun Shen, Tong Zhou, Yubo Chen, Delai Qiu, Shengping Liu, Kang Liu, Jun Zhao

Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation (2025.emnlp-main)

Challenge:	citation generation and retrieval-augmented generation are still lacking in large language models due to hallucinations.
Approach:	They propose a retrieval-augmented citation generation task that requires models to generate citations considering both external and internal knowledge while providing trustworthy references.
Outcome:	The proposed method achieves better performance across scenarios compared to baselines . retrieval quality, question types, and model knowledge influence trustworthiness .

Copied to clipboard

Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Baobao Chang

Zero-shot Graph Reasoning via Retrieval Augmented Framework with LLMs (2025.findings-emnlp)

Challenge:	Recent advances in retrieval-augmented generation (RAG) have substantially improved question-answering systems, particularly for factoid ‘5Ws’ questions.
Approach:	They propose a data organization paradigm where large language models transform documents into more structured and loosely interconnected LUs.
Outcome:	Experiments in open-domain and industrial settings show that the proposed paradigm outperforms existing paradigms and shows high adaptability across diverse document formats.

Copied to clipboard

Hanqing Li, Sharika Mahadevan, Kiran Jyothi Sheena, Henry Liang, Diego Klabjan

Misinformation with Legal Consequences (MisLC): A New Task Towards Harnessing Societal Harm of Misinformation (2024.findings-emnlp)

Challenge:	Existing methods that require extensive finetuning or depend on predefined algorithms are limited by training.
Approach:	a new retrieval-augmented framework is proposed that harnesses retrieval and large language models to address graph reasoning tasks.
Outcome:	The proposed method achieves 100% accuracy on most graph reasoning tasks while maintaining consistent token costs regardless of graph sizes.

Copied to clipboard

Chu Fei Luo, Radin Shayanfar, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu

Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention (2025.emnlp-main)

Challenge:	Existing research has focused on the veracity of information, overlooking the legal implications and consequences of misinformation.
Approach:	They propose a task to detect misinformation using legal issues as a measure of societal ramifications.
Outcome:	The proposed task leverages definitions from a wide range of legal domains covering 4 broader legal topics and 11 fine-grained legal issues, including hate speech, election laws, and privacy regulations.

Copied to clipboard

Nikhil Bhendawade, Irina Belousova, Qichen Fu, Henry Mason, Antonie Lin, Mohammad Rastegari, Mahyar Najibi

Green & Sustainable NLP

Challenge:	Speculative decoding is a prominent technique for accelerating LLM inference by leveraging an auxiliary draft model, but its effectiveness is limited by the autoregressive nature of draft generation.
Approach:	They propose a method that integrates speculative draft generation directly within the target model using multi-stream attention.
Outcome:	The proposed method improves acceptance but also latency and speculation latency, limiting overall speedup.

FaVe: Factored and Verified Search Rationale for Long-form Answer (2025.findings-acl)

Copied to clipboard

Jihyuk Kim, Sungjin Lee, Seung-won Hwang, Yang Liu

UniRAG: A Unified RAG Framework for Knowledge-Intensive Queries with Decomposition, Break-Down Reasoning, and Iterative Rewriting (2025.findings-emnlp)

Challenge:	Existing solutions for long-form question-answering (LFQA) use chain-of-thought (CoT) with retrieval-augmented generation (RAG).
Approach:	They propose to integrate chain-of-thought (CoQ) with retrieval-augmented generation to improve answer comprehensiveness and verifiability.
Outcome:	The proposed approach outperforms ChatGPT baselines while maintaining efficiency.

Copied to clipboard

Gun Il Kim, Jong Wook Kim, Beakcheol Jang

ML-Promise: A Multilingual Dataset for Corporate Promise Verification (2025.emnlp-main)

Challenge:	Existing retrieval-augmented generation approaches struggle with query complexity, propagated reasoning errors, or rely on incomplete or noisy retrieval.
Approach:	a unified retrieval-augmented generation framework is developed to address query complexity . the framework decomposes queries into semantically coherent sub-queries . it explicitly verifies retrieved sub-facts and adaptively refines queries based on identified knowledge gaps.
Outcome:	a new framework improves answer completeness and reliability by decomposing queries into coherent sub-queries . the framework explicitly verifies retrieved sub-facts and adaptively refines queries based on identified knowledge gaps.

Copied to clipboard

Yohei Seki, Hakusen Shu, Anaïs Lhuissier, Hanwool Lee, Juyeon Kang, Min-Yuh Day, Chung-Chi Chen

Multilinguality

Challenge:	Promises shape perceptions and drive decisions, but verification of their fulfillment is difficult due to complexity and volume of commitments . authors propose a new approach to verifying promises in environmental, social, and governance reports . complexity of promises, complexity of evidence, difficulty in verifying their fulfillment a pressing need for new approaches .
Approach:	They propose a multilingual dataset that includes English, French, Chinese, Japanese, and Korean . they propose ML-Promise to facilitate in-depth verification of corporate promises .
Outcome:	The proposed approach includes promise identification, evidence assessment, and evaluation of timing for verification in multiple languages.

LimRank: Less is More for Reasoning-Intensive Information Reranking (2025.emnlp-main)

Copied to clipboard

Tingyu Song, Yilun Zhao, Siyue Zhang, Chen Zhao, Arman Cohan

A Sequential Multi-Stage Approach for Code Vulnerability Detection via Confidence- and Collaboration-based Decision Making (2025.emnlp-main)

Challenge:	Existing approaches to rerank information require large-scale fine-tuning, which is computationally expensive.
Approach:	They propose an open-source pipeline for generating diverse, challenging, and realistic reranking examples.
Outcome:	The proposed model performs competitively on two benchmarks, while being trained on less than 5% of the data typically used in prior work.

Copied to clipboard

Chung-Nan Tsai, Xin Wang, Cheng-Hsiung Lee, Ching-Sheng Lin

Challenge:	Large language models (LLMs) have shown strong capabilities across diverse domains, but their application to code vulnerability detection raises significant concerns regarding efficiency, scalability and cost.
Approach:	They propose a sequential multi-stage approach via confidence- and collaboration-based decision making via a three-stage sequential classification framework with a single agent, retrieval-augmented generation with external examples, and multi-agent reasoning enhanced with RAG.
Outcome:	The proposed approach improves code vulnerability detection performance on a benchmark dataset and a low-resource language.

Experience Retrieval-Augmentation with Electronic Health Records Enables Accurate Discharge QA (2026.acl-long)

Copied to clipboard

Justice Ou, Tinglin Huang, Yilun Zhao, Ziyang Yu, Peiqing Lu, Yifei Shen, Rex Ying

Evaluation of Attribution Bias in Generator-Aware Retrieval-Augmented Large Language Models (2025.findings-acl)

Challenge:	Existing methods to improve the reliability of Large Language Models (LLMs) in clinical applications require factual knowledge from open-ended datasets and clinical case-based knowledge to provide context grounded in real-world patient experiences.
Approach:	They propose a retrieval-augmented generation framework based on the electronic health record to offer contextual information from other patients’ discharge reports.
Outcome:	The proposed framework outperforms a text-based ranker in a clinical QA dataset with 1,280 discharge-related questions .

Copied to clipboard

Amin Abolghasemi, Leif Azzopardi, Seyyed Hadi Hashemi, Maarten de Rijke, Suzan Verberne

PROGRAM: Programmatic Retrieval Optimization with Generative Reasoning and Augmented Multi-queries (2026.findings-acl)

Challenge:	Prior work has focused on improving and evaluating the attribution quality of large language models (LLMs) but this may come at the expense of inducing biases in the attributed answers.
Approach:	They propose to evaluate attribution sensitivity and bias with respect to authorship information in large language models (LLMs) in retrieval-augmented generation pipelines.
Outcome:	The proposed framework can significantly improve the attribution quality of large language models (LLMs) in retrieval-augmented generation pipelines by adding authorship information to source documents.

Copied to clipboard

Gun Il Kim, Jungkyu Shin, Jong Wook Kim, Beakcheol Jang

Query-Driven Multimodal GraphRAG: Dynamic Local Knowledge Graph Construction for Online Reasoning (2025.findings-acl)

Challenge:	Current retrieval-augmented generation methods struggle with complex multi-hop reasoning, relying on unstructured semantic matching that lacks the logical structure needed to systematically guide retrieval.
Approach:	They propose a framework that elevates retrieval to structured, program-guided reasoning by combining three stages of program-type selection and evidence accumulation.
Outcome:	Evaluated on five benchmarks including HotPotQA, 2WikiMultihopQA, ARC-Challenge, MMLU-Pro, and MedQA with various LLMs, PROGRAM achieves state-of-the-art performance with up to 24% relative improvement on HotPtQA and 13.2% on MedQA over strong baselines including FLARE, ProbTree and Self-RAG.

Copied to clipboard

Chenyang Bu, Guojie Chang, Zihao Chen, CunYuan Dang, Zhize Wu, Yi He, Xindong Wu

A Comprehensive Graph Framework for Question Answering with Mode-Seeking Preference Alignment (2025.findings-acl)

Challenge:	Existing approaches to build knowledge graphs with LLMs are constrained by static knowledge bases and ineffective multimodal data integration.
Approach:	They propose a Query-Driven Multimodal GraphRAG framework that dynamically constructs local knowledge graphs tailored to query semantics.
Outcome:	The proposed framework outperforms unsupervised competitors in cross-modal understanding of complex queries.

Copied to clipboard

Quanwei Tang, Sophia Yat Mei Lee, Junshuang Wu, Dong Zhang, Shoushan Li, Erik Cambria, Guodong Zhou

Structured Data in NLP

Challenge:	Existing studies struggle with achieving global understanding of large language models . GraphMPA is a graph-based framework with mode-seeking preference alignment .
Approach:	They propose a graph-based framework with mode-seeking preference alignment to improve model outputs.
Outcome:	The proposed framework constructs a hierarchical document graph mimicking human cognitive processes for information understanding and synthesis.

MS-RAG: Simple and Effective Multi-Semantic Retrieval-Augmented Generation (2025.emnlp-main)

Copied to clipboard

Xiaozhou You, Yahui Luo, Lihong Gu

LORE: Continual Logit Rewriting Fosters Faithful Generation (2025.findings-emnlp)

Challenge:	Existing methods for large language models suffer from poor indexing and inference speed . graph-based RAGs heavily rely on LLM for retrieval thus inference slow .
Approach:	They propose retrieval-augmented generation (RAG) which integrates knowledge with dense vectors to build a multi-semantic RAG.
Outcome:	The proposed method achieves state-of-the-art performance with faster inference speed compared to existing methods .

Copied to clipboard

Charles Yu, Qingyun Wang, Yuting Hu, Jinjun Xiong, Heng Ji

PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality (2026.findings-acl)

Challenge:	Using aspect-oriented summarization as a case study, we propose LOgit REwriting, a new controlled generation paradigm which can be faithful to external knowledge and to the LLM’s intentions.
Approach:	They propose a controlled generation paradigm which can be faithful to external knowledge and to the LLM's intentions.
Outcome:	The proposed paradigm can be faithful to external knowledge and to the LLM's intentions while balancing that with accuracy.

Copied to clipboard

Zeyuan Chen, Ziqing Yang, Yihan Ma, Michael Backes, Yang Zhang

Challenge:	Increasing use of large language models (LLMs) in academic review has raised concerns about quality and fairness.
Approach:	They propose a framework to improve the quality of LLM-generated reviews by using retrieval-augmented generation.
Outcome:	The proposed framework improves the human-level quality of LLM-generated reviews by adopting prompt engineering and retrieval-augmented generation.

Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics (2025.findings-acl)

Copied to clipboard

Ameya Godbole, Robin Jia

Can Language Models Replace Programmers for Coding? REPOCOD Says ‘Not Yet’ (2025.acl-long)

Challenge:	Recent advances in large language models have led to optimism that they can serve as reliable evaluators of natural language outputs.
Approach:	They propose to use factuality metrics to evaluate natural language outputs . they find they misestimate the factual accuracy of NLG systems .
Outcome:	The proposed metrics are inconsistent with each other and often misestimate the factual accuracy of NLG systems, causing biases against paraphrased outputs and outputs that draw upon faraway parts of the source documents.

Copied to clipboard

Shanchao Liang, Nan Jiang, Yiran Hu, Lin Tan

Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory (2026.acl-long)

Challenge:	Existing benchmarks for code generation use short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks.
Approach:	They propose a Python code-generation benchmark that contains 980 whole-function generation tasks with realistic dependencies from 11 popular projects.
Outcome:	The proposed benchmarks are short completions, synthetic examples, or focus on limited scale repositories, failing to represent real-world coding tasks.

Copied to clipboard

Sen Hu, Yuxiang Wei, Jiaxin Ran, Xueran Han, Zhiyuan Yao, Huacan Wang, Ronghao Chen, Lei Zou

COVER: Context-Driven Over-Refusal Verification in LLMs (2025.findings-acl)

Challenge:	Existing literature on dialog memory systems is inconsistent on their effectiveness . empirical findings on graph structures are difficult to attribute to specific design choices .
Approach:	They propose a framework that decomposes dialog memory systems into core components . they conduct stage-wise experiments on LongMemEval and HaluMeM, and compare implementation details .
Outcome:	The proposed framework compares graph-based and non-graph memory architectures on long-term dialog memory systems.

Copied to clipboard

Giovanni Sullutrone, Riccardo A. Vigliermo, Sonia Bergamaschi, Luca Sala

Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have become increasingly prevalent in the field of Natural Language Processing (NLP), achieving unprecedented performance across linguistic tasks.
Approach:	They propose a framework to quantify and analyze context-driven over-refusal . they find that over-fusals depend on the task, system prompts, model family, and the number of retrieved documents.
Outcome:	The proposed framework quantifyes and analyzes the concept of context-driven over-refusal on two public corpora.

Copied to clipboard

Songbo Hu, Yinhong Liu, Ej Zhou, Evgeniia Razumovskaia, Xiaobin Wang, Alexander Fraser, Ivan Vulić, Anna Korhonen

The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems (2025.findings-emnlp)

Challenge:	Creating spoken dialogue datasets is methodologically challenging due to the personally identifiable nature of speech signals.
Approach:	They propose a large-scale, multilingual, and multi-parallel dataset for developing and evaluating retrieval-augmented generation-based spoken dialogue systems.
Outcome:	The proposed dataset includes 6,000 information-seeking dialogues and 163 hours of user speech recorded from native speakers of four official WHO languages.

Copied to clipboard

Chanwoo Choi, Jinsoo Kim, Sukmin Cho, Soyeong Jeong, Buru Chang

SciCompanion: Graph-Grounded Reasoning for Structured Evaluation of Scientific Arguments (2025.findings-emnlp)

Challenge:	Existing approaches to degrade retrieval-augmented generation systems rely on unrealistic assumptions in which external attackers have access to internal components such as the retriever.
Approach:	They propose a black-box attack based on the RAG paradox, a structural vulnerability that emerges from the system’s effort to enhance trust by revealing both the retrieved documents and their sources to users.
Outcome:	The proposed method significantly degrades system performance without internal access while generating natural-looking poisoned documents.

Copied to clipboard

Joshua Alan Flashner, Adithya Kulkarni, Dawei Zhou

It’s High Time: A Survey of Temporal Question Answering (2026.acl-long)

Challenge:	Existing retrieval-augmented generation (RAG) methods fail to provide deep, relational understanding of scientific literature.
Approach:	They propose a graph-grounded reasoning framework for structured scientific evaluation that uses multi-hop reasoning to iteratively construct contextual graphs and generate structured critiques.
Outcome:	The proposed framework reduces evaluation error by over 30% compared to baselines and allows smaller models to outperform larger models.

Copied to clipboard

Bhawna Piryani, Abdelrahman Abdallah, Jamshid Mozafari, Avishek Anand, Adam Jatowt

DeepSpecs: Expert-Level Question Answering in 5G (2026.findings-acl)

Challenge:	Temporal Question Answering (TQA) is a research area that focuses on answering questions involving temporal constraints or context.
Approach:	They present a comprehensive overview of Temporal Question Answering (TQA) this research area focuses on answering questions involving temporal constraints or context .
Outcome:	The proposed frameworks are compared against a range of datasets, tasks, and approaches.

Copied to clipboard

Aman Ganapathy Manvattira, Yifei Xu, Ziyue Dang, Songwu Lu

LLMs are Biased Evaluators But Not Biased for Fact-Centric Retrieval Augmented Generation (2025.findings-acl)

Challenge:	3GPP standards define the technical design and implementation of 5G systems . expert-level questions require navigating thousands of pages of cross-referenced standards .
Approach:	They propose a standard-native retrieval-augmented generation system that can answer 5G questions . they use SpecDB, ChangeDB, TDocDB and a metadata-rich retrieval system to do this .
Outcome:	The proposed solution outperforms base models and state-of-the-art RAG systems in QA datasets . expert-level queries require navigating thousands of pages of cross-referenced standards .

Copied to clipboard

Yen-Shan Chen, Jing Jin, Peng-Ting Kuo, Chao-Wei Huang, Yun-Nung Chen

SGIC: A Self-Guided Iterative Calibration Framework for RAG (2025.acl-long)

Challenge:	Recent studies have shown that large language models (LLMs) exhibit significant biases in evaluation tasks, especially in preferentially rating and favoring self-generated content.
Approach:	They propose to simulate two critical phases of retrieval-augmented generation (RAG) frameworks where keyword extraction and factual accuracy take precedence over stylistic elements.
Outcome:	The proposed model emulates two critical phases of the retrieval-augmented generation framework.

Copied to clipboard

Guanhua Chen, Yutong Yao, Lidia S. Chao, Xuebo Liu, Derek F. Wong

Pretraining Context Compressor for Large Language Models with Embedding-Based Memory (2025.acl-long)

Challenge:	Existing studies on retrieval-augmented generation (RAG) focus on extracting relevant documents or refinement of specialized instructions.
Approach:	They propose a framework that provides LLMs with specific cues to improve their calibration efficacy . they propose an iterative self-calibration training set that harnesses uncertainty scores .
Outcome:	The proposed framework significantly improves performance on both closed-source and open-source LLMs.

Copied to clipboard

Yuhong Dai, Jianxun Lian, Yitian Huang, Wei Zhang, Mingyang Zhou, Mingqi Wu, Xing Xie, Hao Liao

CPR-RAG: Clinical Prior-Regularized Retrieval for Anatomy-Aware 3D CT Report Generation (2026.acl-long)

Challenge:	Efficient processing of long contexts in large language models is essential for real-world applications such as retrieval-augmented generation and in-context learning.
Approach:	They propose a decoupled compressor-LLM framework that preserves contextual information within condensed embedding representations.
Outcome:	The proposed framework outperforms baseline models in three domains and across eight datasets while adapting to different downstream LLMs.

Copied to clipboard

Sungkyu Yang, Kang-Min Kim, Mansu Kim

CARO: Chain-of-Analogy Reasoning Optimization for Robust Content Moderation (2026.findings-acl)

Challenge:	Existing approaches to grounding radiology reports from 3D volumetric data are limited due to visual-semantic ambiguity and lack of "normal" context.
Approach:	They propose a model-agnostic retrieval-augmented generation framework that integrates clinical priors into the retrieval process.
Outcome:	The proposed model improves clinical efficacy across state-of-the-art models.

Copied to clipboard

Bingzhe Wu, Haotian Lu, Yuchen Mou

VISA: Retrieval Augmented Generation with Visual Source Attribution (2025.acl-long)

Challenge:	Current large language models struggle with ambiguous content moderation cases due to misleading "decision shortcuts" . authors propose a two-stage training framework to induce robust analogical reasoning in LLMs .
Approach:	They propose a two-stage training framework to induce robust analogical reasoning in LLMs . they bootstrap analogy reasoning chains via retrieval-augmented generation and SFT .
Outcome:	The proposed framework outperforms state-of-the-art reasoning models and specialized moderation models on ambiguous moderation benchmarks.

Copied to clipboard

Xueguang Ma, Shengyao Zhuang, Bevan Koopman, Guido Zuccon, Wenhu Chen, Jimmy Lin

Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking Strategies (2026.acl-long)

Challenge:	Existing approaches to retrieval-augmented generation primarily link generated content to document-level references, making it difficult for users to locate evidence among multiple content-rich retrieved documents.
Approach:	They propose a novel approach that combines answer generation with visual source attribution by leveraging large vision-language models to identify evidence and highlight exact regions that support the generated answers with bounding boxes in the retrieved document screenshots.
Outcome:	The proposed approach identifies evidence and highlights exact regions that support the generated answers with bounding boxes in the retrieved document screenshots.

Copied to clipboard

Yuxuan Ye, Raul Santos-Rodriguez, Edwin Simpson

Evidence-Aligned Entity Verification for Hallucination Detection in Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing methods for factuality checking require dataset-specific threshold tuning, while LLM-based approaches often use direct prompting.
Approach:	They propose to use a reading comprehension task to check for true/false claim factuality and prompt LLMs with explicit test-taking strategies for efficient reasoning.
Outcome:	The proposed method reduces token usage by over 80% compared to unguided open-ended reasoning and achieves competitive performance to more expensive alternatives.

Copied to clipboard

Runsong Jia, Zhen Fang, Mengjia Wu, Jie Lu, Yi Zhang

How Much Would a Clinician Edit This Draft? Evaluating LLM Alignment for Patient Message Response Drafting (2026.acl-long)

Challenge:	Existing methods for hallucination detection depend on internal signals like uncertainty and self-consistency checks to identify unreliable outputs.
Approach:	They propose a retrieval-augmented generation method to enhance hallucination detection by addressing information updating challenges.
Outcome:	The proposed method improves on existing methods with strong generalization capabilities.

Copied to clipboard

Parker Seegmiller, Joseph Gatto, Sarah E. Greer, Ganza Belise Isingizwe, Rohan Ray, Timothy E. Burdick, Sarah Masud Preum

Challenge:	Large language models (LLMs) have been shown to be effective in drafting patient portal responses, yet their integration into clinical workflows raises various concerns.
Approach:	They propose a taxonomy of thematic elements in clinician responses and a framework for assessing clinician editing load of LLM-drafted responses at both content and theme levels.
Outcome:	The proposed framework assesses the editing load of LLM-drafted responses at both content and theme levels.

Leveraging Knowledge Graph-Enhanced LLMs for Context-Aware Medical Consultation (2025.emnlp-main)

Copied to clipboard

Su-Hyeong Park, Ho-Beom Kim, Seong-Jin Park, Dinara Aliyeva, Kang-Min Kim

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG (2026.acl-long)

Challenge:	Recent advances in large language models have significantly influenced the field of online medical consultations, but critical challenges remain, such as the generation of hallucinated information and the integration of up-to-date medical knowledge.
Approach:	They propose a framework that combines retrieval-augmented generation with a structured medical knowledge graph.
Outcome:	The proposed framework outperforms baselines on two medical consultation datasets and shows significant improvements in hallucination reduction and clinical usefulness.

Copied to clipboard

Honghao Fu, Miao Xu, Yiwei Wang, Dailing Zhang, Jun Liu, Yujun Cai

Visual Data in NLP

Challenge:	Existing methods for retrieval-augmented generation (RAG) to long videos are limited by limited context windows and flatten videos into independent segments.
Approach:	They propose a structured and intent-aware long-video RAG framework that structures a video as a spatio-temporal graph and then performs multi-hop retrieval to aggregate evidence across distant yet contextually related events.
Outcome:	The proposed framework is competitive with state-of-the-art baselines without auxiliary information.

Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming (2026.acl-long)

Copied to clipboard

Yuhao Li, Haifeng Sun, Xuesong Zhang, Shu Yao, Haoyu Zheng, Yvchuan Wang, Huazheng Wang, Zirui Zhuang, Qi Qi, Jianxin Liao, Jingyu Wang

NitiBench: Benchmarking LLM Frameworks on Thai Legal Question Answering Capabilities (2025.emnlp-main)

Challenge:	Existing approaches to code generation fail to consider the quality of retrieved examples.
Approach:	They propose a retrieval-augmented generation method that combines existing API examples to improve complexity and readability.
Outcome:	The proposed method achieves up to 22% accuracy improvement over baseline methods.

Copied to clipboard

Pawitsapak Akarajaradwong, Pirat Pothavorn, Chompakorn Chaksangchaichot, Panuthep Tasawong, Thitiwat Nopparatbundit, Keerakiat Pratai, Sarana Nutanong

Detecting Corpus-Level Knowledge Inconsistencies in Wikipedia with Large Language Models (2025.emnlp-main)

Challenge:	Large language models (LLMs) show promise in legal question answering (QA), yet Thai legal QA systems face challenges due to limited data and complex legal structures.
Approach:	They propose a benchmark which uses Thai financial laws and tax rulings to evaluate Thai legal QA systems.
Outcome:	The proposed benchmark compared retrieval-augmented generation and long-context LLM approaches across three key dimensions and found that they improve over naive methods.

Copied to clipboard

Sina Semnani, Jirayu Burapacheep, Arpandeep Khatua, Thanawan Atchariyachanvanit, Zheng Wang, Monica Lam

Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models (2026.findings-acl)

Challenge:	a new study examines the accuracy of Wikipedia's factual inconsistencies . a corpus-level inconsistent detection system can help editors identify inconsistances .
Approach:	They propose a corpus-level inconsistency detection system that combines LLM reasoning with retrieval to detect and contextualize potential contradictions for human review.
Outcome:	The proposed system can detect inconsistencies in Wikipedia and human review.

Copied to clipboard

Can Xu, Lingyong Yan, Jiayi Wu, Haosen Wang, Shuaiqiang Wang, Yuchen Li, Jizhou Huang, Dawei Yin, Xiang Li

Agentic Verification for Ambiguous Query Disambiguation (2026.findings-acl)

Challenge:	Existing training paradigms rely on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process.
Approach:	They propose a framework that integrates large reasoning models with retrieval-augmented generation to improve reasoning fidelity and verification rigor.
Outcome:	Experiments on multiple benchmarks demonstrate the effectiveness of the proposed framework.

Copied to clipboard

Youngwon Lee, Seung-won Hwang, Ruofan Wu, Feng Yan, Danmei Xu, Moutasem Akkad, Zhewei Yao, Yuxiong He

Understanding the Behaviors of Environment-aware Information Retrieval (2026.acl-long)

Challenge:	Prior Diversify-then-Verify pipelines generate interpretations and then retrieve evidence . ambiguous queries require RAG to disambiguate into interpretations that can be answered from corpus .
Approach:	They propose a novel approach that unifies diversification with verification by integrating retriever relevance and generator answerability feedback early.
Outcome:	The proposed approach improves grounding-aware F1 by 23% over baselines across multiple LLMs.

Copied to clipboard

Ruifeng Yuan, Chaohao Yuan, David Dai, Yu Rong, Hong Cheng, Hou Pong Chan, Chenghao Xiao

SkMTEB: Slovak Massive Text Embedding Benchmark and Model Adaptation (2026.acl-long)

Challenge:	Recent retrieval-augmented generation approaches have demonstrated strong capability in handling complex queries.
Approach:	They propose a branching-based rollout technique that improves training stability . they find different retrievers exhibit distinct optimal query styles .
Outcome:	The proposed method improves training stability and improves retrieval-aware systems.

Copied to clipboard

Marek Suppa, Andrej Ridzik, Daniel Hládek, Natália Kňažeková, Viktória Ondrejová

SURE or Not? Investigating Semantic Understanding in Dense Retrieval Models (2026.acl-long)

Challenge:	Slovak embeddings are core infrastructure for semantic search, retrieval-augmented generation (RAG), clustering, and classification.
Approach:	They propose a MTEB-style text embedding benchmark for Slovak, a low-resource West Slavic language . they use 31 datasets across 7 task types to evaluate the performance of the models .
Outcome:	The proposed model achieves competitive performance with proprietary APIs while remaining locally deployable for RAG . the model is based on 31 datasets across 7 task types and is 4 the depth of existing benchmark for Slovak .

Copied to clipboard

Lingdi Kong, Xuanang Chen, Ben He, Le Sun

Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models (2026.findings-acl)

Challenge:	Dense retrieval models have been successful in a number of applications but it is unclear whether they truly understand semantics.
Approach:	They propose a benchmark for semantic understanding in dense retrieval that characterizes semantic precision, semantic abstraction and semantic equivalence along three dimensions.
Outcome:	The proposed model characterizes semantic understanding in dense retrieval along three dimensions: semantic precision, semantic abstraction, and semantic equivalence.

Copied to clipboard

Gabeen Kim, Kyeongpil Kang

Agentic Very Long Video Understanding (2026.acl-long)

Challenge:	Historical documents suffer from illegibility due to physical deterioration and damage due to deteriorating materials.
Approach:	a new framework leverages large language models with retrieval-augmented generation to restore historical documents. authors propose a framework that leverages implicit knowledge of pre-trained LLMs with explicitly retrieved external context.
Outcome:	a new framework outperforms existing methods for restoration of historical documents in Korean . the proposed model can restore both general characters and named entities, the authors say .

Copied to clipboard

Aniket Rege, Arka Sadhu, Yuliang Li, Kejie Li, Ramya Korlakai Vinayak, Yuning Chai, Yong Jae Lee, Hyo Jin Kim