FILTERING

EdTec-QBuilder: A Semantic Retrieval Tool for Assembling Vocational Training Exams in German Language (2024.naacl-demo)

Challenge:	a lack of cross-lingual training data in emergent domains makes it difficult to train on emerging domains.
Approach:	They propose a cross-lingual open-retrieval question answering system for COVID-19 . their system adopts a corpus of scientific articles to ensure that retrieved documents are reliable.
Outcome:	The proposed system outperforms BM25 baselines in cross-lingual settings.

Copied to clipboard

Alonso Palomino, Andreas Fischer, Jakub Kuzilek, Jarek Nitsch, Niels Pinkwart, Benjamin Paassen

Enhancing Content Preservation in Text Style Transfer Using Reverse Attention and Conditional Layer Normalization (2021.acl-long)

Challenge:	Existing methods to gather test items from validated item databases are under-researched, but there is little research on assembling exam items from a database of valid items.
Approach:	They propose to use semantic search to assist vocational educators in assembling exam forms by using eight retrieval strategies and 25 popular sentence similarity models.
Outcome:	The proposed tool is based on eight retrieval strategies and 25 popular pre-trained sentence similarity models.

Copied to clipboard

Dongkyu Lee, Zhiliang Tian, Lanqing Xue, Nevin L. Zhang

Examining the Utility of Self-disclosure Types for Modeling Annotators of Social Norms (2026.findings-eacl)

Challenge:	Text style transfer aims to alter the style of a sentence while preserving its content.
Approach:	They propose to remove style information at token level and fuse it to style representations using conditional layer normalization.
Outcome:	The proposed model outperforms the state-of-the-art models in terms of content preservation and fluency.

Copied to clipboard

Kieran Henderson, Kian Omoomi, Vasudha Varadarajan, Allison Lahnala, Charles Welch

LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models (2025.emnlp-industry)

Challenge:	Recent work has explored the use of personal information in the form of persona sentences to improve modeling of individual characteristics and prediction of annotator labels for subjective tasks.
Approach:	They categorize self-disclosures and use them to build annotator models for predicting judgments of social norms by analyzing comments from original post.
Outcome:	The proposed model improves the model and its ability to predict annotator labels.

Copied to clipboard

Yungi Kim, Hyunsoo Ha, Seonghoon Yang, Sukyung Lee, Jihoo Kim, Chanjun Park

To Paraphrase or Not: Efficient Comment Detoxification with Unsupervised Detoxifiability Discrimination (2026.eacl-short)

Challenge:	Creating high-quality datasets for large language models often relies on resource-intensive, GPU-accelerated models for quality filtering, making the process time-consuming and costly.
Approach:	They propose a framework that operates entirely on CPUs to streamline the processes of dataset extraction, filtering, and curation.
Outcome:	The proposed framework reduces preparation time and costs while maintaining high data quality while enhancing the applicability of LLMs in specialized contexts.

Copied to clipboard

Jing Ke, Zheyong Xie, Shaosheng Cao, Tong Xu, Enhong Chen

Toward Diverse Precondition Generation (2021.starsem-1)

Challenge:	Existing methods for detoxification of toxic comments are limited by overcorrection and data scarcity . experimental results show that DID outperforms existing methods on academic data and an industrial platform .
Approach:	They propose a paradigm that adaptively conducts filtering or paraphrasing for each toxic comment based on its detoxifiability . they propose 'detoxifiabilities-aware detoxification' that can be trained to filter or paraphrase toxic comments based upon their detoxifikatability based only on detoxificable comments .
Outcome:	Experimental results show that DID outperforms existing methods on academic and industrial data.

Copied to clipboard

Heeyoung Kwon, Nathanael Chambers, Niranjan Balasubramanian

Challenge:	a typical goal for language understanding is to logically connect the events of a discourse, but connective events are not described due to their commonsense nature.
Approach:	They propose a system that generates unique and diverse preconditions by using an event sampler, candidate generator, and post-processor.
Outcome:	The proposed system can generate unique and diverse preconditions without training on diverse examples.

KT-Speech-Crawler: Automatic Dataset Construction for Speech Recognition from YouTube Videos (D18-2)

Copied to clipboard

Egor Lakomkin, Sven Magg, Cornelius Weber, Stefan Wermter

Selecting Machine-Translated Data for Quick Bootstrapping of a Natural Language Understanding System (N18-3)

Challenge:	KT-Speech-Crawler is an automated dataset building tool for speech recognition.
Approach:	They propose an approach for automatic dataset construction for speech recognition by crawling YouTube videos.
Outcome:	The proposed algorithm can obtain 150 hours of transcribed speech in a day with an estimated 3.5% word error rate.

Copied to clipboard

Judith Gaspers, Penny Karanasou, Rajen Chatterjee

Machine Translation

Challenge:	In recent years, there has been growing interest in voice-controlled devices, such as Amazon Alexa or Google home.
Approach:	They investigate the use of Machine Translation to bootstrap a natural language understanding system for a new language for the use case of a large-scale voice-controlled device.
Outcome:	The proposed method reduces the time and cost of getting annotated corpus for a new language while still providing a large enough coverage of user requests.

Sanskrit Voyager: Unified Web Platform for Interactive Reading and Linguistic Analysis of Sanskrit Texts (2025.emnlp-demos)

Copied to clipboard

Giacomo De Luca, Danilo Croce, Roberto Basili

Challenge:	Sanskrit Voyager enables users to search for words and phrases as they actually appear in texts . evaluation shows over 92% parsing accuracy on complex compounds compared to BuddhaNexus .
Approach:	Sanskrit Voyager is a web application for searching, reading and analyzing the Sanskrt literary corpus.
Outcome:	Sanskrit Voyager is a web application for searching, reading, and analyzing the Sanskrt literary corpus.

CompUGE-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering (2025.coling-demos)

Copied to clipboard

Ahmad Shallouf, Irina Nikishina, Chris Biemann

Literary Evidence Retrieval via Long-Context Language Models (2025.acl-short)

Challenge:	Comparative Question Answering systems help users make informed decisions by generating comparative information.
Approach:	They propose a comprehensive benchmark designed to evaluate Comparative Question Answering systems.
Outcome:	The proposed benchmark is available on HuggingFace Spaces . it unifies multiple datasets and provides a robust evaluation platform .

Copied to clipboard

Katherine Thai, Mohit Iyyer

Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement (2023.eacl-main)

Challenge:	a recent study shows that long-context language models can exceed human expert performance in literary analysis . despite their speed and apparent accuracy, even the strongest models struggle with nuanced literary signals and overgeneration.
Approach:	They propose a task where a model is given an entire text of a book and a literary criticism with a missing quotation from that work and asked to generate the missing quote.
Outcome:	The proposed model outperforms open-weight models in literary evidence retrieval tasks.

Copied to clipboard

Soyeong Jeong, Jinheon Baek, Sung Ju Hwang, Jong Park

R2A-TLS: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Integration (2025.findings-emnlp)

Challenge:	Existing work uses predicted answers instead of unavailable ground-truth answers as conversation history for inference.
Approach:	They propose to filter out inaccurate answers in the conversation history without making any architectural changes to the model.
Outcome:	The proposed models outperform baselines on two standard ConvQA datasets.

Copied to clipboard

Chenlong Bao, Shijie Li, Minghao Hu, Ming Qiao, Bin Zhang, Jin-Tao Tang, Shasha Li, Ting Wang

Deep Learning against COVID-19: Respiratory Insufficiency Detection in Brazilian Portuguese Speech (2021.findings-acl)

Challenge:	Existing methods struggle to capture coherent event narratives due to fragmented descriptions . Existing approaches accumulate noise through iterative retrieval strategies that lack relevance evaluation.
Approach:	They propose a reflective retrieval-augmented timeline summarization with Causal-Semantic Intergration approach for open-domain timeline summarizing .
Outcome:	The proposed approach outperforms the best prior published approaches.

Copied to clipboard

Edresson Casanova, Lucas Gris, Augusto Camargo, Daniel da Silva, Murilo Gazzola, Ester Sabino, Anna Levin, Arnaldo Candido Jr, Sandra Aluisio, Marcelo Finger

Speech & Audio in NLP

Challenge:	Respiratory insufficiency is a symptom that requires hospitalization . a dataset was created to analyze COVID-19 patients and a control group .
Approach:	They used a dataset to build a Convolution Neural Network to detect respiratory insufficiency using MFCC representations.
Outcome:	The proposed method achieves 91.66% accuracy under real-life environmental conditions.

Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition (2026.findings-acl)

Copied to clipboard

Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su, Tzu-Quan Lin, Shang-Tse Chen, Yun-Nung Chen, Hung-yi Lee

Accurate Training of Web-based Question Answering Systems with Feedback from Ranked Users (2023.acl-industry)

Challenge:	ASR models can be used to correct accent-specific errors without ground truth . pseudo-labels inherit the teacher model's systematic biases, authors say .
Approach:	They propose a parameter-space correction technique that captures pseudo-label biases . they propose achieving up to 35% relative WER reduction on a pseudo-labeled target model .
Outcome:	The proposed model achieves 35% relative WER reduction on ten African accents with the Whisper tiny model.

Copied to clipboard

Liang Wang, Ivano Lauriola, Alessandro Moschitti

NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis (2022.lrec-1)

Challenge:	Recent work shows that large-scale annotated datasets are essential for training state-of-the-art Question Answering (QA) models.
Approach:	They use large-scale annotated datasets to train question answering models . they use feedback data collected from deployed QA systems to provide cheaper supervision .
Outcome:	The proposed model improves on the large scale annotated datasets from QA systems . the proposed model can be easily supervised on large-scale unlabeled web data .

Copied to clipboard

Shamsuddeen Hassan Muhammad, David Ifeoluwa Adelani, Sebastian Ruder, Ibrahim Sa’id Ahmad, Idris Abdulmumin, Bello Shehu Bello, Monojit Choudhury, Chris Chinenye Emezue, Saheed Salahudeen Abdullahi, Anuoluwapo Aremu, Alípio Jorge, Pavel Brazdil

Sentiment Analysis

Challenge:	Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data.
Approach:	They propose a large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria.
Outcome:	The proposed dataset includes 30,000 tweets and a significant fraction of code-mixed tweets.

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search (2025.emnlp-main)

Copied to clipboard

Yiming Jia, Jiachen Li, Xiang Yue, Bo Li, Ping Nie, Kai Zou, Wenhu Chen

MICE: Mixture of Image Captioning Experts Augmented e-Commerce Product Attribute Value Extraction (2025.acl-industry)

Challenge:	Existing vision-language models struggle with reasoning-focused tasks due to the lack of high-quality training data.
Approach:	They propose a new approach that leverages search engines to create a multimodal multimodal dataset . they use a set of 30,000 seed images to extract HTML data from 700K unique URLs .
Outcome:	The proposed model achieves the best known performance on MMMU-Pro (40.7), MathVerse (42.6), and DynaMath (55.7).

Copied to clipboard

Jiaying Gong, Hongda Shen, Janet Jenq

Mining Word Boundaries from Speech-Text Parallel Data for Cross-domain Chinese Word Segmentation (2025.coling-main)

Challenge:	Existing visual attribute value extraction methods rely on product images and textual information, which can be ambiguous, inaccurate, or unavailable.
Approach:	They propose a framework that leverages a curated pool of image captioning models to generate accurate captions from product images.
Outcome:	The proposed framework significantly improves state-of-the-art large multimodal models in zero-shot and fine-tuning settings.

Copied to clipboard

Xuebin Wang, Lei Zhang, Zhenghua Li, Shilin Zhou, Chen Gong, Yang Hou

Unsupervised Adaptation of Question Answering Systems via Generative Self-training (2020.emnlp-main)

Challenge:	Recent studies on Chinese Word Segmentation (CWS) have focused on the cross-domain scenarios, but there is a high cost of manually annotating high-quality data.
Approach:	They propose to explicitly mine word boundaries from parallel speech-text data by using the Montreal Forced Aligner toolkit to perform character-level alignment on speech- text data.
Outcome:	The proposed approach is based on character-level alignment on speech-text data and a robust complete-then-train (CTT) strategy.

Copied to clipboard

Steven Rennie, Etienne Marcheret, Neil Mallinar, David Nahamoo, Vaibhava Goel

ITERATE: Image-Text Enhancement, Retrieval, and Alignment for Transmodal Evolution with LLMs (2025.coling-main)

Challenge:	Supervised self-training methods have transformed applied machine learning . however, adapting to target data has received little attention .
Approach:	They propose a method to generate synthetic QA pairs for unsupervised self adaptation . they use massive amounts of data to simulate self-supervised tasks .
Outcome:	The proposed method improves QA systems significantly by using less data and training computation than existing augmentation approaches.

Copied to clipboard

Chenhan Fu, Guoming Wang, Juncheng Li, Wenqiao Zhang, Rongxing Lu, Siliang Tang

Emotion-Cause Pair Extraction: A New Task to Emotion Analysis in Texts (P19-1)

Challenge:	a new framework for visual annotation of text-based questions is needed to improve performance . obtaining corresponding images through manual annotation often entails high costs .
Approach:	They propose a framework that uses visual modality to enhance the performance of text-based questions.
Outcome:	The proposed framework improves the alignment between text and images by using search engines or web scraping techniques.

Copied to clipboard

Rui Xia, Zixiang Ding

BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation (2022.findings-naacl)

Challenge:	Emotion cause extraction (ECE) aims at extracting potential causes behind certain emotions in text.
Approach:	They propose a 2-step task to extract potential pairs of emotions and corresponding causes in a document.
Outcome:	The proposed task is based on a benchmark emotion cause corpus.

Copied to clipboard

Eleftheria Briakou, Sida Wang, Luke Zettlemoyer, Marjan Ghazvininejad

Uncertainty-Aware Bootstrap Learning for Joint Extraction on Distantly-Supervised Data (2023.acl-short)

Challenge:	Existing methods to improve Neural Machine Translation (NMT) for lowresource languages are often trained on heuristically aligned or automatically mined data.
Approach:	They propose to filter out imperfect translations that yield unreliable training signals for Neural Machine Translation (NMT) instead, they propose to refine mined bitexts by automatic editing .
Outcome:	The proposed method improves the quality of mined bitexts for low-resource languages by up to 8 BLEU points.

Copied to clipboard

Yufei Li, Xiao Yu, Yanchi Liu, Haifeng Chen, Cong Liu

Entity Decomposition with Filtering: A Zero-Shot Clinical Named Entity Recognition Framework (2025.naacl-long)

Challenge:	Existing approaches to extract entity pairs and their relations from labeled data are noisy and expensive.
Approach:	They propose a bootstrap learning approach that is motivated by intuition that the higher the uncertainty of an instance, the more likely the model confidence is inconsistent with the ground truths.
Outcome:	The proposed method outperforms baselines and related methods on two large datasets.

Copied to clipboard

Reza Averly, Xia Ning

Named Entity Recognition

Challenge:	Recent studies have demonstrated that large language models (LLMs) can perform in named entity recognition tasks.
Approach:	They propose a framework for clinical named entity recognition that decomposes the entity recognition task into several retrievals of sub-types and then filters them.
Outcome:	The proposed framework improves on the clinical named entity recognition task.

MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs (2024.acl-long)

Copied to clipboard

Zimu Lu, Aojun Zhou, Houxing Ren, Ke Wang, Weikang Shi, Junting Pan, Mingjie Zhan, Hongsheng Li

Reasoning

Challenge:	Existing models have demonstrated outstanding capabilities in mathematical reasoning, but there is a performance gap between open-source models and closed-source ones.
Approach:	They propose a method for generating diverse and reliable math problems by leveraging the ground-truth solutions of the seed data.
Outcome:	The proposed model outperforms open-source models across five representative mathematical reasoning datasets.

A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages (2020.acl-main)

Copied to clipboard

Pedro Javier Ortiz Suárez, Laurent Romary, Benoît Sagot

Performance and Risk Trade-offs for Multi-word Text Prediction at Scale (2023.findings-eacl)

Challenge:	a recent trend in neural NLP has been the introduction of feature-based and fine-tuning methods . we train monolingual contextualized word embeddings for five mid-resource languages .
Approach:	They use common Crawl corpus to train monolingual contextualized word embeddings . they compare performance of OSCAR-based and Wikipedia-based embeddables on part-of-speech tasks .
Outcome:	The results show that OSCAR-based and Wikipedia-based embeddings perform better than Wikipedia-style embedders on part-of-speech tagging and parsing tasks.

Copied to clipboard

Aniket Vashishtha, S Sai Prasad, Payal Bajaj, Vishrav Chaudhary, Kate Cook, Sandipan Dandapat, Sunayana Sitaram, Monojit Choudhury

Challenge:	Large Language Models (LLMs) generate ethically inappropriate texts even for seemingly innocuous contexts.
Approach:	They propose to use large language models to detect and filter toxic content in text prediction tasks by evaluating their toxicity detection approaches against a manually crafted CheckList of harms.
Outcome:	The proposed methods are compared against a checklist of harms targeted at different groups and different levels of severity in English.

Can Language Models Laugh at YouTube Short-form Videos? (2023.emnlp-main)

Copied to clipboard

Dayoon Ko, Sangho Lee, Gunhee Kim

A Pretrainer’s Guide to Training Data: Measuring the Effects of Data Age, Domain Coverage, Quality, & Toxicity (2024.naacl-long)

Challenge:	Existing datasets that focus on verbal cues and focus on short-form funny videos focus on focusing on verbs and visual cue.
Approach:	They curate a user-generated dataset of 10K multimodal funny videos from YouTube and annotate each video with timestamps and explanations for funny moments.
Outcome:	The proposed dataset improves the ability of large language models to understand humor.

Copied to clipboard

Shayne Longpre, Gregory Yauney, Emily Reif, Katherine Lee, Adam Roberts, Barret Zoph, Denny Zhou, Jason Wei, Kevin Robinson, David Mimno, Daphne Ippolito

Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval (2022.acl-long)

Challenge:	a large number of pretraining data design practices are under-documented, authors say . authors: strong performance of modern language models depends on selfsupervised pretraining .
Approach:	They propose to pretrain models on data curated at different collection times . they find temporal shift between evaluation data and pretraining data leads to performance degradation .
Outcome:	The results validate, quantify, and expose many undocumented intuitions about text pretraining . authors say this practice has outperformed other models in the field .

Copied to clipboard

Luyu Gao, Jamie Callan

Synonymy in Bilingual Context: The CzEngClass Lexicon (C18-1)

Challenge:	Recent research shows that fine-tuning dense retrievers to realize their capacity requires carefully designed fine-cuning techniques.
Approach:	They propose a pre-training architecture that learns to condense information into the dense vector through LM pre-training and a coCondenser architecture which adds an unsupervised corpus-level contrastive loss to warm up the passage embedding space.
Outcome:	The proposed architecture reduces the need for heavy data engineering and large batch training.

Copied to clipboard

Zdeňka Urešová, Eva Fučíková, Eva Hajičová, Jan Hajič

Syntactic Text Processing

Challenge:	Existing lexical resources for semantic annotation of synonyms are lacking in computational language processing.
Approach:	They describe a bilingual lexical resource being built to investigate verbal synonymy in bilingual context and relate semantic roles common to one synonym class to verb arguments.
Outcome:	The proposed resource is based on English and Czech WordNet, FrameNet, PropBank, VerbNet (SemLink), and valency lexicons for Czech and English (PDT-Vallex, Vallex, and EngValleX).

Reinforcement Learning based Curriculum Optimization for Neural Machine Translation (N19-1)

Copied to clipboard

Gaurav Kumar, George Foster, Colin Cherry, Maxim Krikun

Machine Translation

Challenge:	a heterogeneous training dataset can vary in characteristics such as domain, translation quality, and degree of difficulty.
Approach:	They propose to use reinforcement learning to learn an optimal curriculum for NMT training . they find it can beat uniform baselines and hand-designed, state-of-the-art curricula .
Outcome:	The proposed approach beats baselines and hand-designed curricula on English-to-French datasets.

Locate and Label: A Two-stage Identifier for Nested Named Entity Recognition (2021.acl-long)

Copied to clipboard

Yongliang Shen, Xinyin Ma, Zeqi Tan, Shuai Zhang, Wen Wang, Weiming Lu

How Does Knowledge Selection Help Retrieval Augmented Generation? (2025.findings-emnlp)

Challenge:	Named entity recognition (NER) is a well-studied task in natural language processing.
Approach:	They propose a method that generates span proposals and labels them with categories . they use boundary information of entities and partially matched spans to locate them .
Outcome:	The proposed method outperforms state-of-the-art models on nested NER datasets.

Copied to clipboard

Xiangci Li, Jessica Ouyang

Entity Relation Extraction as Dependency Parsing in Visually Rich Documents (2021.emnlp-main)

Challenge:	Retrieval-augmented generation (RAG) is a powerful method for enhancing natural language generation by integrating external knowledge into a model’s output.
Approach:	They empirically analyze how knowledge selection influences downstream generation performance in RAG systems by simulating different retrieval and selection conditions through a controlled mixture of gold and distractor knowledge.
Outcome:	The proposed model is based on a controlled mixture of gold and distractor knowledge and simulated with a gold and distractors.

Copied to clipboard

Yue Zhang, Zhang Bo, Rui Wang, Junjie Cao, Chen Li, Zuyi Bao

Syntactic Text Processing

Challenge:	Existing studies on key information extraction from visually rich documents focus on labeling the text within bounding boxes, while relations between words are unexplored.
Approach:	They propose to use a dependency parsing model to extract semantic entities from visually rich documents by combining entity labeling and relation extraction tasks.
Outcome:	The proposed model achieves 65.96% F1 score on the FUNSD dataset.

Paraphrase Generation and Evaluation on Colloquial-Style Sentences (2020.lrec-1)

Copied to clipboard

Eetu Sjöblom, Mathias Creutz, Yves Scherrer

Multilingual Open Text Release 1: Public Domain News in 44 Languages (2022.lrec-1)

Challenge:	a new study investigates the quality and novelty of generated paraphrases . paraphrase models can be used for information retrieval and data mining .
Approach:	They use state-of-the-art neural machine translation models trained on the Opusparcus corpus to generate paraphrases in six languages.
Outcome:	The proposed model outperforms the existing model on human evaluation in five of the six languages.

Copied to clipboard

Chester Palen-Michel, June Kim, Constantine Lignos

Database reasoning over text (2021.acl-long)

Challenge:	a corpus of permissively licensed text is being developed in 44 languages, many of which have limited existing text resources for natural language processing.
Approach:	They propose to create a multilingual corpus containing text in 44 languages . they describe their process for collecting, filtering, and processing the data .
Outcome:	The first release of the corpus contains over 2.8 million news articles and an additional 1 million short snippets published between 2001–2022 and collected from Voice of America news websites.

Copied to clipboard

James Thorne, Majid Yazdani, Marzieh Saeidi, Fabrizio Silvestri, Sebastian Riedel, Alon Halevy

Improving Hypernymy Extraction with Distributional Semantic Classes (L18-1)

Challenge:	Existing models cannot handle database queries such as “List/Count all female athletes who were born in 20th century”.
Approach:	They propose a modular architecture to answer database-style queries over multiple spans from text and aggregate them at scale.
Outcome:	The proposed architecture scales to databases containing thousands of facts whereas current models are limited by how many facts can be encoded.

Copied to clipboard

Alexander Panchenko, Dmitry Ustalov, Stefano Faralli, Simone P. Ponzetto, Chris Biemann

EMA: An Episodic Memory Agent for Efficient and Selective Memory (2026.findings-acl)

Challenge:	Existing methods for extracting hypernyms focus on the acquisition of binary hypernies .
Approach:	They propose a distributionally-induced semantic class for extracting hypernyms . they also use distributional semantics to induce sense-aware semantic classes .
Outcome:	The proposed method improves the quality of the hypernymy extraction in terms of precision and recall.

Copied to clipboard

Hongyi Lan, Jiaqi Song, Zhengjia Zhong, Hui Li, Hong Liu, Xianming Lin, Rongrong Ji

Dialogue Systems & Conversational Agents

Challenge:	Existing memory-augmented methods often incorporate full dialog histories without filtering, resulting in information redundancy and inference latency.
Approach:	They propose a framework that abstracts conversational context into Episodic Memory Units (EMUs) they propose EMA, MemDecider and a filtering decision module to reduce noise and improve overall performance.
Outcome:	The proposed framework reduces token consumption by 11.48% while improving performance on two widely-used benchmarks.

Zero-to-Strong Generalization: Eliciting Strong Capabilities of Large Language Models Iteratively without Gold Labels (2025.coling-main)

Copied to clipboard

Chaoqun Liu, Qin Chao, Wenxuan Zhang, Xiaobao Wu, Boyang Li, Anh Tuan Luu, Lidong Bing

Exploiting Citation Knowledge in Personalised Recommendation of Recent Scientific Publications (2020.lrec-1)

Challenge:	Pre-trained language models have demonstrated remarkable performance through supervised fine-tuning or in-context learning using gold labels.
Approach:	They propose a new paradigm termed zero-to-strong generalization that prompts LLMs to annotate unlabeled data and retain high-quality labels by filtering.
Outcome:	The proposed framework outperforms pre-trained language models on extensive classification and reasoning tasks on multiple model sizes.

Copied to clipboard

Anita Khadka, Iván Cantador, Miriam Fernandez

End-to-End Emotion-Cause Pair Extraction based on Sliding Window Multi-Label Learning (2020.emnlp-main)

Challenge:	Keeping up with the most recent scientific literature is a challenge for many researchers given the continuous and increasing growth of academic publications.
Approach:	They propose to use citation knowledge to provide personalised recommendations of recent scientific publications to a particular user by capturing authors’ publication history and enriched with different forms of paper citation.
Outcome:	The proposed dataset captures authors’ publication history and is enriched with different forms of paper citation knowledge, namely citation graphs, citation positions, cited contexts, and citation types.

Copied to clipboard

Zixiang Ding, Rui Xia, Jianfei Yu

Learning to Revise References for Faithful Summarization (2022.findings-emnlp)

Challenge:	Existing methods to extract potential pairs of emotions ignore the fact that the cause and the emotion it triggers are inseparable.
Approach:	They propose two frameworks that combine multi-label learning and multi-labeled learning to extract emotion clauses . they evaluate a benchmark emotion cause corpus and find the best performance .
Outcome:	The proposed frameworks achieve the best performance among all compared systems on the ECPE task.

Copied to clipboard

Griffin Adams, Han-Chin Shing, Qing Sun, Christopher Winestock, Kathleen McKeown, Noémie Elhadad

Don’t Be Misled by Style: A Style-Adaptive Reranker for Capturing Effective Knowledge in Retrieval-Augmented Generation (2026.acl-long)

Challenge:	a recent study shows that noisy reference summaries can be detrimental to model performance.
Approach:	They propose to selectively re-write unsupported reference sentences to better reflect source data.
Outcome:	The proposed method improves reference quality while retaining all data.

Copied to clipboard

Ruwen Zhang, Bo Liu, Zhang Sheng Xiang, Yida Chen, Hantao Zhao, Ding Ding, Jiahui Jin, Jiuxin Cao

Pula: Training Large Language Models for Setswana (2025.naacl-long)

Challenge:	Existing rerankers are mainly trained on well-edited texts, but stylistic features can be misled by reranked models.
Approach:	They propose a style-augmented multi-task framework that prioritizes effective knowledge over stylistic perturbations by using an LLM to derive passage-level supervision on whether a passage helps or harms answer correctness.
Outcome:	Extensive experiments show that SARK improves generation performance across multiple LLMs under mixed-style conditions.

Copied to clipboard

Nathan Brown, Vukosi Marivate

VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation (2026.eacl-long)

Challenge:	Setswana is a Bantu language spoken by an estimated five to ten million people worldwide.
Approach:	They propose to make setswana-based models available for the first time using data available from setswa and setswegian databases.
Outcome:	The proposed models outperform GPT-4o and Gemini 1.5 Pro on English-Setswana translation tasks and achieve state-of-the-art performance on Setswanan reasoning tasks.

Copied to clipboard

Hieu Tran, Phuong-Anh Nguyen-Le, Huy Nghiem, Quang-Nhan Nguyen, Wei Ai, Marine Carpuat

RuCoLA: Russian Corpus of Linguistic Acceptability (2022.emnlp-main)

Challenge:	Existing approaches to machine translation (MT) systems degrade when faced with code-mixed text.
Approach:	They propose a system that can augment Vietnamese-English code-mixed text with iterative fine-tuning and targeted filtering.
Outcome:	The proposed framework outperforms strong back-translation baselines and improves zero-shot models by up to +11.9 points.

Copied to clipboard

Vladislav Mikhailov, Tatiana Shamardina, Max Ryabinin, Alena Pestova, Ivan Smurov, Ekaterina Artemova

Neural Topic Model with Reinforcement Learning (D19-1)

Challenge:	Recent research has focused on evaluating the grammatical knowledge of language models with acceptability judgments.
Approach:	They propose to build a corpus of linguistic acceptability in Russian using a binary LA approach.
Outcome:	The proposed set of tests shows that the most widely used language models still fall behind humans by a large margin when detecting morphological and semantic errors.

Copied to clipboard

Lin Gui, Jia Leng, Gabriele Pergola, Yu Zhou, Ruifeng Xu, Yulan He

MultiMWE: Building a Multi-lingual Multi-Word Expression (MWE) Parallel Corpora (2020.lrec-1)

Challenge:	Experimental results show superior performance on perplexity and topic coherence measures compared to state-of-the-art topic models.
Approach:	They propose to incorporate topic coherence measures as reward signals to guide the learning of a VAE-based topic model.
Outcome:	The proposed model is able to separating background words dynamically from topic words eliminating the pre-processing step of filtering infrequent and/or top frequent words, typically required for learning traditional topic models.

Copied to clipboard

Lifeng Han, Gareth Jones, Alan Smeaton

A Turkish Hate Speech Dataset and Detection System (2022.lrec-1)

Challenge:	Existing bilingual or multi-lingual MWE corpora are limited for multilingual use . only 871 pairs of English-German MWEs are available for research .
Approach:	They present a collection of bilingual and multi-lingual MWEs extracted from parallel corpora.
Outcome:	The available bilingual or multi-lingual MWE corpus is very limited . the collection is a small collection of 871 pairs of English-German MWEs .

Copied to clipboard

Fatih Beyhan, Buse Çarık, İnanç Arın, Ayşecan Terzioğlu, Berrin Yanikoglu, Reyyan Yeniterzi

EcoVerse: An Annotated Twitter Dataset for Eco-Relevance Classification, Environmental Impact Analysis, and Stance Detection (2024.lrec-main)

Challenge:	Davidson et al., 2017: hate speech is a discourse that targets a specific group based on race, gender, religion, sexual orientation, etc.
Approach:	They propose a machine learning system for automatic detection of hate speech in Turkish . they use a hate speech dataset and a dataset to collect tweets about immigrants .
Outcome:	The proposed system is able to detect hate speech in Turkish and annotate it using BERTurk.

Copied to clipboard

Francesca Grasso, Stefano Locci, Giovanni Siragusa, Luigi Di Caro

Sentiment Analysis

Challenge:	EcoVerse is an annotated English Twitter dataset of 3,023 tweets . mainstream NLP tasks dominate the scene, but environmental impacts remain unstudied .
Approach:	They propose an annotation scheme for Eco-Relevance Classification, Stance Detection and an original approach for Environmental Impact Analysis.
Outcome:	The proposed scheme produces consistent annotations of high quality . the dataset is made freely available to stimulate further research .

Multilingual Data Filtering using Synthetic Data from Large Language Models (2025.findings-emnlp)

Copied to clipboard

Jonas Waldendorf, Barry Haddow, Alexandra Birch, Mateusz Klimaszewski

Aligning LLMs with Individual Preferences via Interaction (2025.coling-main)

Challenge:	Recent studies have shown that effective filters can be created by utilising Large Language Models to synthetically label data, which is then used to train smaller neural models for filtering purposes.
Approach:	They extend this approach to languages beyond English to train neural models for filtering purposes.
Outcome:	The proposed approach is effective at filtering parallel text for translation quality and filtering for domain specificity.

Copied to clipboard

Shujin Wu, Yi R. Fung, Cheng Qian, Jeonghwan Kim, Dilek Hakkani-Tur, Heng Ji

Challenge:	Existing studies on LLMs alignment focus on generalizing their behavior to generalized values such as helpfulness, harmlessness, and honesty.
Approach:	They train large language models to "interact to align" to implicitly infer user preferences . they use a multi-turn preference dataset to generate a personalized alignment .
Outcome:	The proposed method enables dynamic, personalized alignment via interaction with a multi-turn preference dataset.

LINKED: Eliciting, Filtering and Integrating Knowledge in Large Language Model for Commonsense Reasoning (2024.findings-emnlp)

Copied to clipboard

Jiachun Li, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Kang Liu, Xiaojian Jiang, Jiexin Xu, Jun Zhao

Reasoning

Challenge:	Large language models (LLMs) often exhibit poor performance on knowledge-intensive tasks, such as commonsense reasoning.
Approach:	They propose a method to elicit, filter and integrate knowledge in large language models (LINKED) they propose 'reward model' to filter out noisy knowledge and 'take marginal consistent reasoning module'
Outcome:	The proposed method outperforms SOTA baselines on two commonsense reasoning tasks.

Enhancing Low-Resource LLMs Classification with PEFT and Synthetic Data (2024.lrec-main)

Copied to clipboard

Parth Patwa, Simone Filice, Zhiyu Chen, Giuseppe Castellucci, Oleg Rokhlenko, Shervin Malmasi

DAGS: A Dependency-Based Dual-Attention and Global Semantic Improvement Framework for Metaphor Recognition (2025.findings-acl)

Challenge:	Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks.
Approach:	They propose to make Large Language Models (LLMs) operating in 0-shot or few-shot settings as efficient as 0- shot text classifiers by leveraging a small number of samples.
Outcome:	The proposed model is able to perform better on multiple datasets than existing models on 0-shot or few-shot settings.

Copied to clipboard

Puli Chen, Cheng Yang, Xingmao Zhang, Qingbao Huang

Sentiment Analysis

Challenge:	Existing methods for metaphor recognition ignore interference caused by literal annotations . et al., 2018: Metaphor recognition plays an important role in cognition and communication .
Approach:	They propose a dependency-based Dual-Attention and Global Semantic Improvement framework to improve metaphor recognition.
Outcome:	The proposed framework can extract features from multiple information sources while improving on mainstream metaphor datasets.

Structured List-Grounded Question Answering (2025.coling-main)

Copied to clipboard

Mujeen Sung, Song Feng, James Gung, Raphael Shu, Yi Zhang, Saab Mansour

A Fast and Flexible Webinterface for Dialect Research in the Low Countries (L18-1)

Challenge:	Document-grounded dialogue systems aim to answer user queries by leveraging external information.
Approach:	They propose a dataset to evaluate QA systems' ability to interpret and use structured lists . they use language models and model-based filtering processes to enhance data quality .
Outcome:	The proposed model outperforms baselines on the LIST2QA dataset . it shows that the proposed model is more accurate and complete than baselines .

Copied to clipboard

Roeland van Hout, Nicoline van der Sijs, Erwin Komen, Henk van den Heuvel

Challenge:	e-WBD and eWLD are webportals with search applications built to make the data from the Dictionary of the Brabantic and 39 volumes of the Limburgian accessible and retrievable.
Approach:	This paper describes the development of webportals with search applications built to make the data accessible and retrievable for both the research community and general audience.
Outcome:	The e-WBD and eWLD webportals are being defined in more detail.

Recovering document annotations for sentence-level bitext (2024.findings-acl)

Copied to clipboard

Rachel Wicks, Matt Post, Philipp Koehn

Machine Translation

Challenge:	In machine translation, historical models were incapable of handling longer contexts, so the lack of document-level datasets was less noticeable.
Approach:	They propose a document-level filtering technique that discards document- level metadata.
Outcome:	The proposed method improves translation without degradation of sentence-level translation.

Finding Spoken Identifications: Using GPT-4 Annotation for an Efficient and Fast Dataset Creation Pipeline (2024.lrec-main)

Copied to clipboard

Maliha Jahan, Helin Wang, Thomas Thebaud, Yinglun Sun, Giang Ha Le, Zsuzsanna Fagyal, Odette Scharenborg, Mark Hasegawa-Johnson, Laureano Moro Velazquez, Najim Dehak

ACCESS DENIED INC: The First Benchmark Environment for Sensitivity Awareness (2025.findings-acl)

Challenge:	Existing datasets that are limited to a few dialects, ethnicities, and age groups are not annotated considering these factors.
Approach:	They propose a semi-automated dataset creation pipeline that leverages large language models to perform two complex annotation tasks using human annotations as ground truths.
Outcome:	The proposed pipeline reduces time required for the filtering and tagging tasks while losing no important information.

Copied to clipboard

Dren Fazlija, Arkadij Orlov, Sandipan Sikdar

HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMs (2024.acl-long)

Challenge:	Large language models can process text from various document formats and facilitate user interactions through natural language queries.
Approach:	They propose a concept of sensitivity awareness (SA) which enables LLMs to adhere to predefined access rights rules.
Outcome:	The proposed model can adhere to predefined access rights rules while managing unauthorized requests while effectively addressing legitimate queries.

Copied to clipboard

Pranoy Panda, Ankush Agarwal, Chaitanya Devaguptapu, Manohar Kaul, Prathosh Ap

[MASK]ED - Language Modeling for Explainable Classification and Disentangling of Socially Unacceptable Discourse. (2025.findings-emnlp)

Challenge:	Existing approaches to answer multi-hop questions are query-agnostic and the extracted facts are ambiguous as they lack context.
Approach:	They propose to use a knowledge graph to extract query-relevant information from unstructured text.
Outcome:	The proposed method achieves performance improvements on two popular datasets.

Copied to clipboard

Dimitra Niaouri, Mohamed Rayane Ghilene, Michele Linardi, Julien Longhi

What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations (2023.findings-emnlp)

Challenge:	Pre-trained PMLMs often degrade in multi-label SUD classification due to overlapping linguistic cues.
Approach:	They propose an artifact-guided pre-training strategy that injects statistically salient linguistic features into masked language models to enhance generalization across discourse types.
Outcome:	The proposed approach improves performance in 10 datasets extensively used in SUD classification benchmarks.

Copied to clipboard

Kavel Rao, Liwei Jiang, Valentina Pyatkin, Yuling Gu, Niket Tandon, Nouha Dziri, Faeze Brahman, Yejin Choi

Fighting Bias With Bias: Promoting Model Robustness by Amplifying Dataset Biases (2023.findings-acl)

Challenge:	Moral or ethical judgments rely heavily on the contexts in which they occur . a student model that produces defeasible contexts with improved validity, diversity, and defasibility is superior to intermediate student models .
Approach:	a new study uses a student model to provide contextualizations that make an action morally acceptable . the model is based on a dataset of 115K defeasible moral actions rated highly by human annotators .
Outcome:	The proposed model outperforms all intermediate models in a high-quality dataset . the model is based on 1.2M entries of contextualizations and rationales for 115K moral actions .

Copied to clipboard

Yuval Reif, Roy Schwartz

GitHub Typo Corpus: A Large-Scale Multilingual Dataset of Misspellings and Grammatical Errors (2020.lrec-1)

Challenge:	Recent work sought to develop robust, unbiased models by filtering biased examples from training sets.
Approach:	They propose to filter out biased examples from training sets to improve models' performance.
Outcome:	The proposed evaluation framework is more challenging than the original dataset splits and even more challenging that hand-crafted challenge sets.

Copied to clipboard

Masato Hagiwara, Masato Mita

Discovering Language Model Behaviors with Model-Written Evaluations (2023.findings-acl)

Challenge:	Lack of large-scale datasets has been a major hindrance to the development of NLP tasks such as spelling correction and grammatical error correction.
Approach:	They propose to make GitHub Typo Corpus a multilingual dataset of misspellings and grammatical errors available for use in NLP.
Outcome:	The proposed dataset contains more than 350k edits and 65M characters in more than 15 languages.

Copied to clipboard

Ethan Perez, Sam Ringer, Kamile Lukosiute, Karina Nguyen, Edwin Chen, Scott Heiner, Craig Pettit, Catherine Olsson, Sandipan Kundu, Saurav Kadavath, Andy Jones, Anna Chen, Benjamin Mann, Brian Israel, Bryan Seethor, Cameron McKinnon, Christopher Olah, Da Yan, Daniela Amodei, Dario Amodei, Dawn Drain, Dustin Li, Eli Tran-Johnson, Guro Khundadze, Jackson Kernion, James Landis, Jamie Kerr, Jared Mueller, Jeeyoon Hyun, Joshua Landau, Kamal Ndousse, Landon Goldberg, Liane Lovitt, Martin Lucas, Michael Sellitto, Miranda Zhang, Neerav Kingsland, Nelson Elhage, Nicholas Joseph, Noemi Mercado, Nova DasSarma, Oliver Rausch, Robin Larson, Sam McCandlish, Scott Johnston, Shauna Kravec, Sheer El Showk, Tamera Lanham, Timothy Telleen-Lawton, Tom Brown, Tom Henighan, Tristan Hume, Yuntao Bai, Zac Hatfield-Dodds, Jack Clark, Samuel R. Bowman, Amanda Askell, Roger Grosse, Danny Hernandez, Deep Ganguli, Evan Hubinger, Nicholas Schiefer, Jared Kaplan

Align Documents to Questions: Question-Oriented Document Rewriting for Retrieval-Augmented Generation (2026.findings-acl)

Challenge:	Prior work creates evaluations with crowdwork or existing data sources, which are not always available.
Approach:	They generate evaluations automatically with language models (LMs) using crowdwork or existing data sources to find out how they behave .
Outcome:	The results show that large LMs repeat back a dialog user’s preferred answer and express greater desire to pursue concerning goals like resource acquisition and goal preservation.

Copied to clipboard

Jiaang Li, Zhendong Mao, Quan Wang, Yuning Wan, Yongdong Zhang

Small Language Models Need Strong Verifiers to Self-Correct Reasoning (2024.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) enhances the factuality of Large Language Models (LLMs) however, LLMs exhibit a stylistic bias when presented with mixed contexts, revealing a bottleneck in their utility.
Approach:	They propose a style-controlled rewriter that aligns retrieved documents with a question-oriented style while preserving facts.
Outcome:	The proposed model improves RAG pipelines by 8% with negligible latency overhead.

Copied to clipboard

Yunxiang Zhang, Muhammad Khalifa, Lajanugen Logeswaran, Jaekyeom Kim, Moontae Lee, Honglak Lee, Lu Wang

Fine-Grained Data Ordering Improves Fine-Tuning for Large Language Models (2026.findings-acl)

Challenge:	Existing studies show that large language models can self-correct their outputs by generating a critique and revising it based on the critique.
Approach:	They propose a pipeline that prompts small language models to collect self-correction data that supports the training of self-refinement abilities.
Outcome:	The proposed pipeline improves the self-correction abilities of two models on five datasets spanning math and commonsense reasoning.

Copied to clipboard

Xiaomeng Hu, Yixuan Tang, Haoze Li, Hao Chen, Qi Zhang, Zhanming Shen, Yiming Zhang, Haobo Wang, Junbo Zhao

ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages Using Wikidata (2024.lrec-main)

Challenge:	Prior work focused on data preprocessing, focusing on filtering and cleaning data . a study aimed to improve fine-grained scheduling of data order in epochs .
Approach:	They propose a fine-grained scheduling method of data order in epochs to fill this gap . they define data difficulty based on relevance between data and model .
Outcome:	The proposed method improves on pre-training and small-scale fine-tuning experiments 2.4% over baselines.

Copied to clipboard

Jonne Sälevä, Constantine Lignos

GottBERT: a pure German Language Model (2024.emnlp-main)

Challenge:	ParaNames is a massively multilingual parallel name resource . it provides names for 16.8 million entities in over 400 languages .
Approach:	They propose a massively multilingual parallel name resource with 140 million names . they use Wikidata to standardize the data and perform canonical name translation .
Outcome:	The proposed resource is the largest of its type to date and performs well on 10 languages.

Copied to clipboard

Raphael Scheible, Johann Frei, Fabian Thomczyk, Henry He, Patric Tippmann, Jochen Knaus, Victor Jaravine, Frank Kramer, Martin Boeker

Walk and Read Less: Improving the Efficiency of Vision-and-Language Navigation via Tuning-Free Multimodal Token Pruning (2025.emnlp-main)

Challenge:	Pre-trained language models have advanced natural language processing (NLP) despite the introduction of BERT, single-language models are still relevant.
Approach:	They present a German singlelanguage RoBERT model pre-trained exclusively on the German portion of the OSCAR dataset.
Outcome:	The GottBERT model outperforms the existing models on Named Entity Recognition and text classification tasks.

Copied to clipboard

Wenda Qin, Andrea Burns, Bryan A. Plummer, Margrit Betke

Attention Weights as an Indicator: Analyzing and Improving Document Utilization in Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Large models achieve strong performance on Vision-and-Language Navigation tasks, but are costly to run in resource-limited environments.
Approach:	They propose a method to prune large models to minimize information loss . they use navigation-specific traits to filter the model into foreground and background .
Outcome:	The proposed method outperforms previous work on standard VLN benchmarks while saving 50% FLOPS.

Copied to clipboard

Jing Jin, Yuhan Song, Wen Luo, Houfeng Wang

An Evaluation Resource for Grounding Translation Errors (2025.findings-emnlp)

Challenge:	In traditional RAG models, documents are grouped into categories based on their quality and order, and the quality of inputs is variable due to ineffective retrievers or misalignment between the retriever and generator.
Approach:	They propose to use attention weights to enhance document utilization from three perspectives: document ranking, placement, and filtering.
Outcome:	The proposed method outperforms baselines and improves document utilization effectiveness in a training-free manner.

Copied to clipboard

Sujin Chen, Kang Wang, Zixuan Zhou, Xiangyu Duan, Wanqun Zhang, Hao Yang, Jinsong Su, Min Zhang

Explainability & Interpretability in NLP

Challenge:	Current fine-grained error analyses do not ground the errors to the reasons why the annotated text spans are erroneous.
Approach:	They use a bi-directional grounding scheme to ground erroneous text in two directions . if the error spans of both directions are consistent, the explanation is valid .
Outcome:	The proposed grounding process improves translation error detection significantly.

SimpleDoc: Multi‐Modal Document Understanding with Dual‐Cue Page Retrieval and Iterative Refinement (2025.emnlp-main)

Copied to clipboard

Chelsi Jain, Yiran Wu, Yifan Zeng, Jiale Liu, Shengyu Dai, Zhenwen Shao, Qingyun Wu, Huazheng Wang

Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive Dashboards (2026.acl-long)

Challenge:	Document Visual Question Answering (DocVQA) is a task to answer questions based on documents containing text, tables, and images.
Approach:	They propose a lightweight retrieval framework that uses visual language models to embed and retrieve relevant pages as images and generate answers with VLMs that can accept an image as input.
Outcome:	The proposed framework outperforms baselines by 3.2% on average on 4 DocVQA datasets with much fewer pages retrieved.

Copied to clipboard

Tianhao Niu, Ziyu Han, Qiguang Chen, Shiqi Zhou, Baocai Shan, Hengjie Fang, Qingfu Zhu, Wanxiang Che