MACRO

Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank (C18-1)

Challenge:	Existing efforts in misinformation detection focus on written text, leaving a significant gap in addressing the complexity of spoken text in video transcripts.
Approach:	They propose to annotate video transcripts in three languages and six topics using a custom annotation tool.
Outcome:	The proposed tool shows strong cross-validation performance but challenges for generalization to unseen topics.

Copied to clipboard

Xiaomin Chu, Feng Jiang, Yi Zhou, Guodong Zhou, Qiaoming Zhu

ALERT: Adapt Language Models to Reasoning Tasks (2023.acl-long)

Challenge:	Discourse parsing is a challenging task and plays a critical role in discourse analysis.
Approach:	They propose a macro discourse structure presentation schema to present the macro level discourse structure analysis.
Outcome:	The proposed corpus is based on two tasks of macro discourse structure analysis, including structure identification and nuclearity recognition.

Copied to clipboard

Ping Yu, Tianlu Wang, Olga Golovneva, Badr AlKhamissi, Siddharth Verma, Zhijing Jin, Gargi Ghosh, Mona Diab, Asli Celikyilmaz

A Theory of Unsupervised Speech Recognition (2023.acl-long)

Challenge:	Large language models have shown increasing in-context learning capabilities with scaling up the model and data sizes.
Approach:	They propose a benchmark and suite of analyses to evaluate reasoning skills of large language models.
Outcome:	The proposed model compares pre-trained and fine-tuned models on tasks that require reasoning skills to solve.

Copied to clipboard

Liming Wang, Mark Hasegawa-Johnson, Chang Yoo

Improving Factuality of Abstractive Summarization without Sacrificing Summary Quality (2023.acl-short)

Challenge:	Unsupervised speech recognition (ASR) is the problem of learning automatic speech recognition systems from unpaired speech-only and text-only corpora.
Approach:	They propose a general theoretical framework to study the properties of pasted macro ‘ASRU’/ systems based on random matrix theory and the theory of neural tangent kernels.
Outcome:	The proposed framework proves various learnability conditions and sample complexity bounds on synthetic languages with three classes of transition graphs.

Copied to clipboard

Tanay Dixit, Fei Wang, Muhao Chen

Text Generation

Challenge:	Recent studies have shown that most abstractive summarization models are unfaithful and suffer from a wide range of hallucination.
Approach:	They propose a candidate summary generation and ranking technique to improve summary factuality without sacrificing quality.
Outcome:	The proposed method shows that the model trained using the proposed method improves on factuality and similarity-based metrics without conflicting with the model.

EmoGist: Efficient In-Context Learning for Visual Emotion Understanding (2025.findings-emnlp)

Copied to clipboard

Ronald Seoh, Dan Goldwasser

Information Extraction & Text Mining

Challenge:	EmoGist is a training-free, in-context learning method for visual emotion classification . context-dependent definitions of emotion labels could allow more accurate predictions of emotions .
Approach:	They introduce EmoGist, a training-free, in-context learning method for performing visual emotion classification with LVLMs.
Outcome:	The proposed method improves micro F1 scores and macro F1 with LVLMs.

Applications of BERT Models Towards Automation of Clinical Coding in Icelandic (2024.findings-naacl)

Copied to clipboard

Haraldur Orri Hauksson, Hafsteinn Einarsson

Chinese Discourse Parsing: Model and Evaluation (2020.lrec-1)

Challenge:	Traditionally, clinical coding is manual and laborintensive task prone to human error.
Approach:	They analyze 25 years of electronic health records from the Landspitali University Hospital in Icelandic to explore the potential of using NLP for clinical coding.
Outcome:	The best-performing model achieves competitive results in micro and macro F1 scores, with label attention contributing significantly to its success.

Copied to clipboard

Lin Chuan-An, Shyh-Shiun Hung, Hen-Hsen Huang, Hsin-Hsi Chen

MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platform (2025.emnlp-main)

Challenge:	Chinese discourse parsing has not yet a consistent evaluation metric . micro vs. macro F1 scores, binary v. multiway ground truth, and left-heavy v . right-heaviness binarization are important for Chinese discourses .
Approach:	They propose a neural network model that unifies a pre-trained transformer and a CKY-like algorithm and compare it with previous models with different evaluation scenarios.
Outcome:	The proposed model outperforms the previous models with different evaluation scenarios.

Copied to clipboard

Hayoung Jung, Shravika Mittal, Ananya Aatreya, Navreet Kaur, Munmun De Choudhury, Tanu Mitra

Generate then Select: Open-ended Visual Question Answering Guided by World Knowledge (2023.findings-acl)

Challenge:	108K drug overdose deaths in 2022, according to NIDA .
Approach:	They propose a large-scale study of OUD-related myths on YouTube with clinical experts to validate 8 pervasive myths and release an expert-labeled video dataset.
Outcome:	The proposed model reduces annotation time and cost by over 76% compared to experts and full LLM labeling.

Copied to clipboard

Xingyu Fu, Sheng Zhang, Gukyeong Kwon, Pramuditha Perera, Henghui Zhu, Yuhao Zhang, Alexander Hanbo Li, William Yang Wang, Zhiguo Wang, Vittorio Castelli, Patrick Ng, Dan Roth, Bing Xiang

Complaint Identification in Social Media with Transformer Networks (2020.coling-main)

Challenge:	Open-ended Visual Question Answering (VQA) requires models to reason over visual and natural language inputs using world knowledge.
Approach:	They propose a new VQA pipeline that deploys a generate-then-select strategy guided by world knowledge for the first time.
Outcome:	The proposed pipeline expands the knowledge coverage from in-domain training data by 4.1% on OK-VQA, without additional computation cost.

Copied to clipboard

Mali Jin, Nikolaos Aletras

StoryWars: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation (2023.acl-long)

Challenge:	Existing work on identifying complaints in social media has focused on feature-based and task-specific neural network models.
Approach:	They evaluate a battery of neural models underpinned by transformer networks and combine them with linguistic information to predict complaints.
Outcome:	The proposed models outperform state-of-the-art methods on a publicly available dataset achieving a macro F1 up to 87.

Copied to clipboard

Yulun Du, Lydia Chilton

Modeling the Severity of Complaints in Social Media (2021.naacl-main)

Challenge:	Understanding and generating collaborative stories remains an underexplored area due to the lack of open-domain corpora.
Approach:	They propose to use a dataset of 40,000 collaborative stories written by 9,400 different authors from an online platform to generate a multi-task benchmark.
Outcome:	The proposed model achieves the best performance on fully-supervised, few-shot, and zero-shot scenarios while achieving the best results on the fully-supervised tasks.

Copied to clipboard

Mali Jin, Nikolaos Aletras

Linguistics & Cognitive NLP

Challenge:	Complaining is a speech act used by humans to communicate a negative mismatch between reality and expectations . recent work on modeling complaints in natural language processing (NLP) has focused on distinguishing complaints from non-complaints in social media.
Approach:	They propose to classify complaints into various severity levels based on the face-threat that the complainer is willing to undertake and their purpose.
Outcome:	The proposed model achieves 55.7 macro F1 on binary complaint classification and 88.2 macro F1.

MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling (2023.acl-long)

Copied to clipboard

Yu Song, Santiago Miret, Bang Liu

An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing (2021.emnlp-main)

Challenge:	Using publicly available materials science text data, we construct a benchmark for evaluating the performance of natural language processing (NLP) models on materials science texts.
Approach:	They propose a natural language benchmark for evaluating the performance of natural language processing (NLP) models on materials science text.
Outcome:	The proposed model outperforms BERT-based models on scientific text and a model pretrained on materials science journals.

Copied to clipboard

Yi Chen, Haiyun Jiang, Lemao Liu, Shuming Shi, Chuang Fan, Min Yang, Ruifeng Xu

ODD: A Benchmark Dataset for the Natural Language Processing Based Opioid Related Aberrant Behavior Detection (2024.naacl-long)

Challenge:	Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET) however, there is no comprehensive understanding of how to make better use of the existing information sources and how they affect the performance of ZFET.
Approach:	They propose a multi-source fusion model targeting auxiliary information from multiple sources to improve zero-shot fine-grained entity typing (ZFET)
Outcome:	The proposed model achieves 11.42% and 22.84% gains over state-of-the-art baselines on BBN and Wiki respectively with regard to macro F1 scores.

Copied to clipboard

Sunjae Kwon, Xun Wang, Weisong Liu, Emily Druhl, Minhee Sung, Joel Reisman, Wenjun Li, Robert Kerns, William Becker, Hong Yu

DPDV: Dual-Pathway and Dual-View Representation Learning for Bridging Information Asymmetry in Text-Video Retrieval (2026.acl-long)

Challenge:	Opioid related aberrant behaviors (ORABs) present novel risk factors for opioid overdose.
Approach:	They propose to use a biomedical natural language processing benchmark dataset to classify ORABs from patients’ EHR notes into nine categories: confirmed aberrant behavior, suggested aberrant behaviors, Opioids, indication, diagnosed opioid dependency, Benzodiazepines, medication changes, and Central Nervous System-related.
Outcome:	The proposed dataset outperforms two state-of-the-art models in most categories and the gains are especially higher among uncommon classes.

Copied to clipboard

Zequn Xie, Xin Liu, Fangming Feng, Boyun Zhang, Tao Jin

Visual Data in NLP

Challenge:	Existing methods for text-based person anomaly search fail to address the pose-semantic gap . asymmetric cross-modal information poses a challenge to accurately establishing retrieval relationships .
Approach:	They propose a video retrieval framework that partitions visual features into two categories based on relevance to the text query and performs effective interaction.
Outcome:	The proposed framework achieves leading retrieval performance on five benchmark datasets.

Beyond Counting Datasets: A Survey of Multilingual Dataset Construction and Necessary Resources (2022.findings-emnlp)

Copied to clipboard

Xinyan Yu, Trina Chatterjee, Akari Asai, Junjie Hu, Eunsol Choi

Multilinguality

Challenge:	Existing studies have examined the quality of labeled data in non-English languages.
Approach:	They annotate how datasets are created, input text and label sources, tools used to build them and what they study.
Outcome:	The results show that language-proficient NLP researchers' estimated availability correlates with dataset availability.

Automatic Identification and Classification of Bragging in Social Media (2022.acl-long)

Copied to clipboard

Mali Jin, Daniel Preotiuc-Pietro, A. Seza Doğruöz, Nikolaos Aletras

Text Classification

Challenge:	Bragging is a speech act employed to build a favorable self-image through positive statements about oneself.
Approach:	They propose to use tweets annotated for bragging to build a model that can predict bragging with macro F1 up to 72.42 and 35.95 for binary and multi-class bragging classification tasks respectively.
Outcome:	The proposed models predict bragging with macro F1 up to 72.42 and 35.95 in binary and multi-class classification tasks respectively.

MCDTB: A Macro-level Chinese Discourse TreeBank (C18-1)

Copied to clipboard

Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Syntactic Text Processing

Challenge:	Discourse analysis is becoming increasingly important in the field of natural language processing.
Approach:	They propose to annotate macro discourse information and additional discourse information to make annotation more objective and accurate.
Outcome:	The results show that the annotations are more objective and accurate than the previous ones.

Building a Macro Chinese Discourse Treebank (L18-1)

Copied to clipboard

Xiaomin Chu, Feng Jiang, Sheng Xu, Qiaoming Zhu

Syntactic Text Processing

Challenge:	Discourse structure analysis is an important research topic in natural language processing.
Approach:	They propose to construct a macro discourse structure framework and annotate 147 Newswire articles.
Outcome:	The proposed framework can lay the foundation for further analysis of macro discourse structure.

Zoom Out and Observe: News Environment Perception for Fake News Detection (2022.acl-long)

Copied to clipboard

Qiang Sheng, Juan Cao, Xueyao Zhang, Rundong Li, Danding Wang, Yongchun Zhu

Reasoning

Challenge:	Existing methods for fake news detection "zoom in" to verify content with knowledge sources or check readers’ replies to posts but neglect information in the external news environment where a fake news post is created and disseminated.
Approach:	They propose a framework to capture news environment signals and a module to perceive useful signals and assist final prediction.
Outcome:	The proposed framework can improve the performance of basic fake news detectors by capturing the environmental signals of news posts and analyzing the results.

Evaluating the Factual Consistency of Large Language Models Through News Summarization (2023.findings-acl)

Copied to clipboard

Derek Tam, Anisha Mascarenhas, Shiyue Zhang, Sarah Kwan, Mohit Bansal, Colin Raffel

Information Extraction & Text Mining

Challenge:	Existing LLMs generally assign a higher score to factually consistent summaries than to factualally inconsistent summary.
Approach:	They propose a benchmark to measure whether large language models prefer factually consistent continuations of inputs.
Outcome:	The proposed benchmark compares the scores an LLM assigns to a factually consistent versus a inconsistent summary for an input news article.

Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark (2023.acl-long)

Copied to clipboard

Wenjun Peng, Jingwei Yi, Fangzhao Wu, Shangxi Wu, Bin Bin Zhu, Lingjuan Lyu, Binxing Jiao, Tong Xu, Guangzhong Sun, Xing Xie

Validity Assessment of Legal Will Statements as Natural Language Inference (2022.findings-emnlp)

Challenge:	Large language models (LLMs) have demonstrated exceptional abilities in both text understanding and generation.
Approach:	They propose an Embedding Watermark method that implants backdoors on embeddings to protect copyright of large language models.
Outcome:	The proposed method protects the copyright of large language models without compromising service quality while minimizing the adverse impact on the original embeddings’ utility.

Copied to clipboard

Alice Kwak, Jacob Israelsen, Clayton Morrison, Derek Bambauer, Mihai Surdeanu

Reasoning

Challenge:	This study introduces a dataset that focuses on the validity of statements in legal wills.
Approach:	They propose a dataset that focuses on the validity of statements in legal wills.
Outcome:	The proposed model achieves 80% macro F1 and accuracy, but group accuracy is in mid 80s at best, suggesting that the models’ understanding of the task remains superficial.

ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection (2026.findings-acl)

Copied to clipboard

Benjamin Shiue-Hal Chou, Yi Zhu, Surya Koppisetti

CNER: Concept and Named Entity Recognition (2024.naacl-long)

Challenge:	Audio deepfake detection systems do not generalize well to realistic in-the-wild deepfakkes.
Approach:	They propose a novel In-Context Learning paradigm with comparison-guidance for Audio Deepfake detection framework that uses audio language models for training-free generalization to unseen deepfakes.
Outcome:	The proposed framework improves macro F1 over specialized detectors on in-the-wild datasets with up to 2 relative improvement over existing models.

Copied to clipboard

Giuliano Martinelli, Francesco Molfese, Simone Tedeschi, Alberte Fernández-Castro, Roberto Navigli

Information Extraction & Text Mining

Challenge:	Concept and Named Entity Recognition (CNER) is a new unified task that handles concepts and entities mentioned in unstructured texts seamlessly.
Approach:	They propose a new unified task that handles concepts and entities mentioned in unstructured texts seamlessly.
Outcome:	The proposed task gains +5.4 and +8 macro F1 points when performed as a unified task compared to specialized named entity and concept recognition systems.

Why Swear? Analyzing and Inferring the Intentions of Vulgar Expressions (D18-1)

Copied to clipboard

Eric Holgate, Isabel Cachola, Daniel Preoţiuc-Pietro, Junyi Jessy Li

Challenge:	Vulgar words are employed in language use for several different functions, including expressing aggression, signaling group identity or the informality of the communication.
Approach:	They present a dataset of 7,800 tweets with six categories of vulgarity in which all instances of vulgar words are annotated with one of the six categories.
Outcome:	The proposed model can predict the category of a vulgar word based on the immediate context it appears in with 67.4 macro F1 across six classes.

Open Aspect Target Sentiment Classification with Natural Language Prompts (2021.emnlp-main)

Copied to clipboard

Ronald Seoh, Ian Birle, Mrinal Tak, Haw-Shiuan Chang, Brian Pinette, Alfred Hough

Sentiment Analysis

Challenge:	Existing aspects target sentiment classification models are not trainable if annotated data are not available.
Approach:	They propose an approach that solves ATSC with natural language prompts by 24.13 accuracy points and 33.14 macro F1 points.
Outcome:	The proposed model outperforms supervised SOTA approaches under few-shot scenarios and under supervised settings, especially for few-shot cases.

PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models (2023.findings-acl)

Copied to clipboard

Zhuocheng Gong, Jiahao Liu, Qifan Wang, Yang Yang, Jingang Wang, Wei Wu, Yunsen Xian, Dongyan Zhao, Rui Yan

DB-LLM: Accurate Dual-Binarization for Efficient LLMs (2024.findings-acl)

Challenge:	Quantization is a viable solution for pre-trained language models, but most existing methods are task-specific and require customized training and quantization with a large number of trainable parameters.
Approach:	They propose a "quantize before fine-tuning" framework that allows for quantization with a large number of trainable parameters on each individual task.
Outcome:	The proposed framework is compatible with quantization-aware training and post-training quantization and corrects quantization errors.

Copied to clipboard

Hong Chen, Chengtao Lv, Liang Ding, Haotong Qin, Xiabin Zhou, Yifu Ding, Xuebo Liu, Min Zhang, Jinyang Guo, Xianglong Liu, Dacheng Tao

Green & Sustainable NLP

Challenge:	Existing methods for ultra-low bit quantization cause severe accuracy drops . a novel Dual-Binarization method is proposed for efficient Large Language Models .
Approach:	They propose a Dual-Binarization method that takes 2-bit-width and binarization into account . they propose DB-LLM, which uses a 2-bit binarized weighted model to represent weights efficiently .
Outcome:	The proposed method surpasses the current State-of-the-Art in ultra-low bit quantization and achieves 20% reduction in computational consumption compared to the SOTA method under the same bit-width.

Multi-lingual and Multi-cultural Figurative Language Understanding (2023.findings-acl)

Copied to clipboard

Anubha Kabra, Emmy Liu, Simran Khanuja, Alham Fikri Aji, Genta Winata, Samuel Cahyawijaya, Anuoluwapo Aremu, Perez Ogayo, Graham Neubig

Sentiment Analysis

Challenge:	Figures permeate human communication, but are understudied in NLP.
Approach:	They create a figurative language inference dataset for seven languages associated with a variety of cultures, using cultural and regional concepts for figurativ expressions.
Outcome:	The results show that the most common figurative expressions are found in Hindi, Indonesian, Javanese, Kannada, Sundanese, Swahili and Yoruba.

Cooking Up a Neural-based Model for Recipe Classification (2020.lrec-1)

Copied to clipboard

Elham Mohammadi, Nada Naji, Louis Marceau, Marc Queudot, Eric Charton, Leila Kosseim, Marie-Jean Meurs

Recall, Expand, and Multi-Candidate Cross-Encode: Fast and Accurate Ultra-Fine Entity Typing (2023.acl-long)

Challenge:	a dataset of cooking recipes in French is highly imbalanced due to collaborative nature of the dataset . authors propose a neural-based model to address the first task of the DEFT 2013 shared task .
Approach:	They propose a neural-based model to address the first task of the DEFT 2013 shared task . they use state-of-the-art embedding approaches and deep architectures to address imbalanced dataset .
Outcome:	The proposed model outperforms models that use only pretrained embeddings in micro and macro F1 scores.

Copied to clipboard

Chengyue Jiang, Wenyang Hui, Yong Jiang, Xiaobin Wang, Pengjun Xie, Kewei Tu

WhitenedCSE: Whitening-based Contrastive Learning of Sentence Embeddings (2023.acl-long)

Challenge:	State-of-the-art (SOTA) methods use the cross-encoder architecture to concatenate a mention (and its context) with each type and feed it into a pretrained language model (PLM) to score their relevance.
Approach:	They propose to perform entity typing in a recall-expand-filter manner and use a novel model to encode and score all these K candidates in one forward pass.
Outcome:	The proposed method is thousands of times faster than the CE-based architecture and is very efficient in fine-grained (130 types) and coarse-grain (9 types) entity typing.

Copied to clipboard

Wenjie Zhuo, Yifan Sun, Xiaohan Wang, Linchao Zhu, Yi Yang

ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails (2025.findings-acl)

Challenge:	Extensive experiments on seven semantic textual similarity tasks show our method achieves consistent improvement over the contrastive learning baseline and sets new states of the art.
Approach:	They propose a whitening-based contrastive learning method for sentence embedding learning which combines contrastive and shuffled group whitening.
Outcome:	The proposed method achieves better alignment and uniformity on seven semantic textual similarity tasks.

Copied to clipboard

Xiaofei Wen, Wenxuan Zhou, Wenjie Jacky Mo, Muhao Chen

Text Classification

Challenge:	Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety violations.
Approach:	They propose a critique-augmented guardrail model that distills knowledge from high-capacity LLMs by generating structured critiques alongside safety labels.
Outcome:	The proposed model outperforms existing guardrail models on multiple safety benchmarks and achieves the highest average F1 and AUPRC.

AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation (2026.acl-long)

Copied to clipboard

Nicolas Bougie, Gian Maria Marconi, Xiaotong Ye, Narimawa Watanabe

Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism Detection (2025.acl-long)

Challenge:	Existing evaluation practices for recommender systems rely on few-shot prompting and offline metrics are often misaligned with online behavior.
Approach:	They propose a framework that learns world-model-driven agents from human interactions.
Outcome:	The proposed framework enables agents to express rich preferences and feedback in natural language and interact with recommender systems in a simulation.

Copied to clipboard

Sahrish Khan, Arshad Jhumka, Gabriele Pergola

Responsible & Trustworthy NLP

Challenge:	Existing tools for sexism detection fail to capture subtle distinctions within sexist content, limiting their practical applicability.
Approach:	They propose two techniques to address class imbalance and nuanced nature of sexist language . definition-based data augmentation leverages category-specific definitions to generate semantically-aligned examples .
Outcome:	The proposed techniques improve accuracy across all tasks and improve reliability.

Reward Generalization in RLHF: A Topological Perspective (2025.findings-acl)

Copied to clipboard

Tianyi Alex Qiu, Fanzhi Zeng, Jiaming Ji, Dong Yan, Kaile Wang, Jiayi Zhou, Yang Han, Josef Dai, Xuehai Pan, Yaodong Yang

Challenge:	Existing alignment methods share a common topology of information flow, but their alternatives have not been thoroughly explored.
Approach:	They propose a theory of reward generalization in reinforcement learning from human feedback . they propose induced Bayesian networks to model the impact of dataset topologies on reward generalisation .
Outcome:	The proposed method achieves an average win rate of 65% on three NLP tasks.

Context Minimization for Resource-Constrained Text Classification: Optimizing Performance-Efficiency Trade-offs through Linguistic Features (2025.findings-emnlp)

Copied to clipboard

Nahid Hossain, Md Faisal Kabir

Information Retrieval

Challenge:	Pretrained language models have transformed text classification, but their computational demands often render them impractical for resource-constrained settings.
Approach:	They propose a linguistically-grounded framework for context minimization that leverages theme-rheme structure to preserve critical classification signals while reducing input complexity.
Outcome:	The proposed framework preserves critical classification signals while reducing input complexity.

SSP: Self-Supervised Post-training for Conversational Search (2023.findings-acl)

Copied to clipboard

Quan Tu, Shen Gao, Xiaolong Wu, Zhao Cao, Ji-Rong Wen, Rui Yan

Dialogue Systems & Conversational Agents

Challenge:	Existing methods to search for information are limited by data scarcity and lack contextual semantic understanding.
Approach:	They propose a new post-training paradigm with three self-supervised tasks to initialize the conversational search model to enhance dialogue structure and contextual semantic understanding.
Outcome:	The proposed method can initialize the conversational search model to enhance dialogue structure and contextual semantic understanding.

Decouple knowledge from paramters for plug-and-play language modeling (2023.findings-acl)

Copied to clipboard

Xin Cheng, Yankai Lin, Xiuying Chen, Dongyan Zhao, Rui Yan

DMIN: A Discourse-specific Multi-granularity Integration Network for Conversational Aspect-based Sentiment Quadruple Analysis (2024.findings-acl)

Challenge:	Pre-trained language models (PLMs) have made impressive results in a wide range of NLP tasks.
Approach:	They propose a pre-training model with editable and scalable key-value memory and leverage knowledge in an explainable manner by knowledge retrieval in the pasted macro ‘MEMORY’.
Outcome:	The proposed model decouples the knowledge storage from model parameters with an editable and scalable key-value memory and leverages knowledge in an explainable manner by knowledge retrieval in the pasted macro ‘MEMORY’.

Copied to clipboard

Peijie Huang, Xisheng Xiao, Yuhong Xu, Jiawei Chen

Sentiment Analysis

Challenge:	Existing studies focus on enhancing token-level interactions, but lack sufficient modeling of discourse structure information.
Approach:	They propose to use a discourse structure called "thread" to enhance token interaction among different utterances.
Outcome:	The proposed model achieves state-of-the-art on two datasets.

CAMO: An Agentic Framework for Automated Causal Discovery from Micro Behaviors to Macro Emergence in LLM Agent Simulations (2026.findings-acl)

Copied to clipboard

Xiangning Yu, Yuwei Guo, Yuqi Hou, Xiao Xue, Qun Ma

Challenge:	LLM-empowered agent simulations generate rich, adaptive, and often nonlinear interaction patterns.
Approach:	They propose an automated Causal discovery framework for LLM agent simulations that converts mechanistic hypotheses into computable factors and learns a compact causal representation centered on an emergent target.
Outcome:	Experiments across four emergent settings demonstrate the promise of CAMO.

TACO – Twitter Arguments from COnversations (2024.lrec-main)

Copied to clipboard

Marc Feger, Stefan Dietze

Dialogue Systems & Conversational Agents

Challenge:	Argument mining aims to identify the structural elements of arguments, denoted as information and inference, in online discourses.
Approach:	They propose to use Twitter Arguments to identify structural elements of arguments, denoted as information and inference, in a dataset that uses 1,814 tweets and an annotation framework that incorporates definitions from the Cambridge Dictionary to define and identify argument components.
Outcome:	The proposed dataset identifies arguments on Twitter and achieves an 85.06% macro F1 score in detecting arguments.

Large Language Models Require Curated Context for Reliable Political Fact-Checking—Even with Reasoning and Web Search (2026.findings-acl)

Copied to clipboard

Matthew R. DeVerna, Kai-Cheng Yang, Harry Yaojun Yan, Filippo Menczer

PlanningArena: A Modular Benchmark for Multidimensional Evaluation of Planning and Tool Learning (2025.acl-long)

Challenge:	Large language models (LLMs) have raised hopes for automated end-to-end fact-checking, but prior studies report mixed results.
Approach:	They evaluate 15 large language models on 6,000 claims fact-checked by PolitiFact . standard models perform poorly, reasoning offers minimal benefits, and web search provides only moderate gains .
Outcome:	The models predict claim veracity and a curated RAG system improved macro F1 by 233% on average across model variants.

Copied to clipboard

Zihan Zheng, Tianle Cui, Chuwen Xie, Jiahui Pan, Qianglong Chen, Lewei He

Reasoning

Challenge:	Recent studies have shown that LLMs can be significantly improved by integrating external tools.
Approach:	They propose a framework that integrates external tools into large language models to evaluate their ability to generate action plans.
Outcome:	The proposed framework evaluates the ability of large language models to generate action plans and generate action plan templates.

Sparse Autoencoder Features for Classifications and Transferability (2025.emnlp-main)

Copied to clipboard

Jack Gallifant, Shan Chen, Kuleen Sasse, Hugo Aerts, Thomas Hartvigsen, Danielle Bitterman