ANSWER GENERATION

PeerQA: A Scientific Question Answering Dataset from Peer Reviews (2025.naacl-long)

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

Tim Baumgärtner, Ted Briscoe, Iryna Gurevych

Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation (2022.aacl-main)

Challenge:	a dataset of 579 QA pairs from 208 scientific articles contains answers that reviewers raised while thoroughly examining the scientific article.
Approach:	They propose a dataset that contains questions that reviewers raised while thoroughly examining the scientific article.
Outcome:	The proposed dataset contains 579 QA pairs from 208 academic articles . the results show that decontextualization approaches improve retrieval performance .

Copied to clipboard

Benjamin Muller, Luca Soldaini, Rik Koncel-Kedziorski, Eric Lind, Alessandro Moschitti

Question Decomposition for Retrieval-Augmented Generation (2025.acl-srw)

Challenge:	Open-Domain Generative Question Answering has achieved impressive performance in English . combining document-level retrieval with answer generation can generate complete sentences .
Approach:	They propose an open-domain approach that combines document retrieval with answer generation to generate complete sentences in English . they propose a cross-lingual generative model that exploits passages written in multiple languages .
Outcome:	The proposed model outperforms answer sentence selection baselines for all 5 languages and monolingual pipelines for three out of five languages.

Copied to clipboard

Paul J. L. Ammann, Jonas Golde, Alan Akbik

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

Challenge:	Retrieval-augmented generation (RAG) is effective for question answering tasks . multi-hop questions, such as "Which company among NVIDIA, Apple, and Google made the biggest profit in 2023?" challenge RAG because relevant facts are often distributed across multiple documents .
Approach:	They propose a pipeline that incorporates question decomposition to ground large language models in verifiable external sources.
Outcome:	The proposed approach improves retrieval and answer accuracy over standard RAG . multi-hop questions often require multiple documents to support the model .

Copied to clipboard

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

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

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

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.

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

Copied to clipboard

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

LaMP-QA: A Benchmark for Personalized Long-form Question Answering (2025.emnlp-main)

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

Alireza Salemi, Hamed Zamani

Modeling Multi-hop Question Answering as Single Sequence Prediction (2022.acl-long)

Challenge:	Personalization in question answering systems remains underexplored due to lack of resources . a new benchmark for personalized answer generation is being developed .
Approach:	They propose a LaMP-QA benchmark for evaluating personalized answer generation . they compare evaluation strategies for generating personalized responses and measure their alignment with human preferences.
Outcome:	The proposed benchmark shows that incorporating the personalized context provided leads to performance improvements.

Copied to clipboard

Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Nitish Shirish Keskar, Caiming Xiong

KAT: A Knowledge Augmented Transformer for Vision-and-Language (2022.naacl-main)

Challenge:	Existing generative question answering models that leverage passage retrieval with a pre-trained transformer are not effective for multihop QA.
Approach:	They propose a generative approach that explicitly models the reasoning process to resolve the answer for multi-hop questions by encoding cross-passage interactions.
Outcome:	The proposed model improves on two multi-hop QA datasets and is interpretable.

Copied to clipboard

Liangke Gui, Borui Wang, Qiuyuan Huang, Alexander Hauptmann, Yonatan Bisk, Jianfeng Gao

Semantic Text Processing

Challenge:	Existing methods for knowledge retrieval and answer prediction have left open questions about the quality and relevance of the retrieved knowledge and how the reasoning processes over implicit and explicit knowledge should be integrated.
Approach:	They propose a Knowledge Augmented Transformer which integrates both implicit and explicit knowledge in an encoder-decoder architecture while simultaneously reasoning over both knowledge sources during answer generation.
Outcome:	The proposed model achieves a strong state-of-the-art (+6% absolute) on the open-domain multimodal task of OK-VQA.

Towards Mitigating LLM Hallucination via Self Reflection (2023.findings-emnlp)

Copied to clipboard

Ziwei Ji, Tiezheng Yu, Yan Xu, Nayeon Lee, Etsuko Ishii, Pascale Fung

MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A (2026.acl-industry)

Challenge:	Large language models have shown promise for generative and knowledge-intensive tasks including question-answering (QA) but the practical deployment still faces challenges, notably the issue of “hallucination”, where models generate plausible-sounding but unfaithful or nonsensical information.
Approach:	They propose a self-reflection methodology that incorporates knowledge acquisition and answer generation to address the issue of "hallucination" they use a set of LLMs to generate a more accurate and factually accurate answer.
Outcome:	The proposed approach improves factuality, consistency, and entailment of the generated answers.

Copied to clipboard

Hanoz Bhathena, Parin Rajesh Jhaveri, Rohan Mittal, Prateek Singh, Aymen Kallala, Rachneet Kaur, Yiqiao Jin, Zhen Zeng, Adwait Ratnaparkhi, Denis Kochedykov

From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models (2025.emnlp-main)

Challenge:	Recent advances in multimodal retrieval-augmented generation (MM-RAG) have shifted toward minimal parsing, relying on page-level images for producing retriever embeddings and answer generation.
Approach:	They propose a document structure-aware split that extracts and represents document structure via a structure-based split that dynamically routes documents through orientation-specific ingestion pipelines.
Outcome:	The proposed model outperforms state-of-the-art vision-centric baselines by up to 32% points and achieves strong gains on report-style layouts.

Copied to clipboard

Jue Zhang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

Language Models

Challenge:	Large Reasoning Models generate explicit reasoning traces alongside final answers . the extent to which these traces influence answer generation remains unclear .
Approach:	They conduct empirical evaluation of Large Reasoning Models that include explicit reasoning . they also show that answer tokens attend substantially to reasoning tokens .
Outcome:	The results show that including explicit reasoning improves answer quality across domains . they also show that answer tokens attend substantially to reasoning tokens - the authors .

Video Dialog via Progressive Inference and Cross-Transformer (D19-1)

Copied to clipboard

Weike Jin, Zhou Zhao, Mao Gu, Jun Xiao, Furu Wei, Yueting Zhuang

Efficient Table Retrieval and Understanding with Multimodal Large Language Models (2026.findings-eacl)

Challenge:	Existing visual dialog methods use RNN to encode the dialog history as a vector representation . a new method for video dialog is proposed, which progressively updates query information based on dialog history and video content until the agent think the information is sufficient and unambiguous.
Approach:	They propose a method which progressively updates query information based on dialog history and video content until the agent thinks it is sufficient and unambiguous.
Outcome:	The proposed method can be used to infer video dialog answers on large-scale datasets.

Copied to clipboard

Zhuoyan Xu, Haoyang Fang, Boran Han, Bonan Min, Bernie Wang, Cuixiong Hu, Shuai Zhang

Incorporating External Knowledge into Machine Reading for Generative Question Answering (D19-1)

Challenge:	Tabular data is often captured in image form across a wide range of real-world scenarios.
Approach:	They propose a framework that enables MLLMs to answer queries over large tables.
Outcome:	The proposed framework outperforms existing methods by 7.0% in retrieval recall and 6.1% in answer accuracy on a newly constructed dataset with 48,504 unique tables.

Copied to clipboard

Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li

Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models (2022.emnlp-main)

Challenge:	Existing knowledge-aware QA models do not have commonsense and background knowledge to answer nontrivial questions.
Approach:	They propose a new neural model which exploits external knowledge to generate answers in natural language for a given question with context.
Outcome:	The proposed model improves answer quality over existing models without knowledge and knowledge-aware models, a study shows . state officials in Hawaii confirmed that president Barack Obama was born in the U.S.

Copied to clipboard

Shujian Zhang, Chengyue Gong, Xingchao Liu

WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering (2026.findings-acl)

Challenge:	Xu et al., 2021) find that retrieval-reader models overfit top-rank passages and fail to reason over entire retrieval passages.
Approach:	They propose a passage mask mechanism which desensitizes the impact from top-rank retrieval passages and prevents the model from overfitting.
Outcome:	Experiments on open question answering, dialogue conversation, and fact verification show that the proposed model outperforms baselines.

Copied to clipboard

Yingjian Zhu, Xinming Wang, Kun Ding, Ying Wang, Bin Fan, Shiming Xiang

VD-BERT: A Unified Vision and Dialog Transformer with BERT (2020.emnlp-main)

Challenge:	Existing methods for Knowledge-Based Visual Question Answering rely on images as the retrieval key, and often overlook or misplace the role of Vision-Language Models (VLMs)
Approach:	They propose a multi-modal RAG framework that assigns VLMs two specialized agents: a Refiner and an Inspector.
Outcome:	Experiments on EVQA, InfoSeek, and M2KR show that the proposed framework achieves state-of-the-art performance with significant improvements in both retrieval accuracy and answer quality.

Copied to clipboard

Yue Wang, Shafiq Joty, Michael Lyu, Irwin King, Caiming Xiong, Steven C.H. Hoi

Retrieve-Plan-Generation: An Iterative Planning and Answering Framework for Knowledge-Intensive LLM Generation (2024.emnlp-main)

Challenge:	Prior work focused on attention mechanisms to model complex interactions in visual dialog . a new framework for visual dialog is based on pretrained BERT language models .
Approach:	They propose a framework for a vision-dialog Transformer that leverages pretrained BERT language models for Visual Dialog tasks.
Outcome:	The proposed framework achieves the top position on the visual dialog leaderboard without pretraining on external vision-language data.

Copied to clipboard

Yuanjie Lyu, Zihan Niu, Zheyong Xie, Chao Zhang, Tong Xu, Yang Wang, Enhong Chen

RADAR: A Reasoning-Guided Attribution Framework for Explainable Visual Data Analysis (2026.findings-eacl)

Challenge:	Large language models (LLMs) often produce factual errors due to limited internal knowledge.
Approach:	They propose a retrieval-augmented generation framework that generates plan tokens to guide subsequent generation.
Outcome:	The proposed framework improves the accuracy of large language models with external knowledge sources.

Copied to clipboard

Anku Rani, Aparna Garimella, Apoorv Saxena, Balaji Vasan Srinivasan, Paul Pu Liang

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning (2025.findings-emnlp)

Challenge:	Multimodal Large Language Models (MLLMs) provide no visibility into which parts of visual data informed their conclusions.
Approach:	They propose a semi-automatic approach to attribute reasoning process by highlighting regions in charts and graphs that justify model answers.
Outcome:	The proposed method improves attribution accuracy by up to 15 percentage points compared to baseline methods and achieves high semantic similarity with ground truth responses.

Copied to clipboard

Xiaoyun Zhang, Jingqing Ruan, Xing Ma, Yawen Zhu, Haodong Zhao, Hao Li, Jiansong Chen, Ke Zeng, Xunliang Cai

Responsible & Trustworthy NLP

Challenge:	Large reasoning models (LRMs) incur excessive computational overhead due to redundant reasoning, especially on simple tasks.
Approach:	They propose an Adaptive Self-Recovery Reasoning framework that suppresses unnecessary reasoning and enables implicit recovery.
Outcome:	The proposed framework suppresses unnecessary reasoning and enables implicit recovery.

KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering (2025.findings-emnlp)

Copied to clipboard

Yushi Sun, Kai Sun, Yifan Ethan Xu, Xiao Yang, Xin Luna Dong, Nan Tang, Lei Chen

Structured Data in NLP

Challenge:	Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing to retrieve knowledge strictly necessary for answer generation.
Approach:	They propose a retrieval-filtering-summarization pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information.
Outcome:	The proposed pipeline surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.

InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering (2025.emnlp-main)

Copied to clipboard

Zihan Wang, Zihan Liang, Zhou Shao, Yufei Ma, Huangyu Dai, Ben Chen, Lingtao Mao, Chenyi Lei, Yuqing Ding, Han Li

Faux Polyglot: A Study on Information Disparity in Multilingual Large Language Models (2025.naacl-long)

Challenge:	Retrieval-Augmented Generation (RAG) frameworks struggle with identifying whether retrieved documents meaningfully contribute to answer generation.
Approach:	They propose a document-related metric to quantify the contribution of retrieved documents to correct answer generation.
Outcome:	The proposed framework outperforms existing approaches on both single and multiple retrieval paradigms.

Copied to clipboard

Nikhil Sharma, Kenton Murray, Ziang Xiao

Multilinguality

Challenge:	Recent surge in multilingual large language models (LLMs) and Retrieval Augmented Generation (RAG) has significantly expanded conversational search across varied linguistic and cultural demographics.
Approach:	They found that LLMs displayed systemic bias towards information in the same language as query language in document retrieval and answer generation.
Outcome:	The results highlight the linguistic divide within multilingual LLMs in information search systems.

PokeMQA: Programmable knowledge editing for Multi-hop Question Answering (2024.acl-long)

Copied to clipboard

Hengrui Gu, Kaixiong Zhou, Xiaotian Han, Ninghao Liu, Ruobing Wang, Xin Wang

Language Models

Challenge:	Multi-hop question answering (MQA) is one of the challenging tasks to evaluate machine’s comprehension and reasoning abilities, where large language models (LLMs) have widely achieved the human-comparable performance.
Approach:	They propose a framework to edit multi-hop question models to update model with up-to-date facts while avoiding expensive re-training or fine-tuning.
Outcome:	The proposed framework outperforms all competitors in multi-hop question answering tasks and consistently produces reliable reasoning process.

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

Copied to clipboard

Xingchen Xiao, Heyan Huang, Runheng Liu, Jincheng Xie

Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation (2025.findings-emnlp)

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

Changle Qu, Sunhao Dai, Hengyi Cai, Yiyang Cheng, Jun Xu, Shuaiqiang Wang, Dawei Yin

SCAI-QReCC Shared Task on Conversational Question Answering (2022.lrec-1)

Challenge:	Existing efforts to estimate document utility rely on downstream generation performance, which conflates the influence of external documents with the intrinsic knowledge of the LLM.
Approach:	They propose an uplift-based definition of document utility that quantifies each document’s marginal benefit over the LLM’s internal knowledge.
Outcome:	The proposed framework improves the performance of the LLM by incorporating external retrieved documents into the model.

Copied to clipboard

Svitlana Vakulenko, Johannes Kiesel, Maik Fröbe

AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time (2025.emnlp-main)

Challenge:	evaluating systems for conversational QA remains an open research problem in its own right . evaluating (conversational) QA systems remains an important challenge for developing conversational information retrieval (conversional search) systems.
Approach:	They propose to use a conversational question answering task to extend the original conversational QA dataset with alternative correct answers produced by participant systems.
Outcome:	The proposed task was based on the SCAI-QReCC 2021 shared task on conversational question answering.

Copied to clipboard

Junyu Zhang, Runpei Dong, Han Wang, Xuying Ning, Haoran Geng, Peihao Li, Xialin He, Yutong Bai, Jitendra Malik, Saurabh Gupta, Huan Zhang

Responsible & Trustworthy NLP

Challenge:	Existing monotonic scaling methods for large reasoning models are not reliable.
Approach:	They propose a universal framework for modulating reasoning progress in large reasoning models at test time.
Outcome:	The proposed framework unifies and generalizes existing monotonic scaling methods and enables flexible and dense slow-to-fast reasoning modulation.

Causal Reasoning through Two Cognition Layers for Improving Generalization in Visual Question Answering (2023.emnlp-main)

Copied to clipboard

Trang Nguyen, Naoaki Okazaki

MuKA: Multimodal Knowledge Augmented Visual Information-Seeking (2025.coling-main)

Challenge:	Existing attempts to generalize VQA focus on unimodal aspects, overlooking enhancements in multimodal aspects.
Approach:	They propose to decompose the responsibility of each stage into distinct experts and a cognition-enabled component (CC) they prioritize answer predictions governed by pathways involving both CCs while disregarding answers produced by either CC.
Outcome:	The proposed model improves multimodal predictions by emphasizing causal reasoning factors.

Copied to clipboard

Lianghao Deng, Yuchong Sun, Shizhe Chen, Ning Yang, Yunfeng Wang, Ruihua Song

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

Challenge:	Existing methods for visual information-seeking tasks rely on textual knowledge . existing methods can impair information retrieval and confuse MLLMs .
Approach:	They propose a framework which leverages a multimodal knowledge base to address these limitations.
Outcome:	The proposed framework outperforms state-of-the-art methods on the InfoSeek and E-VQA benchmarks.

Copied to clipboard

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

Robustness in NLP

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.

MESAQA: A Dataset for Multi-Span Contextual and Evidence-Grounded Question Answering (2025.coling-main)

Copied to clipboard

Jui-I Wang, Hen-Hsen Huang, Hsin-Hsi Chen

Question Answering

Challenge:	Existing question answering systems focus on extracting answers from single spans, but real-world scenarios require synthesizing information from multiple spans.
Approach:	They propose a dataset that leverages the MASH-QA dataset and large language models (LLMs) to ensure that each Q/A pair requires considering all selected spans.
Outcome:	The proposed method enables the model to answer multiple Q/A pairs in a single span, while ensuring that all selected spans are considered.

SKRAG: A Retrieval-Augmented Generation Framework Guided by Reasoning Skeletons over Knowledge Graphs (2025.findings-emnlp)

Copied to clipboard

Xiaotong Xu, Yizhao Wang, Yunfei Liu, Shengyang Li

Semantic Text Processing

Challenge:	Existing KG-based question answering frameworks face inefficient subgraph retrieval, limited reasoning capabilities, and high computational costs.
Approach:	They propose a Skeleton-guided RAG framework for knowledge graph question answering . SKRAG leverages a lightweight language model enhanced with the Finite State Machine constraint .
Outcome:	The proposed framework outperforms baselines and general-domain benchmarks on a KGQA dataset in the space science and utilization domain.

Retrieval Augmented Visual Question Answering with Outside Knowledge (2022.emnlp-main)

Copied to clipboard

Weizhe Lin, Bill Byrne

Agentic-R: Learning to Retrieve for Agentic Search (2026.findings-acl)

Challenge:	Recent systems that use Dense Passage Retrieval (DPR) for visual question answering use Denses trained separately from answer generation.
Approach:	They propose a joint training scheme that integrates DPR with answer generation to improve the performance of OK-VQA systems.
Outcome:	The proposed model outperforms existing systems with strong Dense Passage Retrieval (DPR) it yields significant improvements in answer quality and computation required for training.

Copied to clipboard

Wenhan Liu, Xinyu Ma, Yutao Zhu, Yuchen Li, Daiting Shi, Dawei Yin, Zhicheng Dou

AnchorCoT: Anchors Pave the Way for Multi-hop Reasoning (2025.findings-acl)

Challenge:	Existing retrievers for single-turn retrieval-augmented generation (RAG) rely on similarity-based retrievers, but similar passages are not always useful for final answer generation.
Approach:	They propose a retrieval-augmented-generation retriever that integrates reasoning with retrieval . they use local query-passage relevance and global answer correctness to measure passage utility .
Outcome:	The proposed retriever outperforms existing retrievers on QA benchmarks on seven single-hop and multi-hop searches.

Copied to clipboard

Tianshi Ming, Xian Wu, Yingying Zhang, Zichuan Fu, Dawei Cheng

Multi-Level Information Retrieval Augmented Generation for Knowledge-based Visual Question Answering (2024.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated potential reasoning capabilities through prompt design, such as the Chain of Thought (CoT).
Approach:	They propose a new reasoning approach that predicts key entities which work as important “anchors” and employs a ranking algorithm to ensure the logical sequence of the predicted answers.
Outcome:	The proposed approach outperforms existing methods in multi-hop question reasoning and provides more accurate reasoning results in multihop question answering tasks.

Copied to clipboard

Adjali Omar, Olivier Ferret, Sahar Ghannay, Hervé Le Borgne

AgentRM: Enhancing Agent Generalization with Reward Modeling (2025.acl-long)

Challenge:	Knowledge-Aware Visual Question Answering about Entity tasks require two separate steps to generate accurate answers.
Approach:	They propose a multi-level information RAG approach that enhances answer generation through entity retrieval and query expansion.
Outcome:	The proposed approach improves answer generation through entity retrieval and query expansion.

Copied to clipboard

Yu Xia, Jingru Fan, Weize Chen, Siyu Yan, Xin Cong, Zhong Zhang, Yaxi Lu, Yankai Lin, Zhiyuan Liu, Maosong Sun

Robustness in NLP

Challenge:	Existing LLM-based agents have strong performance on held-in tasks, but their generalizability to unseen tasks remains poor.
Approach:	They propose a reward-based generalizable reward model to guide the policy model for effective test-time search.
Outcome:	The proposed agentRM outperforms existing agents on held-in tasks by 8.8 points on average.

ClimRetrieve: A Benchmarking Dataset for Information Retrieval from Corporate Climate Disclosures (2024.emnlp-main)

Copied to clipboard

Tobias Schimanski, Jingwei Ni, Roberto Martín, Nicola Ranger, Markus Leippold

Representation Learning

Challenge:	Qualitative disclosures typically include narrative descriptions of climate-related risks, opportunities, strategies, and governance.
Approach:	They simulate typical tasks of a sustainability analyst by examining 30 sustainability reports with 16 detailed climate-related questions.
Outcome:	The proposed model combines expert knowledge with embeddings in a dataset with over 8.5K unique question-source-answer pairs labeled by different levels of relevance.

MedLogic-AQA: Enhancing Medicare Question Answering with Abstractive Models Focusing on Logical Structures (2024.findings-emnlp)

Copied to clipboard

Aizan Zafar, Kshitij Mishra, Asif Ekbal

MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Bandits (2026.acl-long)

Challenge:	Existing question-answering systems struggle to capture intricate logical structures and relationships inherent in medical contexts, thus limiting their capacity to furnish precise and nuanced answers.
Approach:	They propose a system that harnesses first-order logic-based rules extracted from context and questions to generate well-grounded answers.
Outcome:	The proposed system generates well-grounded answers based on first-order logic-based rules extracted from context and questions.

Copied to clipboard

Yixin Xiang, Yunshan Ma, Xiaoyu Du, Yibing Chen, Yanxin Zhang, Jinhui Tang

Improving Context Fidelity via Native Retrieval-Augmented Reasoning (2025.emnlp-main)

Challenge:	Document Question Answering (DQA) requires interpreting visual layouts, which has prompted recent studies to adopt multimodal Retrieval-Augmented Generation (RAG) that processes page images for answer generation.
Approach:	They propose a multi-armed bandit-based DQA framework that explicitly models the varying importance of multiple implicit aspects in a query.
Outcome:	The proposed framework shows an improvement of 5%-18% over the state-of-the-art method on four benchmarks.

Copied to clipboard

Suyuchen Wang, Jinlin Wang, Xinyu Wang, Shiqi Li, Xiangru Tang, Sirui Hong, Xiao-Wen Chang, Chenglin Wu, Bang Liu

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering (2025.acl-long)

Challenge:	Existing approaches to fidelity to contexts rely on expensive supervised fine-tuning to generate evidence post-answer or train models to perform web searches without improving utilization of the given context.
Approach:	They propose a native retrieval-augmented reasoning framework that integrates in-context evidence with the model’s own retrieval capabilities.
Outcome:	The proposed approach outperforms supervised fine-tuning, retrieval-augmented generation methods, and external retrieval solutions on multiple real-world and counterfactual QA benchmarks.

Copied to clipboard

Rongzhi Zhu, Xiangyu Liu, Zequn Sun, Yiwei Wang, Wei Hu

RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrieval (2025.findings-emnlp)

Challenge:	Empirical results show that ChainRAG consistently outperforms baselines in both effectiveness and efficiency.
Approach:	They propose a method which sequentially handles each sub-question by completing missing key entities and retrieving relevant sentences from a sentence graph for answer generation.
Outcome:	The proposed method outperforms baselines on three multi-hop QA datasets.

Copied to clipboard

Kaishuai Xu, Wenjun Hou, Yi Cheng, Wenjie Li

The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction (2025.findings-acl)

Challenge:	Existing methods focus on refining queries without modeling the reasoning process, limiting their ability to retrieve and integrate clinically relevant knowledge.
Approach:	They propose a joint learning framework that improves Reasoning-Augmented Retrieval and Retri-Agmented Reasoning.
Outcome:	The proposed model outperforms RAG baselines on biomedical question answering datasets.

Copied to clipboard

Yihuai Hong, Meng Cao, Dian Zhou, Lei Yu, Zhijing Jin

Language Models

Challenge:	Large language models excel on a variety of reasoning benchmarks, but struggle to generalize to unseen questions due to over-reliance on memorized training examples.
Approach:	They propose to identify a set of linear features in the model’s residual stream that govern the balance between genuine reasoning and memory recall.
Outcome:	The proposed model can be manipulated to activate the most relevant problem-solving capabilities during answer generation.

ECoRAG: Evidentiality-guided Compression for Long Context RAG (2025.findings-acl)

Copied to clipboard

Yeonseok Jeong, Jinsu Kim, Dohyeon Lee, Seung-won Hwang

TALON: A Multi-Agent Framework for Long-Table Exploration and Question Answering (2025.emnlp-main)

Challenge:	Existing compression methods do not focus on filtering out non-evidential information, which limit performance in LLMs.
Approach:	They propose a framework that leverages external documents through Retrieval-Augmented Generation (RAG) to reduce RAG overhead.
Outcome:	Experiments show that ECoRAG outperforms existing compression methods on ODQA tasks.

Copied to clipboard

Ruochun Jin, Xiyue Wang, Dong Wang, Haoqi Zheng, Yunpeng Qi, Silin Yang, Meng Zhang

BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering (2025.emnlp-main)

Challenge:	Existing approaches to query-relevant content retrieval fail to retrieve contextually relevant data.
Approach:	They propose a multi-agent framework for table question answering over long tables . TALON features a planning agent that iteratively invokes a tool agent to access tabular data .
Outcome:	The proposed framework achieves average accuracy improvements of 7.5% and 12.0% across all language models.

Copied to clipboard

Costas Mavromatis, Soji Adeshina, Vassilis N. Ioannidis, Zhen Han, Qi Zhu, Ian Robinson, Bryan Thompson, Huzefa Rangwala, George Karypis

Structured Data in NLP

Challenge:	Existing approaches to knowledge graph question answering (KGQA) rely on Large Language Model (LLM) agents for graph traversal and retrieval.
Approach:	They propose a framework that synergizes Large Language Models with specialized graph retrieval tools to enhance KGQA.
Outcome:	The proposed framework outperforms the second-best graph retrieval method by 4.5% points while showing better generalization to custom KGs.

Do LLMs Encode Functional Importance of Reasoning Tokens ? (2026.acl-long)

Copied to clipboard

Janvijay Singh, Dilek Hakkani-Tür

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

Challenge:	Existing compact reasoning approaches generate long reasoning chains, but they lack a mechanism to encode token-level functional importance for answer generation.
Approach:	They propose a procedure that iteratively removes reasoning tokens from models and prunes them to yield length-controlled reasoning chains.
Outcome:	The proposed procedure outperforms a frontier model at reasoning lengths and shows that attention scores predict greedy pruning ranks.

Copied to clipboard

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

Piece of Table: A Divide-and-Conquer Approach for Selecting Subtables in Table Question Answering (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

Wonjin Lee, Kyumin Kim, Sungjae Lee, Jihun Lee, Kwang In Kim

Structured Data in NLP

Challenge:	Existing approaches to QA tables rely on independent row or column selection, fail to capture cross-row and cross-column dependencies, or attempt global reasoning.
Approach:	They propose a divide-and-conquer subtable selection framework that aggregates local evidence without requiring explicit global reasoning.
Outcome:	The proposed framework outperforms previous approaches to table QA in the noisy context.

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs (2026.findings-acl)

Copied to clipboard

Hengran Zhang, Keping Bi, Jiafeng Guo, Xueqi Cheng

Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering (2026.acl-long)

Challenge:	Relevance emphasizes the aboutness of a result to a query, while utility refers to the result’s usefulness or value to an information seeker.
Approach:	They propose an Iterative utiliTy judgmEnt fraMework to promote each step in Retrieval-Augmented Generation (RAG) they propose to use relevance ranking, utility judgments, and answer generation to prioritize high-utility results over low-utilitity results.
Outcome:	The proposed framework improves relevance, ranking, and answer generation on retrieval (TREC DL, WebAP), utility judgment task (GTI-NQ), and factoid question-answering (NQ) datasets.

Copied to clipboard

Haosen Wang, Jing Xiao, Chaochao Du, Xiaowang Zhang, Zhiyong Feng

Progressive Re-ranking for Multimodal Retrieval-Augmented Generation via Curriculum Learning (2026.findings-acl)

Challenge:	Document Visual Question Answering (DocVQA) aims to generate answers by understanding textual, layout, and visual elements within document images.
Approach:	They propose a Flow-Based Page Unique Semantic Mapping Architecture to solve the distinguishability problem among semantically similar pages.
Outcome:	The proposed model outperforms existing methods in evidence localization and answer generation.

Copied to clipboard

Zhu Min, Yanchao Hao, Jian Liu, Shizhu He, Xi Chen

BubbleRAG: Interactive Cognitive Offloading with Thought Bubble in Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Existing approaches to improve retrieval performance of large language models are limited by static knowledge.
Approach:	They propose a multimodal re-ranking framework that combines curriculum learning with fine-grained reranking and multimodal section reassessment to improve CLIP-based visual coarse-grain retrieval.
Outcome:	The proposed framework achieves state-of-the-art answer accuracy and competitive retrieval performance on InfoSeek and Enc-VQA.

Copied to clipboard

Fuda Ye, Jiachuan Wang, Yongqi Zhang, Lei Chen, Shuangyin Li