SUB-TASKS

Comparing Constraints for Taxonomic Organization (N18-1)

Challenge:	Existing work on question answering over knowledge bases limited the search space to a subset of KBs . a retrieval-and-rerank framework is used to access KB and rerank retrieved candidates with more powerful neural networks.
Approach:	They propose to share a BERT encoder across all three sub-tasks and define task-specific layers on top of the shared layer.
Outcome:	The proposed method improves accuracy and accuracy on the SimpleQuestions dataset and the FreebaseQA dataset.

Copied to clipboard

Anne Cocos, Marianna Apidianaki, Chris Callison-Burch

Challenge:	Using general ontologies and domain-specific ontology, taxonomies encode knowledge that is important for understanding systems.
Approach:	They propose to modify a non-transitive branching algorithm to explicitly incorporate synonymy into the taxonomy structure to give it a faster performance.
Outcome:	The proposed method outperforms the best transitive algorithm while giving comparable performance over a dataset of local taxonomies.

Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications (2023.acl-short)

Copied to clipboard

Jatin Arora, Youngja Park

Can Sequence-to-Sequence Transformers Naturally Understand Sequential Instructions? (2023.starsem-1)

Challenge:	Named entity recognition (NER) is a foundational task for a variety of applications like question answering and machine translation.
Approach:	They propose to split entity recognition problem into two sub-tasks and optimize them separately for each sub-task.
Outcome:	The proposed system outperforms baselines on OntoNotes5.0, WNUT17 and a cybersecurity dataset and gives on-par performance on BioNLP13CG.

Copied to clipboard

Xiang Zhou, Aditya Gupta, Shyam Upadhyay, Mohit Bansal, Manaal Faruqui

Efficient Dialogue State Tracking by Selectively Overwriting Memory (2020.acl-main)

Challenge:	Using a limited annotation budget, we can greatly improve the performance on intermediate steps with a drop in final-step performance.
Approach:	They propose to use a pre-supervised sequence-to-sequence transformer to provide training signals on intermediate steps with zero gold supervision instead of only final-step supervision to improve performance.
Outcome:	The proposed model significantly improves on intermediate steps with a drop in final-step performance on one subtask, but also shows decreased performance on another subtask.

Copied to clipboard

Sungdong Kim, Sohee Yang, Gyuwan Kim, Sang-Woo Lee

Dialogue Systems & Conversational Agents

Challenge:	Recent work in dialogue state tracking (DST) is inefficient in that it predicts dialogue state at every turn from scratch.
Approach:	They propose a method that selectively overwrites memory for dialogue state tracking by predicting dialogue state on each memory slot and overwriting it with new values.
Outcome:	The proposed model achieves state-of-the-art joint goal accuracy with 51.72% in MultiWOZ 2.0 and 53.01% in MultiWoz 2.1 in an open vocabulary-based DST setting.

An Empirical Study of Pipeline vs. Joint approaches to Entity and Relation Extraction (2022.aacl-short)

Copied to clipboard

Zhaohui Yan, Zixia Jia, Kewei Tu

Sentiment Tagging with Partial Labels using Modular Architectures (P19-1)

Challenge:	Entity and Relation Extraction tasks are often compared to pipeline approaches . a recent study shows that joint approaches can produce comparable results .
Approach:	They propose to use two approaches to the Entity and Relation Extraction task to compare their performance.
Outcome:	The proposed approach outperforms the best pipeline model but improperly designed approaches may have poor performance.

Copied to clipboard

Xiao Zhang, Dan Goldwasser

AQE: Argument Quadruplet Extraction via a Quad-Tagging Augmented Generative Approach (2023.findings-acl)

Challenge:	Many NLP learning tasks can be decomposed into sub-tasks, each associated with a partial label.
Approach:	They propose a modular learning approach where sub-tasks are learned using functional modules . they propose 'learning with partial labels' approach that decomposes tasks into partial labels .
Outcome:	The proposed approach can simplify learning and reduce supervision efforts.

Copied to clipboard

Jia Guo, Liying Cheng, Wenxuan Zhang, Stanley Kok, Xin Li, Lidong Bing

Joint Learning for Emotion Classification and Emotion Cause Detection (D18-1)

Challenge:	Argument mining involves multiple subtasks, but each one is insufficient for understanding argumentative structure and reasoning process.
Approach:	They propose a quadruplet extraction task that extracts four argumentative components . they use a generative quadragging module to augment the training of the generative framework .
Outcome:	The proposed method can extract arguments from a large-scale dataset.

Copied to clipboard

Ying Chen, Wenjun Hou, Xiyao Cheng, Shoushan Li

Label Correction Model for Aspect-based Sentiment Analysis (2020.coling-main)

Challenge:	Using a unified framework, we propose a joint approach for emotion classification and emotion cause detection.
Approach:	They propose a neural network-based joint approach for emotion classification and emotion cause detection which captures mutual benefits across the two sub-tasks.
Outcome:	The proposed approach can capture mutual benefits across two sub-tasks on Chinese microblogs.

Copied to clipboard

Qianlong Wang, Jiangtao Ren

Sentiment Analysis

Challenge:	Existing models for aspect-based sentiment analysis ignore a phenomenon: aspect boundary label and sentiment label can correct each other.
Approach:	They propose a model that uses aspect boundary label and sentiment label to correct each other . they evaluate the model on three benchmark datasets and evaluate its performance .
Outcome:	The proposed model performs state-of-the-art on three benchmark datasets.

AnaDE1.0: A Novel Data Set for Benchmarking Analogy Detection and Extraction (2024.eacl-long)

Copied to clipboard

Bhavya Bhavya, Shradha Sehgal, Jinjun Xiong, ChengXiang Zhai

Reasoning

Challenge:	Textual analogies that make comparisons between two concepts are often used for explaining complex ideas, creative writing, and scientific discovery.
Approach:	They propose a task that includes three synergistic tasks: detecting documents containing analogies, extracting text segments that make up the analogy, and identifying the (source and target) concepts being compared.
Outcome:	The proposed task performs well on all sub-tasks and smaller models perform better than non-finetuned ChatGPT, suggesting high task difficulty.

FELIX: Flexible Text Editing Through Tagging and Insertion (2020.findings-emnlp)

Copied to clipboard

Jonathan Mallinson, Aliaksei Severyn, Eric Malmi, Guillermo Garrido

StoryER: Automatic Story Evaluation via Ranking, Rating and Reasoning (2022.emnlp-main)

Challenge:	FELIX is efficient in low-resource settings and fast at inference time, while being capable of modeling flexible input-output transformations.
Approach:	They propose a flexible text-editing approach that decomposes a text-generating task into two sub-tasks: tagging and insertion.
Outcome:	The proposed model is efficient in low-resource settings and fast at inference time while being capable of modeling flexible input-output transformations.

Copied to clipboard

Hong Chen, Duc Vo, Hiroya Takamura, Yusuke Miyao, Hideki Nakayama

Crawling The Internal Knowledge-Base of Language Models (2023.findings-eacl)

Challenge:	Existing automatic story evaluation methods place a premium on story lexical level coherence, deviating from human preference.
Approach:	They propose a novel Story Evaluation method that mimics human preference when judging a story . the model is based on a well-annotated dataset and a longformer-encoder-decoder .
Outcome:	The proposed method is applicable to machine-generated and human-written stories.

Copied to clipboard

Roi Cohen, Mor Geva, Jonathan Berant, Amir Globerson

MatRank: Text Re-ranking by Latent Preference Matrix (2022.findings-emnlp)

Challenge:	Existing methods for representing factual knowledge in a language model are insufficient.
Approach:	They propose a procedure for “crawling” the internal knowledge-base of a language model by expanding a knowledge-graph around it.
Outcome:	The proposed method yields high precision graphs (82-92%) while emitting a reasonable number of facts per entity.

Copied to clipboard

Jinwen Luo, Jiuding Yang, Weidong Guo, Chenglin Li, Di Niu, Yu Xu

Information Retrieval

Challenge:	Existing methods for text ranking have improved performance, but there are still challenges.
Approach:	They propose a method that learns to re-rank the text retrieved for a given query by learning to predict the most relevant passage based on a latent preference matrix.
Outcome:	The proposed method outperforms all prior methods on datasets with extensive results.

Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Tasks (2021.naacl-main)

Copied to clipboard

Siddharth Dalmia, Brian Yan, Vikas Raunak, Florian Metze, Shinji Watanabe

Semantic Alignment with Calibrated Similarity for Multilingual Sentence Embedding (2021.findings-emnlp)

Challenge:	ESPnet framework exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks.
Approach:	They propose a framework that exploits compositionality to learn searchable hidden representations at intermediate stages of a sequence model using decomposed sub-tasks.
Outcome:	The proposed framework outperforms the state-of-the-art on speech translation tasks by +6 and +3 BLEU on the two test sets of Fisher-CallHome and +4 BLUE on the English-German and English-French test sets.

Copied to clipboard

Jiyeon Ham, Eun-Sol Kim

Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering (2021.naacl-main)

Challenge:	Existing methods for learning semantic similarity between two English sentences have focused on one sub-task and therefore showed biased performance.
Approach:	They propose a method to learn semantic similarity between two English sentences using siamese networks.
Outcome:	The proposed method improves on both sub-tasks and predicts similarity scores in 14 languages.

Copied to clipboard

Kiran Ramnath, Leda Sari, Mark Hasegawa-Johnson, Chang Yoo

Towards End-to-End Open Conversational Machine Reading (2023.findings-eacl)

Challenge:	Question-Answering has long been of interest, but its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies.
Approach:	They propose a task and a synthetically-generated dataset to do Fact-based Visual Spoken-Question Answering (FVSQA) the task requires a system to retrieve an entity from Knowledge Graphs (KGs) the question is spoken rather than typed.
Outcome:	The proposed task performs at same levels of accuracy across 3 languages, including English, Hindi, and Turkish.

Copied to clipboard

Sizhe Zhou, Siru Ouyang, Zhuosheng Zhang, Hai Zhao

Natural Language Interfaces

Challenge:	Existing approaches to the problem of open-retrieval conversational machine reading (OR-CMR) use two separate modules to approach the problem's two successive sub-tasks.
Approach:	They propose to model OR-CMR as a unified text-to-text task in a fully end-to end style and propose to use a text-based approach to solve the problem.
Outcome:	Experiments on the ShARC and OR-ShARC dataset show that the proposed framework can generalize to different backbone models.

EdiT5: Semi-Autoregressive Text Editing with T5 Warm-Start (2022.findings-emnlp)

Copied to clipboard

Jonathan Mallinson, Jakub Adamek, Eric Malmi, Aliaksei Severyn

End-to-End Chinese Speaker Identification (2022.naacl-main)

Challenge:	Pre-trained seq2seq models have established strong baselines for text-to-text transduction tasks.
Approach:	They propose a semi-autoregressive text-editing approach that combines the strengths of non-auto-regressively text- editing and autoregressive decoding.
Outcome:	The proposed model is faster at inference times than conventional models while being capable of modeling flexible input-output transformations.

Copied to clipboard

Dian Yu, Ben Zhou, Dong Yu

Visual Named Entity Linking: A New Dataset and A Baseline (2022.findings-emnlp)

Challenge:	Existing methods for speaker identification in texts are incomplete and introduce errors that propagate and seriously affect the final output.
Approach:	They propose to use speaker identification (SI) in texts to identify the speaker(s) for each utterance in texts.
Outcome:	The proposed model can achieve comparable or better than previous state-of-the-art methods on all public SI datasets for Chinese.

Copied to clipboard

Wen Sun, Yixing Fan, Jiafeng Guo, Ruqing Zhang, Xueqi Cheng

Visual Data in NLP

Challenge:	Existing tasks in Visual Entity Linking (VEL) rely on textual data to complement multi-modal linking or only link objects with general entities.
Approach:	They propose a task to link regions of images with corresponding entities in Knowledge Bases . they propose three sub-tasks, based on a human-annotated visual person dataset .
Outcome:	The proposed task is based on a human-annotated visual person linking dataset . the proposed sub-tasks are validated on the WIKIPerson dataset based upon the proposed methods .

EVGeoQA: Benchmarking LLMs on Dynamic, Multi-Objective Geo-Spatial Exploration (2026.findings-acl)

Copied to clipboard

Jianfei Wu, Zhichun Wang, Zhensheng Wang, Zhiyu He

Challenge:	Existing geo-spatial question answering benchmarks focus on static retrieval, failing to capture the complexity of real-world planning that involves dynamic user locations and compound constraints.
Approach:	They propose a new benchmark for Large Language Models that integrates location-anchored and dual-objective queries with a user's real-time coordinates.
Outcome:	The proposed model can summarize historical exploration trajectories to enhance exploration efficiency.

Non-Parametric Adaptation for Neural Machine Translation (N19-1)

Copied to clipboard

Ankur Bapna, Orhan Firat

Machine Translation

Challenge:	Neural Networks trained with gradient descent are susceptible to catastrophic forgetting due to parameter shift during the training process.
Approach:	They propose a semi-parametric approach that relies on local phrase level similarities to retrieve neighboring phrases that are useful for translation even when overall sentence similarity is low.
Outcome:	The proposed approach performs well on a heterogeneous dataset with WMT, IWSLT, JRC-Acquis and OpenSubtitles.

GraPPI: A Retrieve-Divide-Solve GraphRAG Framework for Large-scale Protein-protein Interaction Exploration (2025.findings-naacl)

Copied to clipboard

Ziwen Li, Xiang Chen, Youngseung Jeon

LayoutPointer: A Spatial-Context Adaptive Pointer Network for Visual Information Extraction (2024.naacl-long)

Challenge:	Large Language Models and Retrieval-Augmented Generation frameworks have accelerated drug discovery, but integrating models into workflows remains challenging.
Approach:	They propose a large-scale knowledge graph-based retrieve-divide-solve agent pipeline RAG framework to support large-level PPI signaling pathway exploration.
Outcome:	The proposed framework is based on large-scale knowledge graphs and can be used to analyze protein-protein interactions.

Copied to clipboard

Huang Siyuan, Yongping Xiong, Wu Guibin

Learning to Decompose and Organize Complex Tasks (2021.naacl-main)

Challenge:	Existing models inadequately utilize spatial information of entities, causing incorrectly linking spatially distant entities.
Approach:	They propose a Spatial-Context Adaptive Pointer Network to restore semantic order among entities . they propose XFUND-based tail-to-head pointer to restore the semantic order .
Outcome:	The proposed method outperforms existing state-of-the-art methods in F1 scores for RE tasks.

Copied to clipboard

Yi Zhang, Sujay Kumar Jauhar, Julia Kiseleva, Ryen White, Dan Roth

Structured Data in NLP

Challenge:	Using a novel end-to-end pipeline, we propose a solution that consumes a complex task and induces 'dependency graphs' from unstructured text to represent sub-tasks and their relationships.
Approach:	They propose a pipeline that consumes a complex task and induces 'dependency graphs' from unstructured text to represent sub-tasks and their relationships.
Outcome:	The proposed pipeline outperforms state-of-the-art graph induction pipelines in a dataset of complex tasks with their sub-task graphs.

A Neural Transition-based Joint Model for Disease Named Entity Recognition and Normalization (2021.acl-long)

Copied to clipboard

Zongcheng Ji, Tian Xia, Mei Han, Jing Xiao

Deep Natural Language Feature Learning for Interpretable Prediction (2023.emnlp-main)

Challenge:	Existing models for disease recognition and normalization ignore text surface form of each candidate concept, causing boundary inconsistency.
Approach:	They propose a neural transition-based joint model to normalize disease entities from biomedical text.
Outcome:	The proposed model improves on two publicly available datasets.

Copied to clipboard

Felipe Urrutia, Cristian Calderon, Valentin Barriere

Making Flexible Use of Subtasks: A Multiplex Interaction Network for Unified Aspect-based Sentiment Analysis (2021.findings-acl)

Challenge:	Using a small transformer language model, we can break down a complex task into a set of intermediary easier sub-tasks.
Approach:	They propose a method to break down a main task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task.
Outcome:	The proposed method breaks down a complex task into a set of easier sub-tasks, which are formulated in natural language as binary questions related to the final target task.

Copied to clipboard

Guoxin Yu, Xiang Ao, Ling Luo, Min Yang, Xiaofei Sun, Jiwei Li, Qing He

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

Challenge:	Existing studies aim to integrate multiple sub-tasks into a unified ABSA model but suffer from major disadvantages .
Approach:	They propose a multi-task learning approach to make use of sub-tasks for a unified ABSA.
Outcome:	The proposed model can work well when some sub-tasks are absent, and the interactive relations among subtasks not adequate.

Copied to clipboard

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

Information Retrieval

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.

ADaPT: As-Needed Decomposition and Planning with Language Models (2024.findings-naacl)

Copied to clipboard

Archiki Prasad, Alexander Koller, Mareike Hartmann, Peter Clark, Ashish Sabharwal, Mohit Bansal, Tushar Khot

Automatic rule generation for time expression normalization (2021.findings-emnlp)

Challenge:	Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment.
Approach:	They propose an approach that explicitly plans and decomposes complex sub-tasks when the LLM is unable to execute them.
Outcome:	The proposed approach significantly outperforms established strong baselines, achieving success rates up to 28.3% higher in ALFWorld, 27% in WebShop, and 33% in TextCraft.

Copied to clipboard

Wentao Ding, Jianhao Chen, Jinmao Li, Yuzhong Qu

Challenge:	Existing SOTA methods for normalization rely on expert-designed rules or grammars . current methods are domain sensitive and not sufficient on emerging corpora .
Approach:	They propose a method that generates normalization rules from annotated data without expert intervention.
Outcome:	The proposed method surpasses existing rule-based methods on the Tweets benchmark and on the TempEval-3 benchmark.

From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis (2024.emnlp-main)

Copied to clipboard

Chuanqi Cheng, Jian Guan, Wei Wu, Rui Yan

DoT: An efficient Double Transformer for NLP tasks with tables (2021.findings-acl)

Challenge:	Existing models consisting of multiple steps of visual and language processing are limited in the visual and visual processing community . a visual reasoner is a plug-and-play approach that can be used to improve VLMs' reasoning abilities.
Approach:	They propose a least-to-most visual reasoning paradigm that divides a question into sub-questions and invokes external tools for resolving sub-questions.
Outcome:	The proposed method can improve four VLMs on four VQA benchmarks.

Copied to clipboard

Syrine Krichene, Thomas Müller, Julian Eisenschlos

Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once? (2024.acl-long)

Challenge:	Recent studies have shown that transformer-based approaches to NLP tasks are slow and require computational and memory costs.
Approach:	They propose a transformer-based model that decomposes a problem into two sub-tasks and a pruning transformer that takes as input the pruning scores.
Outcome:	The proposed model improves training and inference time by at least 50% for a small drop in accuracy and also enables the model to maintain similar accuracy as slower baseline models.

Copied to clipboard

Guijin Son, SangWon Baek, Sangdae Nam, Ilgyun Jeong, Seungone Kim

Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System (2022.acl-long)

Challenge:	Large language models (LLMs) are typically trained to follow a single instruction per inference call.
Approach:	They introduce a benchmark to evaluate Large language models' ability to follow one instruction per inference call.
Outcome:	The proposed model reduces the total inference time by 1.46 times in average since it does not require multiple inference calls.

Copied to clipboard

Yixuan Su, Lei Shu, Elman Mansimov, Arshit Gupta, Deng Cai, Yi-An Lai, Yi Zhang

Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification (2023.findings-acl)

Challenge:	Existing pre-trained language models often form a cascaded generation problem . this can lead to error accumulation across different sub-tasks and greater data annotation overhead.
Approach:	They propose a plug-and-play model for task-oriented dialogue that learns primary TOD task completion skills from heterogeneous dialog corpora.
Outcome:	The proposed model learns primary TOD task completion skills from heterogeneous dialog corpora.

Copied to clipboard

Seongmin Park, Kyungho Kim, Jihwa Lee

Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks (2025.findings-acl)

Challenge:	Existing methods for text classification with extremely weak supervision impose stricter supervision constraints than those under regular weak supervision.
Approach:	They propose a framework that creates weak labels by leveraging recent developments in zero-shot text classification.
Outcome:	The proposed framework outperforms existing methods on weak labels generated by weakly supervise classification.

Copied to clipboard

Yuanjie Lyu, Chao Zhang, Yuhao Chen, Yong Chen, Tong Xu

Analyzing Key Factors Influencing Emotion Prediction Performance of VLLMs in Conversational Contexts (2024.emnlp-main)

Challenge:	Recent advances in "Chain of Models" approach increase resource demands as each model must be deployed separately.
Approach:	They propose a prompt-tuning method that enables models to share hidden states . they modify input and attention masks during training to eliminate redundant forward passes .
Outcome:	Empirical results show that FTHSS matches the performance of traditional model chains while improving inference efficiency.

Copied to clipboard

Jaewook Lee, Yeajin Jang, Hongjin Kim, Woojin Lee, Harksoo Kim

Natural Language Interfaces

Challenge:	Recent studies show that large language models and vision large language model (VLLMs) possess EI and the ability to understand emotional stimuli in the form of text and images.
Approach:	They analyze the key elements affecting the emotion prediction performance of VLLMs in conversational contexts.
Outcome:	The proposed model performance was compared with other models in a conversational context.

SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition (2025.acl-long)

Copied to clipboard

Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Junhao Huang, Conghui He, Dahua Lin, Jiaqi Wang

Towards Topic-Guided Conversational Recommender System (2020.coling-main)

Challenge:	Creating lyrics and melodies in symbolic format requires expert knowledge of melody and an advanced understanding of lyrics.
Approach:	They introduce SongComposer, a music-specialized large language model that can create symbolic lyrics and melodies following instructions.
Outcome:	The proposed model outperforms existing models in symbolic song composition tasks.

Copied to clipboard

Kun Zhou, Yuanhang Zhou, Wayne Xin Zhao, Xiaoke Wang, Ji-Rong Wen

Dialogue Systems & Conversational Agents

Challenge:	Existing CRS datasets focus on immediate requests from users, while lack proactive guidance to the recommendation scenario.
Approach:	They propose a topic-guided conversational recommendation dataset . it incorporates topic threads to enforce natural semantic transitions towards the recommendation scenario .
Outcome:	The proposed approach is more reasonable and controllable than previous approaches.

Fact-Checking Complex Claims with Program-Guided Reasoning (2023.acl-long)

Copied to clipboard

Liangming Pan, Xiaobao Wu, Xinyuan Lu, Anh Tuan Luu, William Yang Wang, Min-Yen Kan, Preslav Nakov

Programming Languages in NLP

Challenge:	Fact-checking real-world claims often requires collecting multiple pieces of evidence and complex multi-step reasoning.
Approach:	They propose a novel fact-checking model that decomposes complex claims into simpler sub-tasks that can be solved using a shared library of specialized functions.
Outcome:	The proposed model outperforms seven baselines on two fact-checking datasets and has explicit output programs that benefit human debugging.

A New Task and Dataset on Detecting Attacks on Human Rights Defenders (2023.findings-acl)

Copied to clipboard

Shihao Ran, Di Lu, Aoife Cahill, Joel Tetreault, Alejandro Jaimes

Robustness in NLP

Challenge:	Existing datasets for event extraction cannot extract information from textual sources.
Approach:	They propose to use crowdsourced annotations on 500 online news articles to train and evaluate baseline models to predict annotated characteristics.
Outcome:	The proposed dataset includes crowdsourced annotations on 500 online news articles and includes fine-grained information about the type and location of attacks, as well as information about victims.

A Modular Approach for Multimodal Summarization of TV Shows (2024.acl-long)

Copied to clipboard

Louis Mahon, Mirella Lapata

Text Generation

Challenge:	In this paper, we address the task of summarizing television shows, which touches key areas in AI research.
Approach:	They propose a modular approach where separate components perform specialized sub-tasks . they propose atomic facts to measure precision and recall of generated summaries .
Outcome:	The proposed method produces higher quality summaries than comparison models on a recently released dataset.

Branch-Solve-Merge Improves Large Language Model Evaluation and Generation (2024.naacl-long)

Copied to clipboard

Swarnadeep Saha, Omer Levy, Asli Celikyilmaz, Mohit Bansal, Jason Weston, Xian Li

CIFLEX: Contextual Instruction Flow for Sub-task Execution in Multi-Turn Interactions with a Single On-Device LLM (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) are often used for multi-faceted language generation and evaluation tasks that require complex user constraints or taking into account multiple aspects and criteria.
Approach:	They propose a Large Language Model program that consists of branch, solve, and merge modules that are parameterized with specific prompts to the base LLM.
Outcome:	The proposed program improves the evaluation correctness and consistency for each LLM by up to 26%, reducing length and pairwise position biases by up 50%, and allowing LLaMA-2-chat to match or outperform GPT-4 on most domains.

Copied to clipboard

Juntae Lee, Jihwan Bang, Seunghan Yang, Simyung Chang

Responsible & Trustworthy NLP

Challenge:	Experiments show that CIFLEX significantly reduces computational costs without degrading task performance.
Approach:	They propose a new execution system for efficient sub-task handling with a single large language model.
Outcome:	Experiments show that CIFLEX significantly reduces computational costs without degrading task performance.

Self-play through Computational Runtimes improves Chart Reasoning (2025.findings-acl)

Copied to clipboard

Tautvydas Misiūnas, Hassan Mansoor, Jasper Uijlings, Oriana Riva, Victor Carbune

Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding (2020.emnlp-main)

Challenge:	Vision-language models (VLMs) achieve impressive zero-shot performance on multimodal reasoning tasks.
Approach:	They propose a self-play programming interface which leverages visual reasoning models to generate code to decompose a complex visual reasoning task in sub-tasks and use it as a tool to solve decomposed tasks.
Outcome:	The proposed approach outperforms baselines on difficult chart reasoning benchmarks.

Copied to clipboard

Jiaxin Huang, Yu Meng, Fang Guo, Heng Ji, Jiawei Han

Multilingual Neural RST Discourse Parsing (2020.coling-main)

Challenge:	Existing methods for aspect-based sentiment analysis of review text use only a few keywords describing each aspect/sentiment without using any labeled examples.
Approach:	They propose a weakly-supervised approach for aspect-based sentiment analysis which uses only a few keywords describing each aspect/sentiment without using any labeled examples.
Outcome:	The proposed method generates quality joint topics and outperforms baselines significantly on benchmark datasets.

Copied to clipboard

Zhengyuan Liu, Ke Shi, Nancy Chen

SSR: Utilizing Simplified Stance Reasoning Process for Robust Stance Detection (2022.coling-1)

Challenge:	Existing studies on text discourse parsing for English are limited due to the lack of annotated data.
Approach:	They propose to use multilingual vector representations and segment-level translation to establish a neural, cross-lingual discourse parser.
Outcome:	The proposed model achieves state-of-the-art on cross-lingual, document-level discourse parsing on all sub-tasks.

Copied to clipboard

Jianhua Yuan, Yanyan Zhao, Yanyue Lu, Bing Qin

Robustness in NLP

Challenge:	Existing methods for stance detection are task-agnostic, which fail to utilize task knowledge to better discriminate between genuine and bias features.
Approach:	They propose to incorporate stance reasoning process as task knowledge to aid in learning genuine features without using targets.
Outcome:	The proposed model achieves better performance than previous task-agnostic debiasing methods on new test sets.

ACUEval: Fine-grained Hallucination Evaluation and Correction for Abstractive Summarization (2024.findings-acl)

Copied to clipboard

David Wan, Koustuv Sinha, Srini Iyer, Asli Celikyilmaz, Mohit Bansal, Ramakanth Pasunuru

Summarization

Challenge:	Recent-proposed evaluation metrics for large language models have a preference-bias . however, such metrics often lack interpretability and only offer a single score .
Approach:	They propose a metric that leverages the power of large language models to perform two sub-tasks: decomposing summaries into atomic content units and validating them against the source document.
Outcome:	The proposed metric improves faithfulness scores on three summarization evaluation benchmarks by 3% compared to the next-best metric.

Transferring Confluent Knowledge to Argument Mining (2022.coling-1)

Copied to clipboard

João António Rodrigues, António Branco

Reasoning

Challenge:	Argument mining is a natural language processing task that seeks to obtain structured arguments from unstructured text.
Approach:	They propose to use a transfer learning methodology to assess the potential of argument mining knowledge with confluent tasks.
Outcome:	The proposed method dispenses with heavy feature and model engineering and allows for new state-of-the-art performance for its three main sub-tasks.

A Zero-Shot Claim Detection Framework Using Question Answering (2022.coling-1)

Copied to clipboard

Revanth Gangi Reddy, Sai Chetan Chinthakindi, Yi R. Fung, Kevin Small, Heng Ji

Responsible & Trustworthy NLP

Challenge:	Existing claims detection frameworks are portability to emerging events and low-resource training data settings.
Approach:	They propose a claim detection framework that leverages zero-shot Question Answering to solve sub-tasks such as topic filtering, claim object detection, and claimer detection.
Outcome:	The proposed framework outperforms baselines on the NewsClaims benchmark.

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space (2025.emnlp-main)

Copied to clipboard

Yong Zhao, Kai Xu, Zhengqiu Zhu, Yue Hu, Zhiheng Zheng, Yingfeng Chen, Yatai Ji, Chen Gao, Yong Li, Jincai Huang

Natural Language Interfaces

Challenge:	Embodied Question Answering (EQA) tasks are primarily focused on indoor environments, leaving the complexities of urban settings unexplored.
Approach:	They propose a task where an embodied agent answers open-vocabulary questions in dynamic city spaces.
Outcome:	The proposed agent achieves 60.7% of human-level answering accuracy compared to baselines . the proposed agent outperforms existing agents in open-ended city spaces .

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition (2026.findings-acl)

Copied to clipboard

Yujie Liu, Zonglin Yang, Tong Xie, Jinjie Ni, Ben Gao, Yuqiang Li, Shixiang Tang, Wanli Ouyang, Erik Cambria, Dongzhan Zhou

Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study (2025.coling-main)

Challenge:	Large language models have shown potential in assisting scientific research, yet their ability to discover high-quality research hypotheses remains unexamined due to the lack of a dedicated benchmark.
Approach:	They propose a benchmark for evaluating large language models on a sufficient set of scientific discovery sub-tasks.
Outcome:	The proposed framework extracts critical components from papers across 12 disciplines with expert validation confirming its accuracy.

Copied to clipboard

Yulin Fei, Yuhui Gao, Xingyuan Xian, Xiaojin Zhang, Tao Wu, Wei Chen

CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning (2020.acl-main)

Challenge:	a new benchmark evaluates video-based optical character recognition (Video OCR) performance of multi-modal models in videos . the benchmark aims to improve video LLMs' ability to extract text from video content . previous benchmarks have focused on video QA, but not video-related QA.
Approach:	They propose to evaluate the video OCR performance of multi-modal models in videos . they use a semi-automated approach that integrates the OCR ability of image LLMs with manual refinement .
Outcome:	The proposed benchmark includes 1,028 videos and 2,961 question-answer pairs . it integrates the OCR ability of image LLMs with manual refinement .

Copied to clipboard

Alessandro Suglia, Ioannis Konstas, Andrea Vanzo, Emanuele Bastianelli, Desmond Elliott, Stella Frank, Oliver Lemon

Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization (2023.findings-acl)

Challenge:	Approaches to Grounded Language Learning focus on a single task-based final performance measure which may not depend on desirable properties of the learned hidden representations.
Approach:	They propose an evaluation framework for Grounded Language Learning with Attributes based on three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation.
Outcome:	The proposed framework evaluates the quality of learned representations with respect to attribute grounding.

Copied to clipboard

Luyao Cheng, Siqi Zheng, Zhang Qinglin, Hui Wang, Yafeng Chen, Qian Chen

PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Models (2025.findings-emnlp)

Challenge:	Current speaker diarization systems consider only acoustic information, resulting in performance degradation when encountering adverse acustic environment.
Approach:	They propose methods to extract speaker-related information from conversational semantics in multi-party meetings.
Outcome:	The proposed method improves on AISHELL-4 and AliMeeting datasets on speakers diarization and speaker-turn detection.

Copied to clipboard

Wanru Zhuang, Wenbo Li, Zhibin Lan, Xu Han, Peng Li, Jinsong Su

Multilinguality

Challenge:	Current TIMT studies focus on providing translations for all text within an image, neglecting to provide bounding boxes and covering limited scenarios.
Approach:	They extend traditional TIMT into position-aware TIMt to support fine-grained translation . they introduce an Adaptive Image OCR Refinement Pipeline to refine results .
Outcome:	The proposed model supports fine-grained and layout-preserving translation . the experimental data highlight the scalability and generalizability of the model.

Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management (2026.acl-long)

Copied to clipboard

Weitao Ma, Xiaocheng Feng, Lei Huang, Xiachong Feng, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Bing Qin

Small LLMs Are Weak Tool Learners: A Multi-LLM Agent (2024.emnlp-main)

Challenge:	Existing approaches to memory management rely on final task performance as the primary reward, resulting in severe reward sparsity and ineffective credit assignment.
Approach:	They propose a framework for fine-grained feedback alignment using a Chunk-level step reward and Evidence-Anchored Reward Attribution to redistribute global rewards based on memory items utilized as evidence in reasoning.
Outcome:	The proposed framework outperforms baselines and supports generalization across different model configurations and backbones.

Copied to clipboard

Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan, Hehong Chen, Ji Zhang, Fei Huang

NutFrame: Frame-based Conceptual Structure Induction with LLMs (2024.lrec-main)

Challenge:	Large Language Models (LLMs) have revolutionized natural language processing with impressive capabilities, but they lack domain specificity, real-time information and face challenges in solving specialized problems.
Approach:	They propose a multi-LLM approach that decomposes the aforementioned capabilities into a planner, caller, and summarizer.
Outcome:	The proposed model outperforms existing models by demonstrating its effectiveness and advantages in tool learning.

Copied to clipboard

Shaoru Guo, Yubo Chen, Kang Liu, Ru Li, Jun Zhao

Challenge:	Existing studies focus on syntactic knowledge and world knowledge, but conceptual structure is not well-understood.
Approach:	They propose a benchmark for coNceptual structure induction based on FrameNet . they use prompts to induce conceptual structure of Framenet with LLMs .
Outcome:	The proposed model is able to induce conceptual structure of FrameNet with LLMs.

Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark (2025.acl-long)

Copied to clipboard

Rong-Cheng Tu, Zi-Ao Ma, Tian Lan, Yuehao Zhao, Heyan Huang, Xian-Ling Mao

MIBench: Evaluating Multimodal Large Language Models over Multiple Images (2024.emnlp-main)

Challenge:	Existing MLLMs rely on commercial models such as GPT-4o for evaluations, but they are not universally accessible.
Approach:	They propose a task decomposition evaluation framework based on GPT-4o to automatically construct a specialized training dataset to break down the multifaceted evaluation process into simpler sub-tasks.
Outcome:	The proposed framework outperforms the current state-of-the-art GPT-4o evaluation framework with over 4.6% improvement in Spearman and Kendall correlations with human judgments.

Copied to clipboard

Haowei Liu, Xi Zhang, Haiyang Xu, Yaya Shi, Chaoya Jiang, Ming Yan, Ji Zhang, Fei Huang, Chunfeng Yuan, Bing Li, Weiming Hu

DDO: Dual-Decision Optimization for LLM-Based Medical Consultation via Multi-Agent Collaboration (2025.emnlp-main)

Challenge:	Existing benchmarks and MLLMs focus on single-image input scenarios, leaving performance of ML models when handling multiple images underexplored.
Approach:	They propose a benchmark to evaluate fine-grained abilities of multimodal large language models in multi-image scenarios.
Outcome:	The proposed benchmark categorizes the multi-image abilities into three scenarios: MII, MKS and MIC.

Copied to clipboard

Zhihao Jia, Mingyi Jia, Junwen Duan, Jianxin Wang

Challenge:	Existing LLMs fail to capture the dual nature of medical consultation (MC) this mismatch often results in ineffective symptom inquiry and unreliable disease diagnosis.
Approach:	They propose a novel LLM-based framework that performs Dual-Decision Optimization by decoupling the two sub-tasks and optimizing them with distinct objectives through a collaborative multi-agent workflow.
Outcome:	The proposed framework outperforms existing LLM-based approaches on three real-world MC datasets and achieves competitive performance with state-of-the-art generation-based methods.

Synergetic Interaction Network with Cross-task Attention for Joint Relational Triple Extraction (2024.lrec-main)

Copied to clipboard

Da Luo, Run Lin, Qiao Liu, Yuxiang Cai, Xueyi Liu, Yanglei Gan, Rui Hou