Papers with classification
ActiveLLM: Large Language Model-Based Active Learning for Textual Few-Shot Scenarios (2026.tacl-1)
Copied to clipboard
| Challenge: | Active learning strategies struggle with a ‘cold-start’ problem, needing substantial initial data to be effective. |
| Approach: | They propose an active learning approach that leverages Large Language Models such as GPT-4, o1, Llama 3, or Mistral Large for selecting instances. |
| Outcome: | The proposed approach outperforms existing methods ADAPET, PERFECT, and SetFit in few-shot scenarios and can be extended to non-few scenarios. |
Distributed Knowledge Based Clinical Auto-Coding System (P19-2)
Copied to clipboard
| Challenge: | Codification of free-text clinical narratives has long been recognised to be beneficial for secondary uses such as funding, insurance claim processing and research. |
| Approach: | They propose to use NLP and related machine learning techniques to assign ICD-10-AM and ACHI codes to clinical records using local and international standards. |
| Outcome: | The proposed system utilises NLP and ML techniques to assign ICD-10-AM and ACHI codes to clinical records while adhering to local and international standards. |
Transfer Learning for Humor Detection by Twin Masked Yellow Muppets (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing humor classification systems have been dealing with different forms of humor independently. |
| Approach: | They propose to combine different forms of humor to tackle different humor types by a shared-private multitask architecture using a transfer learning paradigm. |
| Outcome: | The proposed architecture shows statistically significant improvements over baselines and accounting for new state-of-the-art figures for two datasets. |
Neural Network based Extreme Classification and Similarity Models for Product Matching (N18-3)
Copied to clipboard
| Challenge: | Matching a seller listed item to an appropriate product has become a fundamental step for e-commerce platforms. |
| Approach: | They propose to use a shallow neural network to match a seller's item to an appropriate product . they also propose a similarity approach based on deep siamese network to train and infer product information. |
| Outcome: | The proposed models outperform the baseline models by more than 5% in terms of accuracy and are capable of efficient training and inference. |
Uncertainty Quantification for Large Language Models (2025.acl-tutorials)
Copied to clipboard
| Challenge: | Large language models (LLMs) produce hallucinations, which undermine user trust and reliability. |
| Approach: | This tutorial offers the first systematic introduction to uncertainty quantification (UQ) for LLMs in text generation tasks. |
| Outcome: | The proposed framework provides tools for communicating the reliability of a model answer. |
How LLMs React to Industrial Spatio-Temporal Data? Assessing Hallucination with a Novel Traffic Incident Benchmark Dataset (2025.naacl-industry)
Copied to clipboard
Qiang Li, Mingkun Tan, Xun Zhao, Dan Zhang, Daoan Zhang, Shengzhao Lei, Anderson S. Chu, Lujun Li, Porawit Kamnoedboon
| Challenge: | Large language models (LLMs) have a high potential to digitize and enhance the health & public services industry. |
| Approach: | They propose to use a cross-lingual benchmark dataset to assess the robustness of state-of-the-art LLMs in the spatio vs temporal domain for traffic incident classification. |
| Outcome: | The proposed model performs well in the spatio-temporal domain and in the non-English context. |
Automatic detection of dyslexia based on eye movements during reading in Russian (2025.acl-short)
Copied to clipboard
| Challenge: | Existing screening tests for dyslexia are time- and resource-consuming . early diagnosis is key for learning disabilities, but eye tracking technology is promising . |
| Approach: | They propose to automatically classify dyslexia based on eye movements recorded during natural reading combined with basic demographic information and linguistic features. |
| Outcome: | The proposed model outperforms the state-of-the-art model by 7 % and has an AUC of 0.93 . the focus features matter the most for classification, the authors show . |
Recognizing Multimodal Entailment (2021.acl-tutorials)
Copied to clipboard
Cesar Ilharco, Afsaneh Shirazi, Arjun Gopalan, Arsha Nagrani, Blaz Bratanic, Chris Bregler, Christina Funk, Felipe Ferreira, Gabriel Barcik, Gabriel Ilharco, Georg Osang, Jannis Bulian, Jared Frank, Lucas Smaira, Qin Cao, Ricardo Marino, Roma Patel, Thomas Leung, Vaiva Imbrasaite
| Challenge: | This tutorial introduces the multimodal entailment task for detecting semantic alignments . the task requires fine-grained understanding of visual and linguistic semantics questions . |
| Approach: | This tutorial introduces the multimodal entailment task to machine learning . it introduces a dataset for recognizing multimodal alignments . |
| Outcome: | This tutorial introduces the multimodal entailment task . it can be useful for detecting semantic alignments when a single modality alone is not enough . |
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers (2025.tacl-1)
Copied to clipboard
Kabir Ahuja, Vidhisha Balachandran, Madhur Panwar, Tianxing He, Noah A. Smith, Navin Goyal, Yulia Tsvetkov
| Challenge: | Inductive biases in transformers can cause hierarchical generalization without explicitly encoding structural bias. |
| Approach: | They investigate sources of inductive bias in transformer models and their training that could cause such preference for hierarchical generalization. |
| Outcome: | The proposed model can generalize to novel syntactic forms without explicit bias . the proposed model is able to generalize on a dataset with a hierarchical grammar . |
Analyzing Text Representations by Measuring Task Alignment (2023.acl-short)
Copied to clipboard
| Challenge: | Recent advances in text classification have shown that pre-trained representations are key for text classification. |
| Approach: | They propose a task alignment score that measures alignment at different levels of granularity. |
| Outcome: | The proposed score shows that task alignment can explain the performance of a given representation. |
Domain Adapted Word Embeddings for Improved Sentiment Classification (P18-2)
Copied to clipboard
| Challenge: | Generic word embeddings are trained on large-scale generic corpora, while domain specific ones are trained only on data from a domain of interest. |
| Approach: | They propose a method to combine breadth of generic and specific embeddings to form domain-specific embeddables. |
| Outcome: | The proposed method outperforms generic and domain specific embeddings on sentiment classification tasks. |
Token Sequence Labeling vs. Clause Classification for English Emotion Stimulus Detection (2020.starsem-1)
Copied to clipboard
| Challenge: | Emotion stimulus detection is the task of finding the cause of an emotion in a textual description. |
| Approach: | They propose to evaluate whether clause classification or token sequence labeling is better for emotion stimulus detection in English. |
| Outcome: | The proposed framework compares clause classification and token sequence labeling on four English datasets. |
Forum 4.0: An Open-Source User Comment Analysis Framework (2021.eacl-demos)
Copied to clipboard
Marlo Haering, Jakob Smedegaard Andersen, Chris Biemann, Wiebke Loosen, Benjamin Milde, Tim Pietz, Christian Stöcker, Gregor Wiedemann, Olaf Zukunft, Walid Maalej
| Challenge: | Using Forum 4.0, we analyze, aggregate, and visualize user comments based on labels defined by domain experts. |
| Approach: | They introduce an open-source framework to semi-automatically analyze, aggregate, and visualize user comments based on labels defined by domain experts. |
| Outcome: | The proposed framework can analyze, aggregate, and visualize user comments based on labels defined by domain experts. |
BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to make exiting decisions are limited to classification tasks . large-scale pre-trained language models such as BERT have brought performance gain but at the cost of heavy computational burden. |
| Approach: | They propose a fine-tuning strategy and a learning-to-exit module to accelerate BERT inference . they propose to make trade-offs between model quality and efficiency by early exiting . |
| Outcome: | The proposed approach improves early exiting for BERT, with better trade-offs . it can be combined with other acceleration methods, and the proposed strategy can be applied to regression tasks. |
Hierarchical Attention Network for Explainable Depression Detection on Twitter Aided by Metaphor Concept Mappings (2022.coling-1)
Copied to clipboard
| Challenge: | Existing black-box-like deep learning methods for depression detection focus on improving classification performance, but it is impossible to explain and interpret those models that rely on state-of-the-art (SOTA) deep learning techniques. |
| Approach: | They propose to use hierarchical attention mechanisms and feed-forward neural networks to encode a model for depression detection on Twitter that leverages metaphorical concept mappings as input. |
| Outcome: | The proposed model leverages metaphorical concept mappings as input to detect depressed individuals and identify features of such users’ tweets. |
Hierarchical Text Classification with LLM-Refined Taxonomies (2026.eacl-long)
Copied to clipboard
| Challenge: | Hierarchical text classification (HTC) relies on taxonomies that organize labels into structured hierarchies, but many real-world taxonomies introduce ambiguities, such as identical leaf names under similar parent nodes, which prevent language models from learning clear decision boundaries. |
| Approach: | They propose a framework that uses large language models to transform entire taxonomies through operations such as renaming, merging, splitting, and reordering to better match the semantics encoded by LMs. |
| Outcome: | The proposed framework outperforms human-curated taxonomies in three HTC benchmarks and shows that it aligns better with the model's actual confusion patterns. |
Arabic Synonym BERT-based Adversarial Examples for Text Classification (2024.eacl-srw)
Copied to clipboard
| Challenge: | Often, research studies quantifying the impact of adversarial text attacks have been applied only to models trained in English. |
| Approach: | They propose a word-level study of adversarial text examples in Arabic . they use a synonym attack with a BERT model to assess their robustness . |
| Outcome: | The proposed attack compares Arabic adversarial examples with their original examples and regains 2% accuracy after training. |
IDP Accelerator: Agentic Document Intelligence from Extraction to Compliance Validation (2026.acl-demo)
Copied to clipboard
Md Mofijul Islam, Md Sirajus Salekin, Joe King, Priyashree Roy, Vamsi Thilak Gudi, Spencer Romo, Akhil Nooney, Bob Strahan, Boyi Xie, Diego A. Socolinsky
| Challenge: | Large Language Models (LLMs) are inadequate for extracting structured insights from unstructured documents. |
| Approach: | They propose a framework enabling agentic AI for end-to-end document intelligence with four key components: DocSplit, configurable Extraction Module, and Rule Validation Module. |
| Outcome: | The proposed framework achieves 98% classification accuracy, 80% reduced processing latency, and 77% lower operational costs over legacy baselines. |
Introducing the CURLICAT Corpora: Seven-language Domain Specific Annotated Corpora from Curated Sources (2022.lrec-1)
Copied to clipboard
Tamás Váradi, Bence Nyéki, Svetla Koeva, Marko Tadić, Vanja Štefanec, Maciej Ogrodniczuk, Bartłomiej Nitoń, Piotr Pęzik, Verginica Barbu Mititelu, Elena Irimia, Maria Mitrofan, Dan Tufiș, Radovan Garabík, Simon Krek, Andraž Repar
| Challenge: | The CURLICAT CEF Telecom project aims to collect and deeply annotate a set of large corpora from selected domains. |
| Approach: | They present the results of the CURLICAT CEF Telecom project . they propose to collect and deeply annotate a set of large corpora from selected domains . |
| Outcome: | The CURLICAT CEF Telecom project provides a set of large corpora from selected domains . the corporatized corporates are tokenized, lemmatized and morphologically analysed . |
Detecting Response Generation Not Requiring Factual Judgment (2024.naacl-srw)
Copied to clipboard
| Challenge: | Large language models (LLMs) have undergone considerable development and can solve various natural language processing tasks. |
| Approach: | They aimed to achieve both attractiveness and factuality in a dialogue response by crowdsourcing a dataset and performing classification tasks on several models. |
| Outcome: | The proposed model with the highest classification accuracy could yield about 88% accurate classification results. |
Concreteness vs. Abstractness: A Selectional Preference Perspective (2022.aacl-srw)
Copied to clipboard
| Challenge: | Using a collection of 5,438 nouns and 1,275 verbs, we exploit selectional preferences as a salient characteristic in classifying abstract vs. concrete words. |
| Approach: | They propose to use selectional preferences as a criterion to distinguish between concrete and abstract concepts and words. |
| Outcome: | The proposed method achieves an f1-score of 0.84 for nouns and 0.71 for verbs in classification and Spearman’s correlation of 0.86 for nonoms and 0.59% for verb. |
Multi-Task Learning of Generation and Classification for Emotion-Aware Dialogue Response Generation (2021.naacl-srw)
Copied to clipboard
| Challenge: | Existing models for human-like interaction with humans are not expected to improve the accuracy of emotion recognition, but instead focus on generating emotion-aware responses. |
| Approach: | They propose a neural response generation model with multi-task learning of generation and classification, focusing on emotion. |
| Outcome: | The proposed model makes generated responses more emotionally aware. |
Evaluating Research Novelty Detection: Counterfactual Approaches (D19-53)
Copied to clipboard
| Challenge: | Despite its importance, this direction of research has not been explored as much. |
| Approach: | They propose to use counterfactual simulations to evaluate paper novelty detection models . they ask models to differentiate papers at time t and counterf actual paper from future time . |
| Outcome: | The proposed models can be compared against a set of papers with a given date and with different annotations. |
PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models (2026.eacl-demo)
Copied to clipboard
| Challenge: | Parameter-Efficient Fine-Tuning (PEFT) methods address the increasing size of Large Language Models (LLMs). |
| Approach: | They propose a framework for efficient fine-tuning Large Language Models (LLMs) they aim to train only a small percentage of the full model's parameters . |
| Outcome: | Xu et al., 2023; Ding e t al, 2024; Lialin e al. 2023) show that using PEFT methods can improve performance. |
The Microsoft Toolkit of Multi-Task Deep Neural Networks for Natural Language Understanding (2020.acl-demos)
Copied to clipboard
Xiaodong Liu, Yu Wang, Jianshu Ji, Hao Cheng, Xueyun Zhu, Emmanuel Awa, Pengcheng He, Weizhu Chen, Hoifung Poon, Guihong Cao, Jianfeng Gao
| Challenge: | MT-DNN is an open-source natural language understanding toolkit . it allows researchers and developers to train customized deep learning models . |
| Approach: | They present MT-DNN, an open-source natural language understanding toolkit . it is designed to facilitate rapid customization for a broad spectrum of NLU tasks . MT supports multi-task knowledge distillation, which can substantially compress a deep neural model without significant performance drop. |
| Outcome: | The proposed model can significantly compress a large model without significant performance drop. |
Non-Topical Coherence in Social Talk: A Call for Dialogue Model Enrichment (2020.acl-srw)
Copied to clipboard
| Challenge: | Current models of dialogue focus on utterances within a topically coherent discourse segment, not on social conversations . a pilot annotation study of NTUs is a first step towards a model capable of rationalizing conversational coherence in social talk. |
| Approach: | They conduct a pilot annotation study of social dialogues as a first step towards a Bayesian game-theoretic model . they first annotate content-based coherence relations that are not available in Disco-SPICE . |
| Outcome: | The proposed model can rationalize conversational coherence in social talk, the authors say . the study focuses on the natural occurring social dialogues in the Disco-SPICE corpus . |
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method (D19-53)
Copied to clipboard
| Challenge: | faceted concept hierarchy is a structure of parent-child relationships . concepts are expected to be organized in a hierarchical structure for student learning . |
| Approach: | They propose a faceted concept hierarchy that aims to build facets from scientific literature. |
| Outcome: | The proposed hierarchy is more complete than "type-of" relations, and resolves conflicts by maintaining the acyclic structure of a hierarchy. |
Predicting Fine-tuned Performance on Larger Datasets Before Creating Them (2025.coling-industry)
Copied to clipboard
| Challenge: | a method to estimate the performance of pretrained models fine-tuned with a larger dataset is proposed . a recent study found that fine-timing PMs with the small amount of data does not always result in ideal performance. |
| Approach: | They propose a method to estimate the performance of pretrained models fine-tuned with a larger dataset from the result with fewer epochs. |
| Outcome: | The proposed method can help resource-limited companies develop machine-learning models . it shows that when a model is fine-tuned with a larger dataset, its classification performance increases . |
An Interface for Annotating Science Questions (D18-2)
Copied to clipboard
Michael Boratko, Harshit Padigela, Divyendra Mikkilineni, Pritish Yuvraj, Rajarshi Das, Andrew McCallum, Maria Chang, Achille Fokoue, Pavan Kapanipathi, Nicholas Mattei, Ryan Musa, Kartik Talamadupula, Michael Witbrock
| Challenge: | a new interface for human annotation of science question-answer pairs with their knowledge and reasoning types is proposed . the interface is based on previous work on the ARC dataset, but does not provide clear definitions of these types of knowledge. |
| Approach: | They propose an interface for human annotation of science question-answer pairs with their respective knowledge and reasoning types. |
| Outcome: | The proposed interface improves the classification of science questions in a preliminary study involving 10 participants. |
“Hold on honey, men at work”: A semi-supervised approach to detecting sexism in sitcoms (2021.acl-srw)
Copied to clipboard
| Challenge: | sexist dialogue in sitcoms is an important part of society's development, according to Sink and Mastro (2017). |
| Approach: | They propose a semi-supervised text classification model that automatically detects instances of sexism in popular sitcom dialogues. |
| Outcome: | The proposed model outperforms deep learning-based systems in detecting sexist dialogues over time and shows that sexism decreases over the years. |
Implicitly Abusive Comparisons – A New Dataset and Linguistic Analysis (2021.eacl-main)
Copied to clipboard
| Challenge: | Using crowdsourcing, we can detect implicitly abusive comparisons . Abusive language is defined as hurtful, derogatory or obscene utterances made by one person to another . |
| Approach: | They propose to use crowdsourcing to generate a dataset for detecting implicitly abusive comparisons . they also use a range of linguistic features to better understand abusive comparison mechanisms . |
| Outcome: | The proposed dataset includes measures to obtain representative and unbiased comparisons. |
Who Plays Which Role? Protagonist Detection and Classification in Moral Discourse (2026.eacl-srw)
Copied to clipboard
| Challenge: | a systematic study of phrase-level protagonist detection and classification in moral discourse focuses on moral values rather than the actors involved. |
| Approach: | They propose to decompose a task into identifying protagonist mentions and classifying them by what kind of actor they are and what function they serve in the moral argument. |
| Outcome: | The proposed model outperforms previous models on the Moralization Corpus and fine-tuned lightweight models and prompting-based large language models. |
CMTA: COVID-19 Misinformation Multilingual Analysis on Twitter (2021.acl-srw)
Copied to clipboard
| Challenge: | myths, sensationalism, rumours and misinformation, generated intentionally or unintentionally, spread rapidly through social networks during the COVID-19 pandemic . evaluation of tweets for recognizing misinformation can create beneficial understanding to review the top quality and also the readability of online information concerning the COV-19. |
| Approach: | They propose a multilingual COVID-19 related tweet analysis method that uses a deep learning model for multilingual tweet misinformation detection and classification. |
| Outcome: | The proposed method outperforms monolingual models in the misinformation detection task and shows that it can be used to improve the quality and readability of online information. |
Detecting (Un)answerability in Large Language Models with Linear Directions (2026.eacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) often respond confidently to questions even when they lack the necessary information, leading to inaccurate responses or hallucinations. |
| Approach: | They propose an approach for identifying a direction in the model’s activation space that captures unanswerability and uses it for classification. |
| Outcome: | The proposed method detects unanswerable questions and generalizes better across datasets than existing prompt-based and classifier-based approaches. |
Sentence-State LSTM for Text Representation (P18-1)
Copied to clipboard
| Challenge: | LSTMs have been shown to suffer from various limitations due to their sequential nature. |
| Approach: | They propose to model hidden states of all words simultaneously at each recurrent step rather than one word at a time. |
| Outcome: | The proposed model has strong representation power, giving competitive performances compared to stacked BiLSTM models with similar parameter numbers. |
Risk-graded Safety for Handling Medical Queries in Conversational AI (2022.aacl-short)
Copied to clipboard
| Challenge: | Conversational AI systems can engage in unsafe behaviour when handling medical queries that could lead to death. |
| Approach: | They label medical queries with crowdsourced and expert annotations to identify the seriousness of the prompts and recognise the risk types posed by the responses. |
| Outcome: | The results suggest that these tasks can be automated, but caution should be exercised, as errors can potentially be very serious. |
MTP: A Dataset for Multi-Modal Turning Points in Casual Conversations (2024.acl-short)
Copied to clipboard
| Challenge: | a new problem setting is designed to detect critical moments in conversations . a human-annotated multi-modal dataset is used to classify and detect turning points . |
| Approach: | They propose a problem setting focusing on turning points in conversations as TPs . they propose MTPC, MTPD, & MTPR tasks to classify and detect turning points . |
| Outcome: | The proposed model achieves an F1-score of 0.88 in classification and 0.61 in detection . it uses state-of-the-art vision-language models to construct a narrative from the videos . |
I already said that! Degenerating redundant questions in open-domain dialogue systems. (2023.acl-srw)
Copied to clipboard
| Challenge: | Neural text generation models have been successful in short open-domain conversations, but their performance degrades significantly in the long term. |
| Approach: | They propose a method to generate training data without crowdsourcing . they adapt negative training, decoding, and classification methods to mitigate redundancy problem . |
| Outcome: | The proposed method reduces the rate of redundant questions from 27.2% to 8.7% while improving the quality of the original model. |
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders (2024.acl-long)
Copied to clipboard
| Challenge: | Conversational systems often rely on embedding models for intent classification and intent clustering tasks. |
| Approach: | They propose a toolkit that gives a more holistic view of intent embedding models by considering three tasks– (1) intent classification, (2) intent clustering, and (3) a novel triplet task. |
| Outcome: | The proposed model improves on the linguistic dimensions while affecting performance on downstream task metrics. |
Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications (2023.acl-short)
Copied to clipboard
| 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. |
Speaker-change Aware CRF for Dialogue Act Classification (2020.coling-main)
Copied to clipboard
| Challenge: | Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. |
| Approach: | They propose to modify the CRF layer to take speaker-change into account and learn meaningful transition patterns conditioned on speaker-changing DA labels. |
| Outcome: | The proposed model outperforms the original model with wide margins for some DA labels. |
Interpretation of Implicit Conditions in Database Search Dialogues (C18-1)
Copied to clipboard
| Challenge: | Existing attempts to extract information from user utterances in database search dialogues have failed . |
| Approach: | They propose to utilise information in user utterances that do not directly mention database fields for constructing database queries. |
| Outcome: | The proposed model performs better than the existing model on a real estate agent-customer dialogue. |
Bag of Tricks for In-Distribution Calibration of Pretrained Transformers (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent studies show that pre-trained language models (PLMs) often predict over-confidently. |
| Approach: | They propose to use ensemble learning and data augmentation to improve confidence calibration for PLMs by combining calibration techniques with a trade-off between accuracy and classification. |
| Outcome: | The proposed calibration method improves classification accuracy and confidence in pre-trained language models by combining several calibration techniques. |
Adapting Deep Learning Methods for Mental Health Prediction on Social Media (D19-55)
Copied to clipboard
| Challenge: | a quarter of the population in Europe suffers from an episode of a mental disorder in their life, according to the World Health Organization . text analysis of rich resources like social media can contribute to deeper understanding of mental health and provide means for their early detection. |
| Approach: | They propose to use a hierarchical attention network to predict if a user suffers from one of nine disorders to adapt a deep neural model to the task. |
| Outcome: | The proposed model outperforms previous benchmarks for four out of nine disorders in a binary classification task on social media. |
AutoML Meets Hugging Face: Domain-Aware Pretrained Model Selection for Text Classification (2025.naacl-srw)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning text classification models are resource-intensive and require substantial computational power and time. |
| Approach: | They propose a corpus-driven domain mapping pipeline that integrates pre-fine-tuned models from Hugging Face Model Hub into AutoML systems to improve model selection. |
| Outcome: | The proposed pipeline improves model selection and streamlines workflows and reduces computational costs. |
A Layered Debating Multi-Agent System for Similar Disease Diagnosis (2025.naacl-short)
Copied to clipboard
| Challenge: | Traditional classification, contrastive learning, and large language models fail to detect subtle clues necessary for differentiation. |
| Approach: | They propose a framework that leverages Large Language Models to achieve accurate disease diagnosis . they structure patient information and integrate extensive medical knowledge to guide the analysis . |
| Outcome: | The proposed framework aims to identify subtle differences between similar diseases . the proposed framework can be used in clinical practice to improve accuracy . |
Learning from Litigation: Graphs for Retrieval and Reasoning in eDiscovery (2025.acl-industry)
Copied to clipboard
| Challenge: | Electronic Discovery (eDiscovery) requires identifying relevant documents from vast collections for legal production requests. |
| Approach: | They propose a system that integrates knowledge graphs for enhanced document ranking and classification, augmented by LLM-driven reasoning. |
| Outcome: | The proposed system outperforms baselines in F1-score, precision, and recall across balanced and imbalanced datasets. |
Alfred: A System for Prompted Weak Supervision (2023.acl-demo)
Copied to clipboard
| Challenge: | Alfred is the first system for programmatic weak supervision (PWS) that creates training data for machine learning by prompting. |
| Approach: | They propose to use Python to create training data by prompting for machine learning . they find that it improves query throughput by 2.9x versus a naive approach . |
| Outcome: | The proposed system improves query throughput by 2.9x versus a naive approach. |
ViHOS: Hate Speech Spans Detection for Vietnamese (2023.eacl-main)
Copied to clipboard
| Challenge: | Increasing use of social networking sites can cause problems for human moderators to review tagged comments. |
| Approach: | They present a dataset that contains 26k spans on 11k comments and detailed annotation guidelines . they also provide definitions of hateful and offensive spans in Vietnamese comments . |
| Outcome: | The proposed dataset shows that it is difficult to detect specific types of spans in the dataset . the dataset is the first human-annotated corpus containing 26k spans on 11k comments . |
Acoustic Individual Identification of White-Faced Capuchin Monkeys Using Joint Multi-Species Embeddings (2025.acl-short)
Copied to clipboard
| Challenge: | acoustic identification of animals is an essential task for conservation and wildlife monitoring . but, many methods for automatic identification are hindered by lack of data . |
| Approach: | They explore cross-species pre-training to address the task of individual classification in white-faced capuchin monkeys. |
| Outcome: | The proposed methods can be used to identify calls from individual monkeys using acoustic embeddings from birds and humans. |
PartisanLens: A Multilingual Dataset of Hyperpartisan and Conspiratorial Immigration Narratives in European Media (2026.eacl-long)
Copied to clipboard
Michele Joshua Maggini, Paloma Piot, Anxo Pérez, Erik Bran Marino, Lúa Santamaría Montesinos, Ana Lisboa Cotovio, Marta Vázquez Abuín, Javier Parapar, Pablo Gamallo
| Challenge: | Existing methods for detecting hyperpartisan narratives and PRCTs are limited . hyperpartisan content promotes extreme views through one-sided, emotional language . |
| Approach: | They propose a multilingual dataset of 1617 hyperpartisan news headlines in Spanish, Italian, and Portuguese annotated in multiple political discourse aspects. |
| Outcome: | The proposed dataset is the first multilingual dataset of 1617 hyperpartisan headlines in Spanish, Italian, and Portuguese. |
Lexical Features Are More Vulnerable, Syntactic Features Have More Predictive Power (D19-55)
Copied to clipboard
| Challenge: | Existing metrics to quantify lexical diversity have been proposed. |
| Approach: | They propose to examine how generic language characteristics are impacted by text alterations. |
| Outcome: | The proposed models show that lexical features are more sensitive to text modifications than syntactic ones. |
ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks (2025.acl-long)
Copied to clipboard
Yu Lin, Ruining Yang, Yunlong Mao, Qizhi Zhang, Jue Hong, Quanwei Cai, Ye Wu, Huiqi Liu, Zhiyu Chen, Bing Duan, Sheng Zhong
| Challenge: | Recent studies show that obfuscation techniques for MLaaS are susceptible to embedding inversion attacks (EIAs). |
| Approach: | They propose a model obfuscation framework that protects client inputs from embedding inversion attacks by obliviously obbing models. |
| Outcome: | The proposed framework outperforms existing works in utility by 10% with a nearly 80% resistance rate against embedding inversion attacks. |
Leveraging Multi-lingual Positive Instances in Contrastive Learning to Improve Sentence Embedding (2024.eacl-long)
Copied to clipboard
| Challenge: | Recent trends in learning monolingual and multilingual sentence embeddings are based on contrastive learning (CL) among an anchor, one positive and multiple negative instances. |
| Approach: | They propose to leverage multiple positives to improve learning of multilingual sentence embeddings by using an anchor, one positive, and multiple negative instances. |
| Outcome: | The proposed approach improves retrieval, semantic similarity, and classification performance on unseen languages. |
MultiCAT: Multimodal Communication Annotations for Teams (2025.findings-naacl)
Copied to clipboard
Adarsh Pyarelal, John M Culnan, Ayesha Qamar, Meghavarshini Krishnaswamy, Yuwei Wang, Cheonkam Jeong, Chen Chen, Md Messal Monem Miah, Shahriar Hormozi, Jonathan Tong, Ruihong Huang
| Challenge: | Recent flagship models from OpenAI and Google are only capable of 1-on-1 interactions with humans, limiting the potential for integration into human-machine teams of the future. |
| Approach: | They propose a dataset that allows team members to make multiple types of predictions on the same dataset. |
| Outcome: | The proposed dataset builds upon data from teams working collaboratively to save victims in a simulated search and rescue mission. |
Exploring the Role of BERT Token Representations to Explain Sentence Probing Results (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have focused on enhancing existing models with the primary objective of improving downstream performance on various NLP tasks. |
| Approach: | They propose to use BERT to encode meaningful knowledge in token representations to explain probing results. |
| Outcome: | The proposed model can detect syntactic and semantic abnormalities and distinguish between grammatical number and tense subspaces. |
Estimating User Communication Styles for Spoken Dialogue Systems (2020.lrec-1)
Copied to clipboard
| Challenge: | a neural network estimation system for spoken dialogues can be used to estimate the communication style of a user's interaction, but this is rarely implemented in a live system. |
| Approach: | They propose a neural network approach to estimate the communication style of spoken interaction, namely elaborateness and directness. |
| Outcome: | The proposed method can estimate the elaborateness and directness of spoken interaction and improve the results with additional linguistic features. |
A new approach for fine-tuning sentence transformers for intent classification and out-of-scope detection tasks (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Virtual assistants often can handle only a limited scope of intents. |
| Approach: | They propose to combine out-of-scope (OOS) rejection with intent classification . they propose to regularize cross-entropy loss with an in-scope embedding reconstruction loss . |
| Outcome: | The proposed method achieves a 1-4% improvement in the area under the precision-recall curve for rejecting out-of-sample instances without compromising intent classification performance. |
RegTrack: A Fine-Grained Benchmark for Multi-Class Legal Change Detection (2026.acl-srw)
Copied to clipboard
| Challenge: | Existing models lack finegrained classification schemes to determine whether small changes impact legal obligations or merely update formatting. |
| Approach: | They propose a benchmark for change detection in EU regulations that uses 4,772 manually annotated pairs of structurally distinct provisions mapped to a six-class taxonomy of legal change types. |
| Outcome: | The proposed framework combines lexical algorithms, dense encoders, and Large Language Models (LLMs) as baselines. |
A Few More Examples May Be Worth Billions of Parameters (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent work on few-shot learning for natural language tasks explores the dynamics of scaling up either the number of model parameters or labeled examples while controlling for the other variable by setting it to a constant. |
| Approach: | They explore the dynamics of scaling up the number of model parameters versus the number labeled examples across a wide variety of tasks. |
| Outcome: | The results show that scaling parameters yields performance improvements, while adding examples does not. |
REIC: RAG-Enhanced Intent Classification at Scale (2025.emnlp-industry)
Copied to clipboard
Ziji Zhang, Michael Yang, Zhiyu Chen, Yingying Zhuang, Shu-Ting Pi, Qun Liu, Rajashekar Maragoud, Vy Nguyen, Anurag Beniwal
| Challenge: | Accurate intent classification is critical for efficient routing in customer service . however, as companies expand their product lines, intent classification faces scalability challenges . |
| Approach: | They propose a retrieval-augmented generation Enhanced Intent Classification approach which leverages retrieval augmented generation to integrate relevant knowledge into a model. |
| Outcome: | The proposed approach outperforms fine-tuning, zero-shot, and few-shot methods on real-world datasets. |
Automatic Evaluation of Local Topic Quality (P19-1)
Copied to clipboard
Jeffrey Lund, Piper Armstrong, Wilson Fearn, Stephen Cowley, Courtni Byun, Jordan Boyd-Graber, Kevin Seppi
| Challenge: | Topic models are evaluated with global topic distributions but without local topic assignments. |
| Approach: | They propose a task to elicit human judgments of token-level topic assignments . they propose to use global metrics to evaluate topic models at a local level . |
| Outcome: | The proposed task elicits human judgments of token-level topic assignments . global metrics agree poorly with human assignments, the authors show . |
On the Effect of Isotropy on VAE Representations of Text (2022.acl-short)
Copied to clipboard
| Challenge: | Injecting desired geometric properties into text representations has attracted a lot of attention due to its better utilisation of representation space. |
| Approach: | They propose to use an isotropic Gaussian posterior instead of the ellipsoidal Gausssian priori to inject isotropy into text representations. |
| Outcome: | The proposed method improves classification performance, robustness to input perturbation, and generative behavior compared to the ellipsoidal Gaussian posterior. |
Leveraging Task Dependency and Contrastive Learning for Case Outcome Classification on European Court of Human Rights Cases (2023.eacl-main)
Copied to clipboard
| Challenge: | a new method for case outcome classification is being developed for the European Court of Human Rights. |
| Approach: | They propose to use case facts descriptions to classify whether a court finds a violation of conventions. |
| Outcome: | The proposed model improves on single-task and joint models without contrastive loss. |
A Multi-Task Transformer Model for Fine-grained Labelling of Chest X-Ray Reports (2024.lrec-main)
Copied to clipboard
| Challenge: | Chest radiography is one of the most commonly performed imaging examinations, with over 50 million chest X-rays annually in the United States . manual review of chest x-ray images can be onerous process prone to errors due to large volumes of images interpreted daily by radiologists . |
| Approach: | They propose a transformer-based model that segments radiology reports into semantically coherent segments and classifies each segment using a set of 37 radiological abnormalities. |
| Outcome: | The proposed model achieves state-of-the-art on report segmentation (0.0442 WinDiff) and multi-label classification (0.8 report-level macro F1) over 37 radiological labels and 8 NLP-specific labels. |
Tonal Salience in Cognitive Decline: In-Context MCI Detection with Multimodal LLMs (2026.acl-srw)
Copied to clipboard
| Challenge: | a recent study shows that tonal languages like Chinese have a higher classification performance than non-tonal languages like English. |
| Approach: | a new study examines the differences between tonal and non-tonal language classifications . they hypothesize that the difference is rooted in language typology . early cognitive decline is notoriously difficult to detect . |
| Outcome: | The proposed method compared to TAUKADIAL audio shows that Chinese and English perform better on Chinese . the findings suggest that language typology should inform the design of audio-based cognitive screening tools . |
Where to Attack: A Dynamic Locator Model for Backdoor Attack in Text Classifications (2022.coling-1)
Copied to clipboard
| Challenge: | BackDoor Attack (BDA) study aims to train a poisoned model with clean data and some trigger-embedded instances to perform normally on normal inputs. |
| Approach: | They propose to train a poisoned model with clean and poisonest inputs . they propose to use triggers to predict those poisonets as target labels . |
| Outcome: | The proposed model can predict P2P dynamically without human intervention. |
Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent Detection (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to identify all possible user intents at design time are expensive and require storage of past data. |
| Approach: | They propose to continually train an intent detector on new intents while maintaining performance on prior intents. |
| Outcome: | The proposed method outperforms exemplar replay-based approaches on lifelong intent detection tasks and achieves state-of-the-art on four public datasets. |
E-VarM: Enhanced Variational Word Masks to Improve the Interpretability of Text Classification Models (2022.coling-1)
Copied to clipboard
Ling Ge, ChunMing Hu, Guanghui Ma, Junshuang Wu, Junfan Chen, JiHong Liu, Hong Zhang, Wenyi Qin, Richong Zhang
| Challenge: | Empirical studies show that our approach outperforms the SOTA methods in improving the interpretability of text classification models. |
| Approach: | They propose an enhanced variational word masks approach that exploits the Variational Information Bottleneck to obtain task-specific words. |
| Outcome: | Empirical results show that the proposed method outperforms the SOTA methods in improving the interpretability of the model. |
A Hierarchical Neural Attention-based Text Classifier (D18-1)
Copied to clipboard
| Challenge: | Existing hierarchical classification models are unable to handle large corpora and the number of categories increases with increasing corpus. |
| Approach: | They propose to use external knowledge to introduce a hierarchical neural attention-based classifier to help with the classification of documents. |
| Outcome: | The proposed model performs better than or comparable to state-of-the-art hierarchical models at significantly lower computational cost while maintaining high interpretability. |
Leveraging Generative Large Language Models with Visual Instruction and Demonstration Retrieval for Multimodal Sarcasm Detection (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal sarcasm detection do not fully utilize cross-modal features, limiting their performance on in-domain datasets. |
| Approach: | They propose a multimodal sarcasm detection model with a designed instruction template and a demonstration retrieval module. |
| Outcome: | The proposed model outperforms existing methods on in-domain datasets and achieves state-of-the-art performance. |
Generative Text Modeling through Short Run Inference (2021.eacl-main)
Copied to clipboard
| Challenge: | Latent variable models for text capture global semantic and syntactic features when trained correctly. |
| Approach: | They propose a short run dynamics for inference that initializes from the prior distribution of the latent variable and runs a small number of Langevin dynamics steps guided by its posterior distribution. |
| Outcome: | The proposed model is able to generate coherent sentences with smooth transition and shows no sign of posterior collapse. |
Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences (C18-1)
Copied to clipboard
| Challenge: | Existing generative networks for rationale extraction have a trade-off between extracting diversified rationales and achieving good classification results. |
| Approach: | They propose a multilevel heuristic approach to regulate rationale extraction to avoid extracting monotonous rationales without compromising classification performance. |
| Outcome: | The proposed approach improves classification performance and interpretability 20% compared to state-of-the-art approaches. |
Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks? (2021.findings-acl)
Copied to clipboard
| Challenge: | In July 2019, RoBERTa was the first to surpass a human baseline on GLUE . since then, 13 more methods have outperformed humans on the GLu leaderboard . |
| Approach: | They found that 75% to 90% of correct predictions of BERT-based classifiers remain constant after input words are randomly shuffled. |
| Outcome: | The proposed model outperforms humans on GLUE and SQuAD 2.0. |
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for unknown intent detection are limited by prior knowledge of class labels. |
| Approach: | They propose to use a Gaussian mixture model to model utterance embeddings with a distribution and inject dynamic class semantic information into Gausssian means. |
| Outcome: | The proposed model performs well on three real task-oriented dialogue datasets in two languages. |
A Deep Neural Network Sentence Level Classification Method with Context Information (D18-1)
Copied to clipboard
| Challenge: | Existing methods that use context for sentence classification are difficult to scale . Usually, sentences are treated as separate instances for the task . however, in many situations the sentence that is the focus of classification appears in a context that can provide additional information. |
| Approach: | They propose a method that uses potentially large contexts to classify sentences . they use an LSTM, and short-span features to classize sentences based on a stacked CNN . |
| Outcome: | The proposed method consistently improves on two different datasets. |
Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Among recent NLP research, multi-document processing is gaining increasing attention due to the need to handle and process an increasing amount of textual data and available documents online. |
| Approach: | They propose to pre-train a generic multi-document model from a cross-document question answering pre-training objective by generating salient sentences from one document and challenging it to recover the sentence from which it was generated. |
| Outcome: | The proposed model outperforms zero-shot GPT-3.5 and GPT-4 in multiple document tasks and generates the correct answer and the salient sentence from a salient document. |
Bidirectional Reasoning Supervision for Multilingual Financial Decision Making (2025.emnlp-industry)
Copied to clipboard
Muhammad Rafsan Kabir, Jawad Ibn Ahad, Robin Krambroeckers, Silvia Ahmed, M M Lutfe Elahi, Nabeel Mohammed, Shafin Rahman
| Challenge: | Large Language Models have been used for sentiment analysis, machine translation, and question answering, but their effectiveness in the multilingual financial domain remains unknown. |
| Approach: | They propose a fine-tuning approach that integrates positive and negative rationales alongside classification labels. |
| Outcome: | The proposed approach outperforms existing methods across English, Hindi, Bengali, and Telugu, and is suitable for industry applications. |
A Combinatorial Approach to Neural Emergent Communication (2025.coling-main)
Copied to clipboard
| Challenge: | Existing research on emergent communication uses the Lewis signaling game . however, the training data is limited and the messages are often ineffective . |
| Approach: | They propose a combinatorial algorithm to solve the symbolic complexity for classification, which is the minimum number of symbols in the message for successful communication. |
| Outcome: | The proposed algorithm increases the number of effective symbols in the emergent language. |
Handling Ambiguity in Emotion: From Out-of-Domain Detection to Distribution Estimation (2024.acl-long)
Copied to clipboard
| Challenge: | Experimental results show that incorporating utterances without majority-agreed labels into an additional class reduces the classification performance of the other emotion classes. |
| Approach: | They propose to combine utterances without majority-agreed labels into an additional class . they propose to quantify uncertainty in emotion classification using evidential deep learning . |
| Outcome: | The proposed method retains classification accuracy while effectively detects ambiguous emotion expressions. |
EmoGist: Efficient In-Context Learning for Visual Emotion Understanding (2025.findings-emnlp)
Copied to clipboard
| 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. |
Polarized Opinion Detection Improves the Detection of Toxic Language (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating polarized annotations are un-normalized and difficult to exploit in machine learning. |
| Approach: | They propose a method for K-class text classification that exploits polarized texts in the dataset. |
| Outcome: | The proposed method exploits polarized texts in a dataset and can improve classification performance. |
“Chère maison” or “maison chère”? Transformer-based prediction of adjective placement in French (2023.findings-eacl)
Copied to clipboard
| Challenge: | Prior work has shown that transformer-based language models are insensitive to permutated word order, but this is not the case with pretraining. |
| Approach: | They conduct experiments to assess whether transformer-based language models are able to learn the adjective position in noun phrases in French. |
| Outcome: | The proposed model is weaker with complex structures and fixed expressions, but favors context and global syntactic roles. |
VAULT: VAriable Unified Long Text Representation for Machine Reading Comprehension (2021.acl-short)
Copied to clipboard
| Challenge: | Existing models on Machine Reading Comprehension (MRC) require complex model architecture for effectively modeling long texts with paragraph representation and classification, making inference computationally inefficient for production use. |
| Approach: | They propose a novel Gaussian distribution-based paragraph representation for Machine Reading Comprehension (MRC) that is light-weight and parallel-efficient. |
| Outcome: | The proposed model can achieve comparable performance on Wikipedia-based (NQ) and TechNotes (TechQA) with a state-of-the-art (SOTA) complex document modeling approach while being 16 times faster, demonstrating the efficiency of the proposed model. |
PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck (2024.findings-naacl)
Copied to clipboard
| Challenge: | CLIP-based classifiers rely on the prompt containing a class name that is known to the text encoder and perform poorly on new classes or the classes whose names rarely appear on the Internet. |
| Approach: | They propose to use a set of text descriptors to express a class name into a textual descriptable and match the embeddings of the detected parts to their textual ones to compute a logit score. |
| Outcome: | The proposed classifier outperforms CLIP-based classifiers on zero-shot and supervised learning settings by 88.80% and 92.20% accuracy on CUB-200 and Stanford Dogs-120. |
Nonparametric Masked Language Modeling (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing language models (LMs) predict tokens with a softmax over a finite vocabulary, which can make it difficult to predict rare tokens or phrases. |
| Approach: | They introduce a nonparametric masked language model that replaces a softmax with a distribution over every phrase in a reference corpus and uses an in-batch approximation to train it. |
| Outcome: | The proposed model outperforms larger parametric models on 16 tasks including classification, fact probing and question answering. |
Better Explain Transformers by Illuminating Important Information (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing explanations focus on the input and output of the Transformers, resulting in confusing results. |
| Approach: | They propose to highlight important information and eliminate irrelevant information by a refined information flow on top of the layer-wise relevance propagation method. |
| Outcome: | The proposed method outperforms baseline models on classification and question-answering datasets with over 3% to 33% improvement on explanation metrics. |
NeuroPrune: A Neuro-inspired Topological Sparse Training Algorithm for Large Language Models (2024.findings-acl)
Copied to clipboard
Amit Dhurandhar, Tejaswini Pedapati, Ronny Luss, Soham Dan, Aurelie Lozano, Payel Das, Georgios Kollias
| Challenge: | Transformer-based Language Models have become ubiquitous in natural language processing due to impressive performance on various tasks. |
| Approach: | They explore how sparsity affects network topology by exploiting mechanisms seen in biological networks . they show that model-agnostic sparsities are performant across diverse NLP tasks . |
| Outcome: | The proposed model-agnostic sparsity approaches are performant and efficient across NLP tasks. |
Event Detection as Graph Parsing (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to event detection focus on using syntactic dependency structures or external knowledge to boost the performance. |
| Approach: | They propose a graph parsing problem that explicitly models multiple event correlations and utilizes rich information conveyed by event type and subtype. |
| Outcome: | The proposed model outperforms existing models on the public ACE2005 dataset by 4.2% on the dataset. |
Inferring about fraudulent collusion risk on Brazilian public works contracts in official texts using a Bi-LSTM approach (2020.findings-emnlp)
Copied to clipboard
Marcos Lima, Roberta Silva, Felipe Lopes de Souza Mendes, Leonardo R. de Carvalho, Aleteia Araujo, Flavio de Barros Vidal
| Challenge: | Public works procurements are a preferred field for collusion and fraud in Brazil . current methods of fraud detection use structured data to classification and usually do not involve annotated data. |
| Approach: | They propose to use public works procurements to classify risky entries using a dataset of 15,132,968 textual entries of which 1,907 are annotated. |
| Outcome: | The proposed datasets show that both bottleneck deep neural network and biLSTM are competitive compared with classical classifiers and achieve better precision (93.0% and 92.4%, respectively). |
DRAFT: Dense Retrieval Augmented Few-shot Topic classifier Framework (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for few-shot topic classification are limited due to the volume of information pouring in from the Internet . a new framework is proposed to train a classifier for few shot topics . |
| Approach: | They propose a framework to train a classifier for few-shot topic classification using a customized dataset and a dense retriever model. |
| Outcome: | The proposed framework shows superior performance on few-shot topic classification tasks compared to baselines that use in-context learning . |
Take Off the Training Wheels! Progressive In-Context Learning for Effective Alignment (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have explored the working mechanisms of In-Context Learning (ICL) however, they mainly focus on classification and simple generation tasks, limiting their broader application to more complex generation tasks in practice. |
| Approach: | They propose an efficient Progressive In-Context Alignment method that embeds the task function learned from demonstrations into the separator token representation. |
| Outcome: | The proposed method surpasses vanilla ICL and achieves comparable performance to other alignment tuning methods. |
Enhancing Online Grooming Detection via Backtranslation Augmentation (2025.coling-main)
Copied to clipboard
| Challenge: | Existing models to detect predatory conversations for online conversation platforms are lacking in real-world applications due to sparse distribution of predatory conversation data. |
| Approach: | They propose backtranslation augmentation to augment training datasets with more predatory conversations by using 3 neural translators to augment them. |
| Outcome: | The proposed model improves with fewer training epochs for better classification efficacy on 8 languages from 4 language families and shows that it is more efficient than previous models. |
Controllable Sentence Simplification via Operation Classification (2022.findings-naacl)
Copied to clipboard
| Challenge: | Sentence simplification involves a sentence being transformed into a simpler version of itself while preserving its core meaning. |
| Approach: | They propose a controllable-simplification model that tailors simplifications to four global operations . they propose to use a dataset to train highly accurate classification systems for these operations based on syntactic or discourse structure . |
| Outcome: | The proposed model outperforms both end-to-end and controllable approaches in sentence simplification tasks. |
Message Passing on Semantic-Anchor-Graphs for Fine-grained Emotion Representation Learning and Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Emotion classification is an important task with applications in education, virtual reality, and robotics. |
| Approach: | They propose to use token embeddings to generate a "semantic-anchor graph" using semantic anchors, sentences can be projected onto them to form a graph . |
| Outcome: | Empirically, the proposed system can generate meaningful semantic anchors and discriminative graph patterns for different emotion. |
Multilingual Image Corpus – Towards a Multimodal and Multilingual Dataset (2022.lrec-1)
Copied to clipboard
| Challenge: | The goal of the project Multilingual Image Corpus is to provide a large image dataset with annotated objects and object descriptions in 24 languages. |
| Approach: | They propose to provide a large image dataset with annotated objects and object descriptions in 24 languages. |
| Outcome: | The project provides a large image dataset with annotated objects and object descriptions in 24 languages. |
HARALD: Augmenting Hate Speech Data Sets with Real Data (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Hate speech detection depends on the availability of variable labeled data. |
| Approach: | They propose a method that uses real unlabelled data from online platforms to augment existing models by harvesting and processing it. |
| Outcome: | The proposed approach improves the classification performance of hate speech classification models. |
Compressing then Matching: An Efficient Pre-training Paradigm for Multimodal Embedding (2026.acl-long)
Copied to clipboard
Da Li, Yuxiao Luo, Keping Bi, Jiafeng Guo, Wei Yuan, Biao Yang, Yan Wang, Fan Yang, Tingting Gao, Guorui Zhou
| Challenge: | Recent approaches demonstrate that MLLMs can be adapted into competitive embedding models via large-scale contrastive learning. |
| Approach: | They propose a compressed pre-training phase which serves as a warm-up stage for contrastive learning. |
| Outcome: | The proposed model achieves state-of-the-art among MLLMs of comparable size on the MMEB, realizing optimization in both efficiency and effectiveness. |
The Automatic Annotation of the Semiotic Type of Hand Gestures in Obama’ s Humorous Speeches (L18-1)
Copied to clipboard
| Challenge: | Existing studies on hand gestures from video-recorded speeches have not identified them. |
| Approach: | They annotated and analysed hand gestures produced by Barack Obama . they trained machine learning algorithms to classify the semiotic type of hand gesture . |
| Outcome: | The proposed method can be used to classify hand gestures on video-recorded speeches and in advanced multimodal interactive systems. |
FloDusTA: Saudi Tweets Dataset for Flood, Dust Storm, and Traffic Accident Events (2020.lrec-1)
Copied to clipboard
| Challenge: | Detecting events from tweets can help to predict real-world events precisely. |
| Approach: | They propose to use tweets written in Arabic and Saudi dialects to identify events from tweets. |
| Outcome: | The proposed system can detect flood, dust storm, traffic accident, and non-event. |
GRAMMAR-LLM: Grammar-Constrained Natural Language Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to fine-tuning and prompting are insufficient to ensure compliance with predefined taxonomies, syntactic structures, or domain-specific rules. |
| Approach: | They propose a framework that integrates formal grammatical constraints into the decoding process to enforce syntactic correctness in linear time while maintaining expressiveness in grammar rule definition. |
| Outcome: | The proposed framework enforces syntactic correctness in linear time while maintaining expressiveness in grammar rule definition. |
Learning Invariant Representations of Social Media Users (D19-1)
Copied to clipboard
| Challenge: | Existing methods for learning to compare social media users fail to generalize to new users or even to previously known users. |
| Approach: | They propose a procedure to learn a mapping from short episodes of user activity to a vector space in which the distance between points captures the similarity of the corresponding users’ invariant features. |
| Outcome: | The proposed procedure can be applied to users not seen at training time and enables efficient comparisons of users in the resulting vector space. |
FinMTEB: Finance Massive Text Embedding Benchmark (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing text embedding benchmarks for financial domains are inadequately addressing the nuanced requirements of specialized domains like finance. |
| Approach: | They propose a finance-adapted embedding model that outperforms general-purpose models . they also introduce a new model, Fin-E5, which is also open-sourced . |
| Outcome: | The proposed framework outperforms general-purpose models on financial embedding tasks. |
Granular Entity Mapper: Advancing Fine-grained Multimodal Named Entity Recognition and Grounding (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for fine-grained content extraction are limited by long-tailed distribution of textual entity categories and performance of object detectors. |
| Approach: | They propose a multi-granularity entity recognition module and a reranking module to integrate hierarchical information of entity categories, visual cues, and external textual resources collectively. |
| Outcome: | The proposed framework achieves state-of-the-art on the fine-grained content extraction task. |
ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification (2022.acl-long)
Copied to clipboard
| Challenge: | Existing work on event-centric reasoning fails to model event-level correlations . Existing studies limit their scope to specific scenarios or overlook event- level correlations. |
| Approach: | They propose to pre-train a general Correlation-aware context-to-Event Transformer for event-centric reasoning by highlighting event-level correlations with effective training. |
| Outcome: | The proposed model is applicable to a wide range of event-centric reasoning scenarios, considering its versatility of event correlation types, application formulations, and reasoning types. |
Rumor Detection on Twitter with Tree-structured Recursive Neural Networks (P18-1)
Copied to clipboard
| Challenge: | Existing methods for detecting rumors are difficult to implement and require a lot of effort. |
| Approach: | They propose two recursive neural models that follow tweets' propagation layouts to learn discriminative features from tweets and generate more powerful representations for rumors detection. |
| Outcome: | The proposed models perform better than state-of-the-art approaches on two public Twitter datasets and show superior performance on detecting rumors at very early stage. |
Speaker Turn Modeling for Dialogue Act Classification (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to DA classification model utterances without incorporating the turn changes among speakers throughout the dialogue, thus treating it no different than non-interactive written text. |
| Approach: | They propose to integrate the turn changes in conversations among speakers when modeling DAs by learning conversation-invariant speaker turn embeddings to represent speaker turns in a conversation. |
| Outcome: | The proposed model captures semantics from the dialogue content while accounting for different speaker turns in a conversation. |
A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks (2024.lrec-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have enabled advances in the field of natural language processing . however, their application and potential are still underexplored . |
| Approach: | They evaluate four state-of-the-art instruction-tuned Large Language Models on 13 NLP tasks in English. |
| Outcome: | The evaluated models outperform state-of-the-art models on 13 real-world clinical and biomedical NLP tasks in English. |
Efficient Annotator Reliability Assessment and Sample Weighting for Knowledge-Based Misinformation Detection on Social Media (2025.findings-naacl)
Copied to clipboard
Owen Cook, Charlie Grimshaw, Ben Peng Wu, Sophie Dillon, Jack Hicks, Luke Jones, Thomas Smith, Matyas Szert, Xingyi Song
| Challenge: | Misinformation spreads rapidly on social media, confusing the truth and targeting potentially vulnerable people. |
| Approach: | They propose to use inter- and intra-annotator agreement to understand the reliability of each annotator and influence the training of large language models based on annotators reliability. |
| Outcome: | The proposed framework utilises inter- and intra-annotator agreement to understand the reliability of each annotator and influence the training of large language models based on annotators reliability. |
Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding (2021.acl-long)
Copied to clipboard
| Challenge: | a benchmark corpus of text in 15 different styles is used to study stylistic language . a similar benchmark is used for cross-style language understanding . |
| Approach: | They propose a benchmark corpus that combines existing datasets and collects a new one for cross-style language understanding. |
| Outcome: | The proposed benchmark corpus contains 15 different styles under four theoretical groupings: figurative, personal, affective, and interpersonal groups. |
Recurrent Attention Networks for Long-text Modeling (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to encoding long documents using self-attention have been limited by quadratic computational complexities and limited application in long text processing. |
| Approach: | They propose a long-document encoding model that allows the recurrent operation of self-attention. |
| Outcome: | The proposed model extracts global semantics in token-level and document-level representations, making it inherently compatible with both sequential and sequential tasks. |
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation (2022.findings-acl)
Copied to clipboard
Tianxiang Sun, Xiangyang Liu, Wei Zhu, Zhichao Geng, Lingling Wu, Yilong He, Yuan Ni, Guotong Xie, Xuanjing Huang, Xipeng Qiu
| Challenge: | Existing methods to measure instance difficulty use generalization and threshold-tuning . a new approach to learn to exit is based on hash functions to assign tokens to a fixed exiting layer. |
| Approach: | They propose a Hash-based Early Exiting approach that replaces learn-to-exit modules with hash functions to assign each token to a fixed exiting layer. |
| Outcome: | The proposed approach improves on learning to exit and predicting instance difficulty. |
MIRTT: Learning Multimodal Interaction Representations from Trilinear Transformers for Visual Question Answering (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing bilinear methods focus on inter-modality information between images and questions . existing models focus on the interaction between images, questions, and images . |
| Approach: | They propose a trilinear interaction framework that incorporates attention mechanisms for capturing inter-modality and intra-modal relationships. |
| Outcome: | The proposed model outperforms bilinear models on the Visual7W Telling task and VQA-1.0 Multiple Choice task and outperformed baselines on the VQA, TDIUC and GQA datasets. |
Comparative Evaluation of Label-Agnostic Selection Bias in Multilingual Hate Speech Datasets (2020.emnlp-main)
Copied to clipboard
| Challenge: | a recent study has shown that data collection is neglected by ignoring the quality of data. |
| Approach: | They propose to use latent semantics to evaluate selection bias in hate speech . they compare latent Dirichlet Allocation (LDA) to eleven hate speech corpora . |
| Outcome: | The proposed method could be revisable before focusing on classification performance. |
ZeroAE: Pre-trained Language Model based Autoencoder for Transductive Zero-shot Text Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text classification use only encoders or decoders that do not allow for the use of labels in unseen domains. |
| Approach: | They propose an autoencoder that encodes text into two disentangled spaces and decodes it to generate text with labels in the unseen domains. |
| Outcome: | The proposed model outperforms the existing methods in label-partially-unseen and label-fully-un-seeen scenarios and even outperfects the SOTA methods. |
MetaICL: Learning to Learn In Context (2022.naacl-main)
Copied to clipboard
| Challenge: | Large language models can do in-context learning by conditioning on a few training examples with no parameter updates or task-specific templates. |
| Approach: | They propose a meta-training framework where a pretrained language model is tuned to do in-context learning on a large set of training tasks. |
| Outcome: | The proposed framework outperforms baseline models on 142 NLP datasets and a range of target tasks with domain shifts. |
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench (2025.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) and Multimodal Large Language models (MLLMs) trained on vast web corpora can memorize and disclose individuals’ confidential and private data, raising legal and ethical concerns. |
| Approach: | They propose a benchmark to assess unlearning algorithms from multiple perspectives and provide a baseline for existing generative models. |
| Outcome: | The proposed benchmark consists of 500 fictitious profiles and 153 profiles for public celebrities, evaluated from both multimodal (image+text) and unimodal (text) perspectives. |
How many data points is a prompt worth? (2021.naacl-main)
Copied to clipboard
| Challenge: | Proponents of prompting argue that they provide a method for injecting task-specific guidance, which is beneficial in low-data regimes. |
| Approach: | They aim to quantify prompting's benefit by testing prompts in a fair setting . they propose to use a generic model head or a task-specific prompt for prediction . |
| Outcome: | The proposed approach is used in T5 fine-tuning leading to state-of-the-art results on the SuperGLUE benchmark. |
SEP-MLDC: A Simple and Effective Paradigm for Multi-Label Document Classification (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods focus on optimizing document features, overlooking the potential of high-quality label features to enhance classification performance. |
| Approach: | They propose a multi-label document classification paradigm that utilizes large language models to expand the label content and generate pseudo-samples for the tail categories. |
| Outcome: | The proposed method significantly outperforms state-of-the-art models. |
Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Adaptive Retention is a probabilistic, layer-wise token selection mechanism that learns which representations to keep under a strict global budget M. |
| Approach: | They propose a probabilistic token selection mechanism that learns which representations to keep under a strict global budget M. |
| Outcome: | The proposed method reduces memory usage by 35–45% while improving throughput by 1.8. |
GigaCheck: Detecting LLM-generated Content via Object-Centric Span Localization (2026.findings-acl)
Copied to clipboard
Irina Tolstykh, Aleksandra Tsybina, Sergey Yakubson, Aleksandr Gordeev, Vladimir Dokholyan, Maksim Kuprashevich
| Challenge: | GigaCheck is a framework for AI-generated text detection. |
| Approach: | They propose a dual-strategy framework for AI-generated text detection . they leverage representation learning of fine-tuned LLMs to discern authorship . |
| Outcome: | The proposed framework can detect LLM-generated content with high accuracy and accuracy . it can be used in mixed-authorship scenarios and in academic collaborations . |
Automatically Creating a Lexicon of Verbal Polarity Shifters: Mono- and Cross-lingual Methods for German (C18-1)
Copied to clipboard
| Challenge: | a large number of verbal polarity shifters are available for multiple languages, but only English has a sizable lexicon of them. |
| Approach: | They use methods to create large lexicon of verbal polarity shifters in germany . they bootstrap annotated verbs with a supervised classifier and apply them to German . |
| Outcome: | The proposed method is able to create a large lexicon of verbal polarity shifters in germany . it reduces annotation effort by leveraging cross-lingual information from the English lexico . |
Incorporating Emoji Descriptions Improves Tweet Classification (N19-1)
Copied to clipboard
| Challenge: | Tweets are short messages that often include specialized language such as hashtags and emojis. |
| Approach: | They propose a simple strategy to replace emojis with their natural language description and use pretrained word embeddings to process tweets. |
| Outcome: | The proposed method is more effective than pretrained emoji embeddings for tweet classification. |
Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT (2021.eacl-main)
Copied to clipboard
| Challenge: | a recent study has shown that multilingual BERT encodes sentences in structurally meaningful ways. |
| Approach: | They analyze how morphosyntactic alignment manifests across embedding spaces of languages . they train classifiers to recover subjecthood of mBERT embedds in transitive sentences . |
| Outcome: | The proposed model encodes a high-order grammatical feature of morphosyntactic alignment across languages . the results show that the classifier distributions reflect the morphological alignment of their training languages based on the results . |
Universal Adversarial Triggers for Attacking and Analyzing NLP (D19-1)
Copied to clipboard
| Challenge: | Using adversarial triggers, a model can produce a specific prediction . adversarial attacks are useful for evaluation and interpretation . |
| Approach: | They propose a gradient-guided search over tokens that finds short adversarial triggers that successfully trigger the target prediction. |
| Outcome: | The proposed algorithm finds short trigger sequences that successfully trigger the target prediction. |
Controlling Out-of-Domain Gaps in LLMs for Genre Classification and Generated Text Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have pushed the boundaries of natural language processing, but their consistency is often limited when applied to unfamiliar domains. |
| Approach: | They propose a method that controls which predictive indicators are used and which are excluded during classification. |
| Outcome: | The proposed method reduces the OOD gap by up to 20 percentage points in a few-shot setup. |
MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Data (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for human trafficking detection ignore the multimodal nature of online ads . sex trafficking is a pervasive crime exploiting individuals of all ages and genders . |
| Approach: | They propose to use multimodal authorship attributes to identify suspicious ads that combine text and images to improve vendor identification and verification tasks. |
| Outcome: | The proposed model outperforms existing methods for vendor identification and verification tasks using text-only, vision-only and multimodal training objectives. |
Visual Supervision in Bootstrapped Information Extraction (D18-1)
Copied to clipboard
| Challenge: | a list-based interface populated with informative samples is effective for data annotation . a 2D scatterplot populated by diverse and representative samples yields improved models . |
| Approach: | They propose a list-based interface that can be used to build efficient and effective data annotation models. |
| Outcome: | The proposed model learns the distributional similarity of entities through the patterns that match them in a large corpus while being discriminative with respect to human-labeled and machine-promoted entities. |
Interactive Classification by Asking Informative Questions (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for intent classification rely on a single user input and do not interact with the user to reduce ambiguity and improve the final prediction. |
| Approach: | They propose a limited form of interaction to natural language intent classification . they add binary or multi-choice questions to the system to ask missing information . |
| Outcome: | The proposed method can be bootstrapped without interaction data and is scalable to two domains. |
X-Class: Text Classification with Extremely Weak Supervision (2021.naacl-main)
Copied to clipboard
| Challenge: | Weak supervision is a problem in text classification, but it requires corpusspecific knowledge. |
| Approach: | They propose a framework for extremely weak supervision that can be used to train a text classifier. |
| Outcome: | The proposed framework outperforms seed-driven weakly supervised methods on 7 benchmark datasets. |
CXR Data Annotation and Classification with Pre-trained Language Models (2022.coling-1)
Copied to clipboard
Nina Zhou, Ai Ti Aw, Zhuo Han Liu, Cher heng Tan, Yonghan Ting, Wen Xiang Chen, Jordan sim zheng Ting
| Challenge: | Existing tools for clinical data annotation are limited to specific institutions due to differences in writing style, structure, language use and label definition. |
| Approach: | They propose a weak supervision annotation framework with two improvements over existing ones . the framework provides an efficient form of sample selection and data auto-annotation . |
| Outcome: | The proposed framework provides better results for clinical data annotation tasks compared to existing frameworks. |
LARD: Large-scale Artificial Disfluency Generation (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing datasets suffer from class imbalance issues, causing performance problems . Disfluency detection is a critical task in real-time dialogue systems . |
| Approach: | They propose a method for generating complex and realistic artificial disfluencies with little effort using a large-scale dataset. |
| Outcome: | The proposed method can handle repetitions, replacements, and restarts on a large-scale dataset with disfluencies. |
Classifying Sluice Occurrences in Dialogue (L18-1)
Copied to clipboard
| Challenge: | Ellipsis is an important challenge for natural language processing systems, says a new paper . previous work on ellipsis focused on news data, but sluicing presents a challenge for dialogue systems . |
| Approach: | They describe a corpus of 4100 sluice occurrences from the NYTimes Gigaword corpus . they build a classifier model to automatically classify slujce . |
| Outcome: | The proposed corpus contains 4100 sluice occurrences, with an accuracy of 67% . the work will support empirical research into slujcing in dialogue systems . |
Academic-Industrial Perspective on the Development and Deployment of a Moderation System for a Newspaper Website (L18-1)
Copied to clipboard
| Challenge: | a system that supports the moderation of user comments on a large newspaper website is described in this paper. |
| Approach: | They describe an approach and experiences from the development, deployment and usability testing of a natural language processing and information retrieval system that supports the moderation of user comments on a large newspaper website. |
| Outcome: | The proposed system supports the moderation of user comments on a large newspaper website. |
The STEM-ECR Dataset: Grounding Scientific Entity References in STEM Scholarly Content to Authoritative Encyclopedic and Lexicographic Sources (2020.lrec-1)
Copied to clipboard
| Challenge: | a dataset for scientific entity extraction, classification, and resolution has been developed . a generic conceptual formalism for scientific entities is feasible, the authors say . |
| Approach: | They propose a STEM-ECR dataset that provides a domain-independent benchmark for scientific entity extraction, classification, and resolution tasks. |
| Outcome: | The proposed dataset provides a benchmark for evaluation of scientific entity extraction, classification, and resolution tasks in a domain-independent fashion. |
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models (2025.emnlp-main)
Copied to clipboard
Jiajun Zhou, Yifan Yang, Kai Zhen, Ziyue Liu, Yequan Zhao, Ershad Banijamali, Athanasios Mouchtaris, Ngai Wong, Zheng Zhang
| Challenge: | Large Language Models (LLMs) are quantized to lower precision to reduce memory cost and latency in inference. |
| Approach: | They propose a quantized zeroth-order framework for fine-tuning Large Language Models (LLMs) using low-precision forward passes. |
| Outcome: | The proposed method achieves comparable results to first-order methods in FP8 and superior accuracy in INT8 and INT4 training. |
vONTSS: vMF based semi-supervised neural topic modeling with optimal transport (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent Neural Topic Models (NTMs) have limited applications in the real world due to the challenge of incorporating human knowledge. |
| Approach: | They propose a semi-supervised neural topic modeling method, vONTSS, which uses von Mises-Fisher variational autoencoders and optimal transport. |
| Outcome: | The proposed method outperforms existing semi-supervised topic modeling methods on multiple aspects. |
Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown great potential for in-context learning, but their robustness and performance on downstream tasks remains limited. |
| Approach: | They propose to examine the reliance of LLMs on shortcuts or spurious correlations within prompts for downstream tasks and find larger models are more likely to utilize shortcuts in prompts during inference. |
| Outcome: | The proposed model is “lazy learner” and more likely to use shortcuts in prompts during inference. |
Exploring the Limitations of Detecting Machine-Generated Text (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in the quality of the generation of text by large language models have spurred research into identifying machine-generated text. |
| Approach: | They audit classification performance for detecting machine-generated text by evaluating on texts with varying writing styles. |
| Outcome: | The proposed methods are highly sensitive to stylistic changes and complexity, and in some cases degrade entirely to random classifiers. |
Pre-trained Token-replaced Detection Model as Few-shot Learner (2022.coling-1)
Copied to clipboard
| Challenge: | Pre-trained masked language models have demonstrated remarkable few-shot learning ability . a novel approach to few- shot learning with pre-tried token-replaced detection models is proposed . |
| Approach: | They propose a method to reformulate a classification or regression task as a token-replaced detection problem by using pre-trained token-based models. |
| Outcome: | The proposed approach outperforms pre-trained masked language models in learning tasks . it can learn models with a few examples and generalize well from limited examples like humans . |
Simple Algorithms For Sentiment Analysis On Sentiment Rich, Data Poor Domains. (C18-1)
Copied to clipboard
| Challenge: | Standard word embedding algorithms learn vector representations from large corpora of text documents in unsupervised fashion. |
| Approach: | They propose an algorithm that learns word embeddings jointly with a classifier . their algorithm leverages document label information to learn vector representations of words . |
| Outcome: | The proposed algorithm has superior performance on domains with limited data compared to other methods. |
Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing systems for detecting hateful memes lack sensitivity to subtle differences in memes that are vital for correct hatefulness classification. |
| Approach: | They propose to construct a hatefulness-aware embedding space through retrieval-guided contrastive training to identify hatefulness based on data unseen in training. |
| Outcome: | The proposed system outperforms existing models on the HatefulMemes dataset with an AUROC of 87.0 and improves contextual understanding across domains. |
Punctuation as Native Language Interference (C18-1)
Copied to clipboard
| Challenge: | Numerous aspects of written language have been studied for native language identification (NLI) but its impact has not been studied. |
| Approach: | They propose to use punctuation marks as indicators of native language . they propose to apply them to native language identification . |
| Outcome: | The proposed methods support the hypothesis that punctuation marks are persistent and robust indicators of the native language of the author, even when a high proficiency level in a non-native language is achieved. |
Improving Distantly-supervised Entity Typing with Compact Latent Space Clustering (N19-1)
Copied to clipboard
| Challenge: | Existing studies have addressed this problem with partial-label loss, but they suffer from confirmation bias, which means the classifier fit a pseudo data distribution given by itself. |
| Approach: | They propose to regularize distantly supervised models with Compact Latent Space Clustering to bypass this problem and effectively utilize noisy data yet. |
| Outcome: | The proposed model outperforms state-of-the-art models on standard benchmarks on fine-grained entity typing (FET) by a significant margin. |
A Neural Pairwise Ranking Model for Readability Assessment (2022.findings-acl)
Copied to clipboard
| Challenge: | Automatic Readability Assessment (ARA) is traditionally treated as a classification problem in NLP research. |
| Approach: | They propose a neural ranking approach to automatic readability assessment (ARA) they propose 'neural' ranking methods that can be used to rank texts by reading level . |
| Outcome: | The proposed approach performs well in monolingual single/cross corpus testing scenarios and achieves a zero-shot cross-lingual ranking accuracy of over 80% for both French and Spanish when trained on English data. |
Identifying Spurious Correlations for Robust Text Classification (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Text classifiers often rely on spurious correlations to predict positive reviews . term Spielberg does not cause the review to be positive, so it does not affect the classification accuracy. |
| Approach: | They propose a method to distinguish spurious and genuine correlations in text classification using treatment effect estimators. |
| Outcome: | The proposed method works well even with limited training examples and is possible to transport the word classifier to new domains. |
Attentively Embracing Noise for Robust Latent Representation in BERT (2020.coling-main)
Copied to clipboard
| Challenge: | Modern digital personal assistants interact with users through voice . high error rates still prevail in the widespread adoption of speech technology . |
| Approach: | They propose to extract more robust latent representations for noisy ASR text classification using transformer tokens and attentive embracement layer and multi-head attention layer. |
| Outcome: | The proposed model significantly outperforms the baseline model on the Chatbot and Snips corpora for intent classification with ASR error. |
Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing classification models only consider the temporal variations of existing data . current models focus on English corpora, leaving time as domains unexplored . |
| Approach: | They propose a framework to generalize classifiers over time on four languages, English, Danish, French, and German. |
| Outcome: | The proposed framework can generalize classifiers over time on four languages, English, Danish, French, and German. |
Cross-Modal Conceptualization in Bottleneck Models (2023.emnlp-main)
Copied to clipboard
Danis Alukaev, Semen Kiselev, Ilya Pershin, Bulat Ibragimov, Vladimir Ivanov, Alexey Kornaev, Ivan Titov
| Challenge: | Existing models that use text descriptions to predict labels are limited in their interpretations. |
| Approach: | They propose to use text descriptions to guide the induction of concepts in CBMs . they propose to employ a more moderate assumption and instead use text to guide induction . |
| Outcome: | The proposed model adopts a more moderate assumption and uses text descriptions to guide the induction of concepts. |
The Relevance of Value Systems for Offensive Language Detection (2026.eacl-long)
Copied to clipboard
| Challenge: | Recent research in perspectivism has departed from the assumption that offensiveness can be defined through a universal perspective. |
| Approach: | They propose to use a dataset consisting of neutrally-phrased sentences on controversial topics, evaluated by individuals from 4 different value systems to identify offensiveness patterns. |
| Outcome: | The proposed dataset consists of neutrally-phrased sentences on controversial topics, evaluated by individuals from 4 different value systems. |
Implications of Using Internet Sting Corpora to Approximate Underage Victims (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing systems for classification and triaging child exploitation cases require a high quality of data. |
| Approach: | They propose to annotate a corpus of underage victim chats with convicted predators to compare their goals and tactics. |
| Outcome: | The proposed model is based on a corpus of victim, vigilante, and LEO conversations with convicted predators. |
Learning to Rewrite: Generalized LLM-Generated Text Detection (2025.acl-long)
Copied to clipboard
| Challenge: | Existing detectors for Large Language Models (LLMs) struggle to generalize in open-world settings. |
| Approach: | They propose a framework to detect LLM-generated text with exceptional generalization to unseen domains by reinforcing LLMs’ inherent rewriting tendencies. |
| Outcome: | The proposed framework outperforms state-of-the-art detection methods by 23.04% in AUROC, 35.10% for out-of distribution tests, and 48.66% under adversarial attacks. |
Improving Out-of-Scope Detection in Intent Classification by Using Embeddings of the Word Graph Space of the Classes (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for intent classification use one-class classification or inverse dictionary. |
| Approach: | They propose to represent class labels as a vector space where word graphs are mapped . they use inverse dictionary to take in account inter-class similarities provided by repeated occurrences . |
| Outcome: | The proposed method beats the state-of-the-art method in the Larson dataset by about 31 percentage points. |
Exploiting Noisy Data in Distant Supervision Relation Classification (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to relation classification are noisy and time-consuming . RCEND uses noisy data to split noisy data into correctly and incorrectly labeled data . |
| Approach: | They propose a framework to enhance relation classification by exploiting noisy data . they use an instance discriminator with reinforcement learning to split noisy data into correctly and incorrectly labeled data based on the noisy data. |
| Outcome: | The proposed method outperforms the state-of-the-art models on relation classification . the proposed method is based on a semi-supervised learning method . |
Active Learning Principles for In-Context Learning with Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | In-context learning has significantly enhanced predictive performance in few-shot learning settings. |
| Approach: | They propose to use pool-based Active Learning to identify the most informative demonstrations for few-shot learning over a single iteration to identify best demonstrations. |
| Outcome: | The proposed model outperforms all other methods, including random sampling, in the analysis of 24 classification and multi-choice tasks. |
Do Models of Mental Health Based on Social Media Data Generalize? (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing literature on the validity of proxy-based methods for annotating mental health status in social media has raised new concerns regarding their use in clinical applications. |
| Approach: | They explore the generalization ability of machine learning classifiers trained to detect depression in individuals across multiple social media platforms. |
| Outcome: | The proposed methods show that they can be used to train and analyze large datasets and that they are robust to large dataset sizes. |
DivMerge: A divergence-based model merging method for multi-tasking (2026.eacl-long)
Copied to clipboard
| Challenge: | Existing methods for multitask learning struggle with interference between tasks, especially as the number of tasks grows. |
| Approach: | They propose a reference-free method that minimizes the divergence between models' outputs and those of the merged model, automatically balancing task importance. |
| Outcome: | The proposed method outperforms existing methods on classification and generative tasks and remains robust when scaling to more tasks. |
SciRepEval: A Multi-Format Benchmark for Scientific Document Representations (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing benchmarks for evaluating scientific document representations fail to capture the diversity of relevant tasks. |
| Approach: | They propose a benchmark for training and evaluating scientific document representations that includes 24 challenging and realistic tasks across four formats: classification, regression, ranking and search. |
| Outcome: | The proposed model outperforms existing models by over 2 points absolute. |
Synthesizing Adversarial Negative Responses for Robust Response Ranking and Evaluation (2021.findings-acl)
Copied to clipboard
| Challenge: | Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. |
| Approach: | They propose methods for automatically creating adversarial negative training data . they use mask-and-fill and keyword-guided approaches to generate negative examples . |
| Outcome: | The proposed approaches outperform baseline models in providing informative negative examples for training dialogue systems. |
Multitask Learning for Grapheme-to-Phoneme Conversion of Anglicisms in German Speech Recognition (2022.lrec-1)
Copied to clipboard
| Challenge: | Anglicisms are a challenge in German speech recognition due to their irregular pronunciation compared to native German words. |
| Approach: | They propose a multitask sequence-to-sequence approach for grapheme-tophoneme conversion to improve the phonetization of Anglicisms. |
| Outcome: | The proposed model reduces the word error rate by 1 % and the Anglicism error rate, while still maintaining the accuracy of the baseline model. |
Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts (D18-1)
Copied to clipboard
| Challenge: | Existing sentences classification models often classify sentences in isolation without considering the context in which sentences appear. |
| Approach: | They propose a hierarchical sequential labeling network to make use of contextual information within surrounding sentences to help classify the current sentence. |
| Outcome: | The proposed model outperforms the state-of-the-art methods by 2%-3% on two benchmarking datasets for sequential sentence classification in medical scientific abstracts. |
Finding the Optimal Vocabulary Size for Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Class imbalance is said to exist when one or more classes are not of approximately equal frequency in data. |
| Approach: | They cast neural machine translation (NMT) as a classification task in an autoregressive setting and examine its limitations. |
| Outcome: | The proposed model performs better on multiple languages with large data sizes with different vocabulary sizes. |
KNN-Contrastive Learning for Out-of-Domain Intent Classification (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for OOD intent classification are limited to regions with compact or simply-connected features, which assumes no OOD intentions reside. |
| Approach: | They propose a method that uses k-nearest neighbors to learn discriminative semantic features that are more conducive to OOD detection. |
| Outcome: | The proposed method improves OOD detection performance while requiring no restrictions on feature distribution. |
Finer: Investigating and Enhancing Fine-Grained Visual Concept Recognition in Large Vision Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in instruction-tuned Large Vision-Language Models (LVLMs) have imbued the models with the ability to generate high-level, image-grounded explanations with ease. |
| Approach: | They propose to use a multiple granularity attribute-centric benchmark and training mixture to evaluate LVLMs’ fine-grained visual comprehension ability. |
| Outcome: | The proposed model improves on LLaVa-1.5, InstructBLIP and GPT-4V and demonstrates that they struggle to generate descriptive visual attributes based on a concept that appears within an input image despite their prominent zero-shot image captioning ability. |
Tokenizer-Aware Cross-Lingual Adaptation of Decoder-Only LLMs through Embedding Relearning and Swapping (2026.eacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been primarily focused on English, leaving the multilingual ability unexplored. |
| Approach: | They propose a technique that creates new tokenizers and tunes embeddings on fixed model weights for target language adaptation. |
| Outcome: | The proposed method is light-weight and performant but has limitations for older models and high resource languages. |
FLamE: Few-shot Learning from Natural Language Explanations (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work has shown limited utility of natural language explanations in improving classification. |
| Approach: | They propose a two-stage few-shot learning framework that generates explanations and fine-tunes a smaller model with generated explanations. |
| Outcome: | The proposed framework increases inference accuracy over strong baselines, but human evaluation reveals that the majority of generated explanations does not adequately justify classification decisions. |
XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods for active learning rely on model uncertainty or disagreement to pick unlabeled data, leading to over-confidence in superficial patterns and lack of exploration. |
| Approach: | They propose to use a bi-directional encoder and a uni-directional decoder to generate and score an explanation for low-resource text classification. |
| Outcome: | The proposed model improves on 9 strong baselines on six datasets and can generate explanations for its predictions. |
Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task (2022.lrec-1)
Copied to clipboard
| Challenge: | Numerical tables are widely used to communicate or report the classification performance of machine learning models with respect to a set of evaluation metrics. |
| Approach: | They propose a task where neural models are trained to generate textual explanations based on the metrics’ scores reported in numerical tables. |
| Outcome: | The proposed model outperforms existing methods and can be used to explain the performance of ML models. |
Efficient Sentence Embedding using Discrete Cosine Transform (D19-1)
Copied to clipboard
| Challenge: | Modern NLP systems rely on word embeddings as input units to encode statistical semantic and syntactic properties of words. |
| Approach: | They propose to use discrete cosine transform to compress word sequences in order-preserving manner. |
| Outcome: | The proposed model preserves syntactic information in semantic probing tasks . it is comparable to vector averaging but mediocre in performance. |
A Shared-Private Representation Model with Coarse-to-Fine Extraction for Target Sentiment Analysis (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models with span-based labeling have achieved promising results in sentiment analysis. |
| Approach: | They propose a shared-private representation model with a coarse-to-fine extraction algorithm to solve this problem. |
| Outcome: | The proposed model achieves state-of-the-art on target phrases and extraction tasks. |
Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent large language models have demonstrated improved processing of complex language, but detecting logical fallacies remains a challenge. |
| Approach: | They propose a prompt formulation approach for logical fallacy detection that integrates contextual information into input text and queries for validity within the argument’s context. |
| Outcome: | The proposed approach improves over state-of-the-art models by 0.57 in F1-scores and 0.45 in fine-tuned models. |
Patton: Language Model Pretraining on Text-Rich Networks (2023.acl-long)
Copied to clipboard
| Challenge: | Existing models for text-rich networks do not take inter-document structure into account. |
| Approach: | They propose a pretraining framework for a text-rich network using a masked language model and a masking node prediction framework. |
| Outcome: | The proposed model outperforms baselines on four tasks in academic and e-commerce domains. |
ESG-Kor: A Korean Dataset for ESG-related Information Extraction and Practical Use Cases (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained language models are exhibiting astonishing performances in various natural language processing tasks, including classification, question answering, machine translation, summarization, and conversation generation. |
| Approach: | They built a Korean dataset to automatically extract Environmental, Social, and Governance (ESG) information from Korean companies’ sustainability reports and manually labeled it according to objective rules provided by ESG evaluation agencies. |
| Outcome: | The proposed dataset extracts environmental, social, and governance information from Korean companies’ sustainability reports and labels it according to objective rules provided by ESG evaluation agencies. |
Multitask Learning for Emotionally Analyzing Sexual Abuse Disclosures (2021.naacl-main)
Copied to clipboard
| Challenge: | Prior work on identifying narratives related to sexual abuse disclosures did not consider this as an independent task. |
| Approach: | They propose to identify narratives related to sexual abuse disclosures as a joint modeling task that leverages their emotional attributes through multitask learning. |
| Outcome: | The proposed model leverages emotional attributes of textual conversations to identify narratives related to sexual abuse disclosures in homogeneous and heterogeneously settings. |
Cross-Cultural Transfer Learning for Text Classification (D19-1)
Copied to clipboard
| Challenge: | a large dataset is required to achieve competitive performance in most natural language tasks. large datasets are expensive, time consuming, and error-prone. |
| Approach: | They propose a transfer-learning framework that leverages bilingual corpora for natural language text classification using no task-specific data. |
| Outcome: | The proposed framework can achieve good performance on formality classification and sarcasm detection tasks without any task-specific labeled data. |
Distributional Term Set Expansion (L18-1)
Copied to clipboard
| Challenge: | Iterative term set expansion methods for distributional semantic models are used to label terms belonging to a sought after term set. |
| Approach: | They compare iterative term set expansion methods for distributional semantic models to the Simple Margin method, an active learning approach to classification using Support Vector Machines. |
| Outcome: | The proposed methods outperform centrality and classification based methods for distributional semantic models over five different term sets. |
Consistent Prototype Learning for Few-Shot Continual Relation Extraction (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for few-shot continual relation extraction are overfitting memory samples, resulting in insufficient activation of old relations and limited ability to handle confusion of similar classes. |
| Approach: | They propose a few-shot continual relation extraction task that uses memory-enhanced modules to train a model on incrementally few-shot data to avoid forgetting old relations. |
| Outcome: | The proposed method outperforms existing methods on two commonly-used datasets. |
Consistency Training with Virtual Adversarial Discrete Perturbation (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for regularizing a model are agnostic to the training model and may not be effective for perturbed inputs. |
| Approach: | They propose an augmentation method of adding a discrete noise that would incur the highest divergence between predictions by replacing tokens while keeping original semantics. |
| Outcome: | The proposed method outperforms baselines on semi-supervised text classification tasks and a robustness benchmark. |
Label Augmentation for Zero-Shot Hierarchical Text Classification (2024.acl-long)
Copied to clipboard
| Challenge: | Hierarchical Text Classification is a difficult problem due to the lack of labeled data and the cost of manually annotating data samples. |
| Approach: | They propose a method that uses a Large Language Model to augment the deepest layer of the labels hierarchy to enhance its specificity. |
| Outcome: | The proposed method achieves state-of-the-art on four public datasets and a strong correlation between the metric values and the classification performance. |
AESOP: Paraphrase Generation with Adaptive Syntactic Control (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for paraphrase generation use fixed syntactic structures for all input sentences. |
| Approach: | They propose to add syntactical control to a pretrained language model to generate fluent paraphrases using a retrieval-based selection module. |
| Outcome: | The proposed model achieves state-of-the-art on semantic preservation and syntactic conformation on two benchmark datasets with ground-truth syntaktic control from human-annotated exemplars. |
ModaFact: Multi-paradigm Evaluation for Joint Event Modality and Factuality Detection (2025.coling-main)
Copied to clipboard
| Challenge: | NLP studies have mostly dealt with factuality and modality separately . linguistic modality conveys the relationship a situation is supposed to have with respect to wishes, norms, goals, authority, etc. |
| Approach: | They propose a resource with joint factuality and modality information for event-denoting expressions in Italian. |
| Outcome: | The proposed resource is consistent with existing ones and compares classification systems trained on italy's ModaFact dataset and best-performing model. |
Generalists vs. Specialists: Evaluating Large Language Models for Urdu (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Urdu is underrepresented in natural language processing, yet it is underserved. |
| Approach: | They compare general-purpose models with special-purpose ones that have been fine-tuned on specific tasks. |
| Outcome: | The proposed models outperform general-purpose models on seven classification and seven generation tasks. |
Late Fusion of Transformers for Sentiment Analysis of Code-Switched Data (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Code-switching is a common phenomenon in multilingual communities . however, sentiment analysis of code-switch data is elusive and unexplored . |
| Approach: | They propose to combine two transformers using logits of their output and feed them to a neural network for sentiment analysis. |
| Outcome: | The proposed system achieves an F1 score of 73.66% for English-Hi and 61.24% for English . it outperforms the best model reported for the GLUECoS benchmark dataset. |
Two-level classification for dialogue act recognition in task-oriented dialogues (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for dialogue act classification are limited and feature sets are low . recognizing dialogue acts is useful for identifying type of information and knowledge to be conveyed . |
| Approach: | They propose a 2-level classification technique, distinguishing between generic and specific dialogue acts (DA) they propose an efficient approach for specific DA, based on high-level linguistic features. |
| Outcome: | The proposed method outperforms classical methods for DA classification by including high-level features. |
Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA (2025.emnlp-main)
Copied to clipboard
Sergey Pletenev, Maria Marina, Nikolay Ivanov, Daria Galimzianova, Nikita Krayko, Mikhail Salnikov, Vasily Konovalov, Alexander Panchenko, Viktor Moskvoretskii
| Challenge: | Large Language Models (LLMs) often struggle with question answering due to hallucinated answers. |
| Approach: | They propose a multilingual QA dataset with evergreen labels that can be used to evaluate and train large language models. |
| Outcome: | The proposed model performs well on 12 modern LLMs and EG-E5 classifiers. |
HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to extract relational feature signals from natural language sentences use self-supervised clustering and classification that cause gradual drift problems. |
| Approach: | They propose a framework that derives hierarchical signals from relational feature space using cross hierarchy attention and effectively optimizes relation representation of sentences under exemplar-wise contrastive learning. |
| Outcome: | The proposed framework can extract the relationship between entities from natural language sentences without prior knowledge on relation scope or distribution. |
The Impact of Demonstrations on Multilingual In-Context Learning: A Multidimensional Analysis (2024.findings-acl)
Copied to clipboard
Miaoran Zhang, Vagrant Gautam, Mingyang Wang, Jesujoba Alabi, Xiaoyu Shen, Dietrich Klakow, Marius Mosbach
| Challenge: | In-context learning is a popular inference strategy where large language models solve a task using only a few labeled demonstrations without updating the model parameters. |
| Approach: | They conduct multidimensional analysis of multilingual in-context learning using 5 models from different model families and 9 datasets covering classification and generation tasks. |
| Outcome: | The results show that demonstrations vary significantly across models, tasks, and languages. |
Identifying Motion Entities in Natural Language and A Case Study for Named Entity Recognition (2020.coling-main)
Copied to clipboard
| Challenge: | Identifying motion entities in text is not only challenging but beneficial for a better natural language understanding. |
| Approach: | They propose a Motion Entity Tagging model to identify entities in motion in a text using the Literal-Motion-in-Text dataset for training and evaluating the model. |
| Outcome: | The proposed method improves the Named-Entity Recognition task by splitting clauses and phrases from complex and long motion sentences. |
Multi-Domain Goal-Oriented Dialogues (MultiDoGO): Strategies toward Curating and Annotating Large Scale Dialogue Data (D19-1)
Copied to clipboard
| Challenge: | a large number of goal-oriented dialogue datasets are limited in their size, linguistic diversity, domain coverage, or annotation granularity. |
| Approach: | They propose a multi-domain goal-oriented dialogue dataset that uses a crowd-sourced worker and a trained annotator to curate and annotate large scale data. |
| Outcome: | The proposed dataset is 8 times the size of the largest comparable dialogue dataset available to the public. |
Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) with chat interfaces are increasingly popular in various scientific fields, for a variety of tasks related to social science research questions. |
| Approach: | They propose to use large language models to combine human and machine expertise to improve their models' performance. |
| Outcome: | The proposed model performs better with co-created definitions than with expert-written definitions. |
Interpreting Sentiment Composition with Latent Semantic Tree (2023.findings-acl)
Copied to clipboard
| Challenge: | Current researches on sentiment classification are shifting from improving model performance to interpretability. |
| Approach: | They propose a new tree form capable of interpreting sentiment composition in a principled way. |
| Outcome: | The proposed tree can explain sentiment composition in a principled way. |
FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining (2026.acl-long)
Copied to clipboard
| Challenge: | Existing audio-language models excel at clip-level understanding but struggle with frame-level tasks. |
| Approach: | They propose a novel training paradigm that advances both clip- and frame-level alignment in CLAP with heterogeneous data. |
| Outcome: | The proposed training paradigm improves both clip- and frame-level alignment in CLAP with heterogeneous data. |
Multilingual and Multi-Aspect Hate Speech Analysis (D19-1)
Copied to clipboard
| Challenge: | Current research on hate speech analysis is oriented towards monolingual and single classification tasks. |
| Approach: | They propose to use a multilingual multi-aspect hate speech analysis dataset to test current methods . they evaluate the dataset in various classification settings and discuss how to leverage annotations . |
| Outcome: | The proposed dataset can be used to improve hate speech detection and classification in general. |
Simple Recurrent Units for Highly Parallelizable Recurrence (D18-1)
Copied to clipboard
| Challenge: | recurrent neural networks scale poorly due to the intrinsic difficulty in parallelizing their state computations. |
| Approach: | They propose a simple recurrent unit that provides expressive recurrence and allows highly parallel implementation. |
| Outcome: | The proposed model achieves 5—9x speed-up over cuDNN-optimized LSTM on classification and question answering datasets and delivers stronger results than LS and convolutional models. |
DrBenchmark: A Large Language Understanding Evaluation Benchmark for French Biomedical Domain (2024.lrec-main)
Copied to clipboard
Yanis Labrak, Adrien Bazoge, Oumaima El Khettari, Mickael Rouvier, Pacome Constant Dit Beaufils, Natalia Grabar, Béatrice Daille, Solen Quiniou, Emmanuel Morin, Pierre-Antoine Gourraud, Richard Dufour
| Challenge: | Existing benchmarks for pre-trained language models are limited to only a few languages . a limited number of tasks are evaluated on non-standardized protocols . |
| Approach: | They propose to aggregate diverse downstream tasks into a benchmark to assess PLMs' qualities . they evaluate 8 pre-trained masked language models on general and biomedical-specific data . |
| Outcome: | The proposed benchmark assesses pre-trained language models on 20 diversified tasks. |
DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to augment self-training (ST) in attribute-controllable language generation are limited and limited. |
| Approach: | They propose a new ST framework that integrates self-generated pseudo text into attribute-controllable language generation. |
| Outcome: | The proposed framework can be applied to semi-supervised controllable language generation. |
Modeling Dutch Medical Texts for Detecting Functional Categories and Levels of COVID-19 Patients (2022.lrec-1)
Copied to clipboard
Jenia Kim, Stella Verkijk, Edwin Geleijn, Marieke van der Leeden, Carel Meskers, Caroline Meskers, Sabina van der Veen, Piek Vossen, Guy Widdershoven
| Challenge: | Electronic Health Records contain a lot of information in natural language that is not expressed in structured clinical data. |
| Approach: | They propose a Dutch language model that can determine the functional level of patients according to a WHO coding framework. |
| Outcome: | The proposed model can determine the functional level of patients according to a WHO coding framework. |
Educational Dialogue Systems for Visually Impaired Students: Introducing a Task-Oriented User-Agent Corpus (2024.lrec-main)
Copied to clipboard
Elisa Di Nuovo, Manuela Sanguinetti, Pier Felice Balestrucci, Luca Anselma, Cristian Bernareggi, Alessandro Mazzei
| Challenge: | a corpus of real-world dialogues between visually impaired users and an agent is described . the corpus is part of a larger research project aimed at developing tools for easier access to educational content for visually impaired people. |
| Approach: | They describe a corpus consisting of real-world dialogues between users and a task-oriented conversational agent . they report the results of a classification experiment on the annotated corpus and an additional experiment to assess the annotation capabilities of three large language models. |
| Outcome: | The proposed corpus is part of a larger research project aimed at improving visual aids for visually impaired users. |
DCE-LLM: Dead Code Elimination with Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Dead code can obscure logical errors and be exploited for obfuscation in malware. |
| Approach: | They propose a framework for automated dead code elimination using a codeBERT model with an attribution-based line selector. |
| Outcome: | Experimental results show that DCE-LLM outperforms existing tools for dead code elimination . dead code can obscure logical errors and be exploited for obfuscation in malware . |
From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities, making failures unverifiable. |
| Approach: | They propose a multimodal benchmark that features real-world landmarks with annotations across multiple viewpoints and a framework that treats visual elements as first-class retrieval units through three stages: element-level detection and classification, multi-granularity cross-modal alignment for evidence retrieval, and attribution-constrained generation. |
| Outcome: | The proposed framework achieves up to 29.2% improvement over six strong baselines for this task. |
Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its Applications (2025.emnlp-main)
Copied to clipboard
Kai Tang, Rui Wang, Renyu Zhu, Minmin Lin, Xiao Ding, Tangjie Lv, Changjie Fan, Runze Wu, Haobo Wang
| Challenge: | Existing methods for personality analysis treat corpus as a single unit for classification, but this approach presents several challenges. |
| Approach: | They propose a task paradigm for text-based personality representation learning that uses a triplet personality trend comparison dataset to learn single-sentence personality embeddings with desirable metric properties. |
| Outcome: | The proposed model significantly boosts performance across various applications, including personality detection, personality retrieval, and emotion translation prediction. |
Benchmarking Large Language Model Capabilities for Conditional Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Autoregressive and pre-trained large language models have shifted the field from application-specific to generation-based approaches. |
| Approach: | They propose to adapt existing application-specific generation benchmarks to pre-trained large language models to better suit different tasks. |
| Outcome: | The proposed models differ in their applicability to different data regimes and their generalization to multiple languages. |
A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning disentangled representations of textual data are difficult to implement and suffer from the degeneracy of other losses in multi-class scenarios. |
| Approach: | They propose a variational upper bound to the mutual information between an attribute and the latent code of an encoder that controls the approximation error. |
| Outcome: | The proposed method is superior on fair classification and on textual style transfer tasks. |
Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge-based visual question answering systems rely on Concept-Net and Wikipedia to obtain external knowledge. |
| Approach: | They propose a visual retriever-reader pipeline that uses a natural language knowledge base and a Visual retriever to retrieve relevant knowledge. |
| Outcome: | The proposed method significantly improves the visual retriever-reader pipeline on the OK-VQA benchmark. |
A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature (D19-1)
Copied to clipboard
| Challenge: | Existing academic search engines cannot detect relevant papers where a resource is mentioned. |
| Approach: | They propose a framework to model the role and function of on-line resource citations . they construct a dataset SciRes, which includes 3,088 manually annotated resource contexts based on a multi-task framework . |
| Outcome: | The proposed model achieves the best results on both the classification task and recommendation task. |
Towards Distribution-shift Robust Text Classification of Emotional Content (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work has shown that supervised models are more robust to change in domain and distribution, but the decrease in performance due to the distribution shift is still a major issue for supervised systems. |
| Approach: | They propose to fine-tune supervised models on task-specific datasets to achieve out-of-distribution performance. |
| Outcome: | The proposed model outperforms all available models in distribution and out of distribution with only a few thousand training samples. |
SPECTRA: Sparse Structured Text Rationalization (2021.emnlp-main)
Copied to clipboard
| Challenge: | Sparse attention mechanisms are a deterministic alternative, but they lack a way to regularize rationale extraction. |
| Approach: | They propose a framework for deterministic extraction of structured explanations via constrained inference on a factor graph, forming a differentiable layer. |
| Outcome: | The proposed framework outperforms previous studies on performance and plausibility of extracted rationales. |
Adapting Serious Game for Fallacious Argumentation to German: Pitfalls, Insights, and Best Practices (L18-1)
Copied to clipboard
| Challenge: | 'homeschooling' and 'death penalty' are non-existent in Germany, while being highly controversial topics of discussion in the United States. |
| Approach: | They propose to port Argotario (serious game for learning argumentation fallacies) to another language and analyze users' behavior and in-game created data to assess dissemination strategies and qualitative aspects of the resulting corpus. |
| Outcome: | The proposed game is based on a German-based game platform that can be used to learn argumentation fallacies. |
Generating Hashtags for Short-form Videos with Guided Signals (2023.acl-long)
Copied to clipboard
Tiezheng Yu, Hanchao Yu, Davis Liang, Yuning Mao, Shaoliang Nie, Po-Yao Huang, Madian Khabsa, Pascale Fung, Yi-Chia Wang
| Challenge: | Short-form video hashtag recommendation (SVHR) is a classification or ranking problem that selects hashtags from a set of limited candidates. |
| Approach: | They propose a short-form video hashtag recommendation task that better represents how hashtags are created naturally by retrieving relevant hashtags from a large-scale hashtag pool as extra guidance signals. |
| Outcome: | The proposed model outperforms strong classification baselines on two short-form video datasets and the guidance signals boost the performance by 8.11 and 2.17 absolute ROUGE-1 scores on average. |
Enhancing Knowledge Selection via Multi-level Document Semantic Graph (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods view knowledge selection as a sentence matching or classification. Existing techniques can’t capture the semantic relationships within complex documents. |
| Approach: | They propose a method that can construct multi-level document semantic graph from the grounding document and store semantic relationships within the documents effectively. |
| Outcome: | The proposed method can store semantic relationships within documents effectively and efficiently and achieve state-of-the-art results on public datasets. |
Main Predicate and Their Arguments as Explanation Signals For Intent Classification (2025.naacl-long)
Copied to clipboard
| Challenge: | Intent classification is crucial for conversational agents, and deep learning models perform well in this area due to the lack of suitable benchmark data. |
| Approach: | They propose a technique to augment text samples from intent classification datasets with word-level explanations by marking main predicates and their arguments as explanation signals. |
| Outcome: | The proposed method augments text samples from intent classification datasets with word-level explanations. |
An Element-aware Multi-representation Model for Law Article Prediction (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that using law articles as external knowledge can improve the performance of the Legal Judgment Prediction. |
| Approach: | They propose a Law Article Element-aware Multi-representation Model which makes full use of law article information and can be used for multi-label samples. |
| Outcome: | The proposed model improves the accuracy of 5.84%, macro F1 of 6.42%, and micro F1 by 4.28% compared with baseline models like TopJudge. |
LiveFact: A Dynamic, Time-Aware Benchmark for LLM-Driven Fake News Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Current evaluation frameworks are static and vulnerable to benchmark data contamination . current models are ineffective at assessing reasoning under temporal uncertainty . |
| Approach: | They propose a live-based benchmark that simulates the real-world "fog of war" they propose evaluating models on their ability to reason with evolving, incomplete information . |
| Outcome: | The proposed model outperforms proprietary state-of-the-art models in classification and evidence mode . it also provides a component to monitor BDC explicitly . |
Shallow Domain Adaptive Embeddings for Sentiment Analysis (D19-1)
Copied to clipboard
| Challenge: | Existing domain adaptation algorithms for text classification are limited by lack of training data and exploiting domain idiosyncrasies to improve performance. |
| Approach: | They propose a domain adaptation layer that learns weights to combine a generic and a specific word embedding into a DA embeddable. |
| Outcome: | The proposed approach improves on binary and multi-class classification tasks using popular encoder architectures. |
Predicting the Proficiency Level of Nonnative Hebrew Authors (2022.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that nonnative Hebrew learners can be accurately predicted from their essays . the proficiency level of nonnativ speakers is important for educational purposes . |
| Approach: | They propose to use feature-based classifiers to accurately predict the proficiency level of nonnative Hebrew learners. |
| Outcome: | The proposed classifiers can predict the proficiency level of nonnative Hebrew learners . the results are compared with human graders on a corpus of Hebrew essays . |
The Lou Dataset - Exploring the Impact of Gender-Fair Language in German Text Classification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Gender-fair language fosters inclusion by addressing all genders or using neutral forms. |
| Approach: | They present a dataset that provides high-quality reformulations for German text classification . they find substantial label flips, reduced prediction certainty, and altered attention patterns . |
| Outcome: | The proposed dataset provides high-quality reformulations for German text classification . it finds label flips, reduced prediction certainty, and significantly altered attention patterns . |
Extending LLMs to New Languages: A Case Study of Llama and Persian Adaptation (2025.coling-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are mainly trained on English data and struggle with low-resource languages. |
| Approach: | They propose to add a new language to Llama to improve classification accuracy for Persian tasks by aligning representations through bilingual pretraining and instruction datasets. |
| Outcome: | The proposed model performs on generation and classification tasks with no adverse impact and sometimes even improvements on English tasks. |
Two Birds One Stone: Dynamic Ensemble for OOD Intent Classification (2023.acl-long)
Copied to clipboard
| Challenge: | Out-of-domain (OOD) intent classification is an active field of natural language understanding . previous studies have suggested that PTMs would be "overthinking" the semantic features of the sample in the open-world scenario . |
| Approach: | They propose a method that allows the model to decide whether to make a decision on OOD classification early during inference. |
| Outcome: | The proposed method can improve inference speed and achieve significant performance improvements. |
P2P: A Poison-to-Poison Remedy for Reliable Backdoor Defense in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Defending Large Language Models (LLMs) against backdoors has long been trapped in a "cat-and-mouse" dilemma where defenders passively react to ever-shifting attack strategies. |
| Approach: | They propose a general and effective defense algorithm that implants benign triggers to reshape the model’s decision boundary. |
| Outcome: | The proposed defense algorithm can neutralize malicious backdoors while preserving task performance. |
Multitask-Bench: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning (2025.coling-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis. |
| Approach: | They propose to fine-tune LLMs on benign (non-harmful) data to ensure safe outputs. |
| Outcome: | The proposed model reduces attack success rates across a range of tasks without compromising its usefulness. |
Figurative Language Processing: A Linguistically Informed Feature Analysis of the Behavior of Language Models and Humans (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent years have witnessed a growing interest in investigating what Transformer-based language models (TLMs) actually learn from training data. |
| Approach: | They propose to use a black-box TLM and two intrinsically transparent white-box models to investigate the performance of figurative language models on sarcasm, similes, idioms, and metaphors. |
| Outcome: | The proposed models perform better than other models on figurative language classification tasks. |
GrASP: A Library for Extracting and Exploring Human-Interpretable Textual Patterns (2022.lrec-1)
Copied to clipboard
| Challenge: | a Python library is available for extracting patterns from textual data. |
| Approach: | They propose a Python library for extracting patterns from textual data . it integrates a public implementation of the existing GrASP algorithm . |
| Outcome: | The proposed library integrates a public implementation of the existing GrASP algorithm. |
Building a Sentiment Corpus of Tweets in Brazilian Portuguese (L18-1)
Copied to clipboard
| Challenge: | Sentiment analysis is a popular area of Natural Language Processing due to its subjective and semantic characteristics. |
| Approach: | They propose to annotate Brazilian Portuguese sentences manually using a sentiment corpus . they run experiments on polarity classification using six machine learning classifiers . |
| Outcome: | The proposed method is based on a Brazilian Portuguese sentiment corpus and achieved 80.38% on F-Measure and 64.87% when including the neutral class. |
Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completion (2025.findings-acl)
Copied to clipboard
| Challenge: | Using later reasoning steps does not always improve classification, suggesting LLMs encode key information early. |
| Approach: | They propose a method to predict the success of a zero-shot Chain-of-Thought process by using LLM representations that are based on initial steps representations. |
| Outcome: | The proposed method performs well even before a single token is generated, suggesting that crucial information about the reasoning process is already present in the initial steps representations. |
Rationalizing Transformer Predictions via End-To-End Differentiable Self-Training (2024.emnlp-main)
Copied to clipboard
| Challenge: | Neural networks are increasingly prevalent across a wide range of applications, driving significant advancements in fields such as natural language processing, computer vision, and beyond. |
| Approach: | They propose an end-to-end differentiable training paradigm for stable training of a rationalized transformer classifier. |
| Outcome: | The proposed model is capable of classifying a sample and scoring input tokens without any explicit supervision and produces class-wise rationales without instabilities. |
Machine Reading of Historical Events (2020.acl-main)
Copied to clipboard
| Challenge: | Using a short text description of an event, we can extract relevant sentences from Wikipedia and apply a combination of task-specific and general-purpose feature embeddings for the classification. |
| Approach: | They propose to use Wikipedia sentences to extract relevant sentences and apply feature embeddings to the task. |
| Outcome: | The proposed model outperforms the historical event ordering task and the event focus time task in the literature. |
Self-Training for Sample-Efficient Active Learning for Text Classification with Pre-Trained Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to train models without labeled data are lacking in supervised tasks . a lack of labeles is the main obstacle to real-world applications . |
| Approach: | They propose a semi-supervised approach that uses a model to obtain pseudo-labels for unlabeled data. |
| Outcome: | The proposed method outperforms the reproduced methods on four text classification benchmarks. |
Chat or Learn: a Data-Driven Robust Question-Answering System (2020.lrec-1)
Copied to clipboard
| Challenge: | QA systems tend to perform poorly at chitchat, while data-driven chatbots are typically user-friendly but not goal-oriented . |
| Approach: | They propose to use a controller to perform dialogue act classification and feed user input either to a sequence-to-sequence chatbot or to QA systems. |
| Outcome: | The proposed system is a spoken QA application for the Google Home smart speaker. |
Argument-based Detection and Classification of Fallacies in Political Debates (2023.emnlp-main)
Copied to clipboard
| Challenge: | Fallacies are arguments that employ faulty reasoning, causing inaccurate conclusions and invalid inferences . ad hominem fallacy is one of the most common fallacy labels used in political debates despite its use in many scenarios . |
| Approach: | They extend the ElecDeb60To16 dataset of U.S. presidential debates annotated with fallacious arguments by incorporating the most recent Trump-Biden debate. |
| Outcome: | The proposed method extends the ElecDeb60To16 dataset of U.S. presidential debates annotated with fallacious arguments . |
Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries (2025.acl-long)
Copied to clipboard
| Challenge: | Existing adversarial text attacks rely on abundant access to shared internal features and numerous queries, limited to a single task type. |
| Approach: | They propose a black-box attack that exploits the transferability of adversarial texts . they use a deep-level substitute model trained in a plug-and-play manner for text classification . |
| Outcome: | The proposed attack can target multiple tasks with minimal perturbations . it can target commercial APIs, large language models, and image-generation models . |
Prompt-based Distribution Alignment for Domain Generalization in Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Pretrained language models (PLMs) have achieved competitive performance on a range of NLP tasks. |
| Approach: | They propose to learn distributional invariance across source domains via alignment regularization loss functions to improve domain generalization by prompting. |
| Outcome: | Experiments on sentiment analysis and natural language inference show the effectiveness of the proposed method and achieve state-of-the-art results. |
How Diplomats Dispute: The UN Security Council Conflict Corpus (2024.lrec-main)
Copied to clipboard
| Challenge: | Until now, there has been little work on how to formalize conflicts in a diplomatic setting. |
| Approach: | They present a corpus of 87 UNSC speeches that are annotated for conflicts and demonstrate the difficulty when dealing with diplomatic language. |
| Outcome: | The proposed method demonstrates that diplomatic language is complex and often implicit along various dimensions. |
Sentiment Analysis of Tweets using Heterogeneous Multi-layer Network Representation and Embedding (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to handle sentiment analysis of tweets are inadequate due to various characteristics such as under-specificity, noise, and multilingual content. |
| Approach: | They propose a multi-layer network-based representation of tweets to generate multiple representations of a tweet and classify them using a neural-based early fusion approach. |
| Outcome: | The proposed method can address the problem of under-specificity, noisy text, and multilingual content present in a tweet and provides better representations than the text-based counterparts. |
Text Classification Using Label Names Only: A Language Model Self-Training Approach (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current text classification methods require a large number of labeled documents as training data. |
| Approach: | They propose a model that uses only the label name of each class to train classification models on unlabeled data without using any labeled examples. |
| Outcome: | The proposed model achieves 90% accuracy on four benchmark datasets using label names as the only supervision . |
Feature Projection for Improved Text Classification (2020.acl-main)
Copied to clipboard
| Challenge: | In sentiment classification, there are some good features that are indicative of class labels, but there are also many common features that do not discriminate for classification. |
| Approach: | They propose to project existing features into the orthogonal space of the common features and make them more discriminative for classification. |
| Outcome: | The proposed method improves CNN, RNN, Transformer, and Bert based text classification and obtains markedly better results. |
Unlearn What You Want to Forget: Efficient Unlearning for LLMs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) can be used to memorize a vast amount of data, but can suffer from privacy issues and data protection violations. |
| Approach: | They propose an efficient unlearning framework that could update LLMs without retraining them . they introduce lightweight unlearning layers learned with a selective teacher-student objective into transformers . |
| Outcome: | The proposed framework could update LLMs without having to retrain the whole model after data removals. |
Deep One-Class Hate Speech Detection Model (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing approaches to hate speech detection neglect distinct attributes of hate speeches from other sentimental types such as “aggressive” and “racist”. |
| Approach: | They propose a one-class model where the detection classifier is trained with hate-class samples only. |
| Outcome: | The proposed model outperforms existing models with four benchmark datasets and shows that it performs better than existing models. |
StyleKQC: A Style-Variant Paraphrase Corpus for Korean Questions and Commands (2022.lrec-1)
Copied to clipboard
| Challenge: | Especially for questions and commands, style-variant paraphrasing can be crucial in tone and manner. |
| Approach: | They propose a corpus construction scheme that considers intent and formality of directives in Korean language. |
| Outcome: | The proposed method is validated by a corpus construction scheme on Korean topics. |
QAP: A Quantum-Inspired Adaptive-Priority-Learning Model for Multimodal Emotion Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that multimodal emotion recognition is a state-of-the-art technique . textual, visual and acoustic modalities are involved in multimodal video emotion recognition . |
| Approach: | They propose a quantum-inspired adaptive-priority-learning model to address the challenges . they use quantum state to model modal features and Q-attention to integrate three modalities . |
| Outcome: | Experimental results show that QAP improves on previous models. |
Inferring Social Media Users’ Mental Health Status from Multimodal Information (2020.lrec-1)
Copied to clipboard
| Challenge: | In the United States alone, one in every four adults suffers from a mental health condition, making mental health a pressing concern. |
| Approach: | They propose to use multimodal cues present in social media posts to predict mental health status by analyzing language, visual, and metadata cue data. |
| Outcome: | The proposed approach improves the performance of the classification task compared to using one modality at a time and can provide important cues into a user’s mental status. |
ReCode: Robustness Evaluation of Code Generation Models (2023.acl-long)
Copied to clipboard
Shiqi Wang, Zheng Li, Haifeng Qian, Chenghao Yang, Zijian Wang, Mingyue Shang, Varun Kumar, Samson Tan, Baishakhi Ray, Parminder Bhatia, Ramesh Nallapati, Murali Krishna Ramanathan, Dan Roth, Bing Xiang
| Challenge: | Existing work on robustness in text or code tasks has focused on classification, while robustness for code generation tasks is an uncharted area. |
| Approach: | They propose a robustness evaluation benchmark for code generation models that customizes over 30 transformations specifically for code on docstrings, function and variable names, code syntax, and code format. |
| Outcome: | The proposed model performs better on human annotators and on SOTA models with human annnotators. |
Resource-Limited Joint Multimodal Sentiment Reasoning and Classification via Chain-of-Thought Enhancement and Distillation (2026.findings-acl)
Copied to clipboard
| Challenge: | Current approaches for Multimodal Sentiment Analysis (MSA) rely on parameter-heavy LLMs for classification, overlooking multimodal sentiment reasoning generation in resource-limited environments. |
| Approach: | They propose a multimodal sentiment reasoning distillation model that employs a teacher-assistant-student paradigm to address deployment constraints in resource-limited environments. |
| Outcome: | The proposed model performs well on a resource-limited JMSRC task with only 3B parameters and shows generalization and interpretability. |
Tracing Logit Trajectories Across Layer Depth: Dataset-Level Explainability for Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Sentence-level explanations miss the bigger picture of how a black-box model behaves across data . a dataset-level analysis that traces the intermediate structure of decision formation is needed . |
| Approach: | They propose a method that aggregates logit updates into a reproducible dataset-level trajectory pattern. |
| Outcome: | The proposed model enables depth-wise explainability across 6 languages and 5 NLP tasks. |
Token Prediction as Implicit Classification to Identify LLM-Generated Text (2023.emnlp-main)
Copied to clipboard
| Challenge: | a novel approach for identifying large language models (LLMs) involved in text generation is proposed . instead of adding an additional classification layer, we reframe the classification task as a next-token prediction task . |
| Approach: | They propose a novel approach for identifying large language models involved in text generation . instead of adding an additional classification layer, they reframe the task as a next-token prediction task . |
| Outcome: | The proposed method performs exceptionally well in the text classification task . it can distinguish distinctive writing styles among various LLMs even without an explicit classifier. |
Counterfactual Probing for the Influence of Affect and Specificity on Intergroup Bias (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing work on bias in NLP only considers negative or pejorative language use. |
| Approach: | They propose a revised framing of bias in terms of intergroup social context and its effects on language output. |
| Outcome: | The proposed framework is based on a model of intergroup relationships in English language tweets. |
Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models have shown extraordinary success across text generation tasks . however, their potential for simple yet essential text classification remains underexplored . |
| Approach: | a plug-and-play layer-wise parameter-efficient fine-tuning framework is proposed . it fine- tunes a subset of important LLM layers while freezing redundant ones . |
| Outcome: | a plug-and-play framework fine-tunes a subset of important LLM layers while freezing redundant layers. |
Block Pruning For Faster Transformers (2021.emnlp-main)
Copied to clipboard
| Challenge: | Pruning methods have proven to be effective at reducing model size, while distillation methods are proven for speeding up inference. |
| Approach: | They propose a block pruning approach that integrates structured pruning methods with the movement pruning paradigm for fine-tuning. |
| Outcome: | The proposed model is 2.4x faster, 74% smaller and faster than distilled models on classification and generation tasks. |
HalluMeasure: Fine-grained Hallucination Measurement Using Chain-of-Thought Reasoning (2024.emnlp-main)
Copied to clipboard
Shayan Ali Akbar, Md Mosharaf Hossain, Tess Wood, Si-Chi Chin, Erica Salinas, Victor Alvarez, Erwin Cornejo
| Challenge: | HalluMeasure is a new LLM-based hallucination detection mechanism that decomposes an LLM response into atomic claims and evaluates each claim against the provided reference context. |
| Approach: | They propose a new LLM-based hallucination detection mechanism that decomposes an LLM response into atomic claims and evaluates each atomic claim against the provided reference context. |
| Outcome: | The proposed model can detect 3 major categories of hallucinations and 10 more specific subtypes which help to identify reasons behind the hallucinian errors. |
Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions (2024.emnlp-main)
Copied to clipboard
| Challenge: | Generative large language models (LLMs) have brought advances in text generation, but their potential for enhancing classification tasks remains underexplored. |
| Approach: | They propose a framework for thoroughly investigating fine-tuning LLMs for classification . they instantiate this framework in edit intent classification (EIC) a challenging and underexplored classification task. |
| Outcome: | The proposed framework is applied to edit intent classification (EIC) The proposed methods are generalizable on five further classification tasks. |
Can You Really Trust Code Copilot? Evaluating Large Language Models from a Code Security Perspective (2025.acl-long)
Copied to clipboard
| Challenge: | Existing code security benchmarks focus on one task and paradigm, such as code completion and generation, without comprehensive assessment across dimensions like secure code generation, vulnerability repair and discrimination. |
| Approach: | They propose a multi-task benchmark for comprehensive evaluation of LLM code security . they also propose VC-Judge, an improved judgment model that aligns closely with human experts . |
| Outcome: | The proposed model can evaluate LLM-generated programs for vulnerabilities in a more efficient and reliable way. |
Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current vocabulary adaptation approaches append the target domainspecific vocabulary (V DOMAIN) at the end of the PLM vocabulary. |
| Approach: | They propose a vocabulary adaptation scheme that appends a target domain-specific vocabulary (V DOMAIN) at the end of the PLM vocabulary. |
| Outcome: | The proposed approach improves by 3.57% (in terms of accuracy) and 1.87% (royal-L) over various classification and summarization tasks. |
MemeInterpret: Towards an All-in-One Dataset for Meme Understanding (2025.findings-emnlp)
Copied to clipboard
Jeongsik Park, Khoi P. N. Nguyen, Jihyung Park, Minseok Kim, Jaeheon Lee, Jae Won Choi, Kalyani Ganta, Phalgun Ashrit Kasu, Rohan Sarakinti, Sanjana Vipperla, Sai Sathanapalli, Nishan Vaghani, Vincent Ng
| Challenge: | Existing research has not explored meme captioning's decomposition into subtasks or its connections to other CMU tasks. |
| Approach: | a new meme corpus is built upon the Facebook Hateful Memes dataset . it contains meme captions, corresponding surface messages and relevant background knowledge . |
| Outcome: | a new corpus of meme captions and surface messages unifies three major categories of CMU tasks for the first time. |
PIXAR: Auto-Regressive Language Modeling in Pixel Space (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent work shows the possibility of building open-vocabulary large language models that operate on pixel representations. |
| Approach: | They propose a pixel-based autoregressive LLM that performs generative tasks . they propose an adversarial pretraining stage that improves the readability and accuracy of PIXAR by 8.1 on LAMBADA and 8.5 on bAbI. |
| Outcome: | The proposed model performs free-form generative tasks while keeping the number of parameters on par with previous encoder-decoder models. |
Re-examining Sexism and Misogyny Classification with Annotator Attitudes (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing datasets for content moderation fail to capture plurality of possible annotator perspectives or ensure representation of affected groups. |
| Approach: | They examine the relationship between annotator identities and attitudes and the responses they give to two GBV labelling tasks. |
| Outcome: | The results show that higher Right Wing Authoritarianism scores are associated with a higher propensity to label text as sexist . higher scores are also associated with negative attitudes towards sexism and neosexist attitudes . |
Here’s a Free Lunch: Sanitizing Backdoored Models with Model Merge (2024.findings-acl)
Copied to clipboard
| Challenge: | democratization of pre-trained language models brings significant security risks, including backdoor attacks. |
| Approach: | They propose to merge a backdoored model with other homogeneous models to remediate backdoor vulnerabilities. |
| Outcome: | The proposed model merging approach outperforms other models on classification tasks without additional resources or specific knowledge. |
Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | ZOPrO is a novel algorithm designed for *Preference Optimisation* in large language models. |
| Approach: | They propose a ZO algorithm designed for *Preference Optimisation* in LLMs that uses function evaluations instead of gradients to reduce memory usage. |
| Outcome: | The proposed method improves reward signals while achieving convergence times comparable to first-order methods. |
BANMIME : Misogyny Detection with Metaphor Explanation on Bangla Memes (2025.emnlp-main)
Copied to clipboard
Md Ayon Mia, Akm Moshiur Rahman Mazumder, Khadiza Sultana Sayma, Md Fahim, Md Tahmid Hasan Fuad, Muhammad Ibrahim Khan, Akmmahbubur Rahman
| Challenge: | Existing studies have explored hate speech and general meme classification, but the nuanced identification of misogyny in Bangla memes remains underexplored. |
| Approach: | They propose a Bangla misogynistic meme dataset that includes misos, humor, metaphors and detailed human-written explanations. |
| Outcome: | The proposed dataset is the first comprehensive dataset of misogynistic Bangla memes . it includes misos, humor categories, metaphor localization, and detailed human-written explanations based on 2,000 culturally grounded samples . |
Leveraging Information Redundancy of Real-World Data through Distant Supervision (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for annotation of health care notes are promising but they are limited due to privacy regulations. |
| Approach: | They propose a text labeling method that leverages the redundancy of temporal information in a data lake to create a large programmatically annotated corpus and train transformer models using distant supervision. |
| Outcome: | The proposed method reduces expert annotation time, a scarce and expensive resource. |
Focus on the Core: Efficient Attention via Pruned Token Compression for Document Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained transformers suffer from a computationally expensive self-attention mechanism that interacts with all tokens, including those unfavorable to classification performance. |
| Approach: | They propose to integrate token pruning and token combining strategies to improve model performance and reduce computational demands. |
| Outcome: | Experiments with various datasets show that the proposed model performs better than baseline models, with the best improvement over the existing model. |
SLIDE: A Framework Integrating Small and Large Language Models for Open-Domain Dialogues Evaluation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to evaluate open domain dialogues have a one-to-many problem . existing approaches lack commonsense reasoning biases and perform poorly in domain-specific scenarios. |
| Approach: | They propose a framework that leverages both a small, specialised model and LLMs for the evaluation of open-domain dialogues. |
| Outcome: | The proposed framework achieves state-of-the-art performance in both classification and evaluation tasks and exhibits better correlation with human judgements. |
BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to text classification require large annotated corpora to train or long context to fit many examples. |
| Approach: | They propose a method to few-shot text classification using an LLM. |
| Outcome: | The proposed approach yields high accuracy classifiers within 79% of the performance of models trained with larger datasets while using only 1% of their training sets. |
Locally Differentially Private In-Context Learning (2024.lrec-main)
Copied to clipboard
| Challenge: | Large pretrained language models (LLMs) have shown surprising In-Context Learning ability. |
| Approach: | They propose a locally differentially private framework of in-context learning for LLMs that can be augmented with a private database for some specific task. |
| Outcome: | The proposed framework can predict labels without additional parameter modifications without input-label pairs . |
Prompting with Pseudo-Code Instructions (2023.emnlp-main)
Copied to clipboard
| Challenge: | ambiguity in natural language can hinder performance of large language models. |
| Approach: | They manually create a dataset of pseudo-code prompts for 132 different classification, QA, and generative language tasks, sourced from the Super-NaturalInstructions dataset. |
| Outcome: | The pseudo-code prompts improve the performance of two LLM families, BLOOM and CodeGen. |
mALBERT: Is a Compact Multilingual BERT Model Still Worth It? (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing studies on the ethical and ecological impact of pre-trained language models raise questions about the temporal, financial, and environmental aspects of such models. |
| Approach: | They propose to focus on smaller models, such as compact models like ALBERT, which are more ecologically virtuous than these PLMs. |
| Outcome: | The proposed model is compared with classical multilingual models and is ethically virtuous. |
Elevating Code-mixed Text Handling through Auditory Information of Words (2023.emnlp-main)
Copied to clipboard
| Challenge: | Current language models focus on the semantic representation of words and ignore the auditory phonetic features. |
| Approach: | They propose an approach to create language models for handling code-mixed textual data using auditory phonetic features from SOUNDEX using auditorian information. |
| Outcome: | The proposed approach improves robustness against adversarial attacks on code-mixed classification tasks and improves classification results over baselines. |
Label Confidence Weighted Learning for Target-level Sentence Simplification (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for sentence simplification use label confidence weighting to generate pseudo-labeled sentences with varying proficiency levels. |
| Approach: | They propose a label confidence weighting scheme for multi-level sentence simplification that incorporates a weighting system into the training loss of the encoder-decoder model. |
| Outcome: | The proposed approach outperforms state-of-the-art confidence weighting methods on English grade-level simplification datasets. |
Dialogue Act-Aided Backchannel Prediction Using Multi-Task Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Backchanneling is a form of feedback that is produced by listeners in a conversation . since the advent of ChatGPT, modern dialogue systems exhibit answer quality levels on par with humans in various professions. |
| Approach: | They propose a multi-task learning approach that learns textual representations for the task of backchannel prediction in tandem with dialogue act classification. |
| Outcome: | The proposed approach improves the prediction of specific backchannels by up to 2.0% in F1 . the audio encoder is pre-trained in a self-supervised fashion using voice activity projection . |
Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for Continual Learning (CL) have limited KT and catastrophic forgetting . a new method overcomes CF by isolating the knowledge of each task . |
| Approach: | They propose a method to overcome catastrophic forgetting and encourage knowledge transfer . they propose to discover a sub-network for each task and a soft-masking mechanism to preserve the previous knowledge. |
| Outcome: | The proposed method outperforms baselines in classification, generation, information extraction and their mixture. |
Euphemistic Abuse – A New Dataset and Classification Experiments for Implicitly Abusive Language (2023.emnlp-main)
Copied to clipboard
| Challenge: | Currently, only explicit abuse can be reliably detected due to the increasing amount of abusive language on the Web. |
| Approach: | They propose a crowdsourced dataset that can detect euphemistic abuse by paraphrasing simple explicit utterances. |
| Outcome: | The proposed classifier augments training data with automatically-generated GPT-3 completions. |
Explicit Bayesian Inference to Uncover the Latent Themes of Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have impressive generative capabilities, yet their inner mechanisms remain largely opaque. |
| Approach: | They propose a variational autoencoder-based neural topic model to interpret LLMs generation process through an explicit Bayesian framework by inferring latent topic variables via variational inference. |
| Outcome: | The proposed model outperforms state-of-the-art topic models on intrinsic measures of coherence and diversity on multiple datasets and shows significant gains on classification and summarization tasks. |
Interpretable Text Embeddings and Text Similarity Explanation: A Survey (2025.emnlp-main)
Copied to clipboard
| Challenge: | Text embeddings are a fundamental component in many NLP tasks, but their interpretation and explanation remain challenging. |
| Approach: | They propose a framework for interpretable text embeddings and text similarity explanation . they characterize the main ideas, approaches, and trade-offs and discuss lessons learned . |
| Outcome: | The proposed methods are compared with existing models and compare them with existing ones. |
Pruning before Fine-tuning: A Retraining-free Compression Framework for Pre-trained Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Structured pruning is an effective technique for compressing pre-trained language models (PLMs), but it requires retraining, leading to additional computational overhead. |
| Approach: | They propose a task-specific pruning framework that prunes redundant modules of pre-trained language models before fine-tuning them. |
| Outcome: | The proposed pruning framework achieves higher performance on GLUE, SQUAD, WikiText-2, Wik-103, and PTB datasets while reducing the time required for fine-tuning. |
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite excelling at many natural language processing tasks, large language models fail to grasp the layered semantics of Drivelological text. |
| Approach: | They construct a benchmark dataset of over 1,200+ carefully curated and diverse examples across English, Mandarin, Spanish, French, Japanese, and Korean to examine their Drivelological characteristics. |
| Outcome: | The proposed models lack conceptual understanding and lack conceptual and semantic accuracy. |
Retrieval-enriched zero-shot image classification in low-resource domains (2024.emnlp-main)
Copied to clipboard
| Challenge: | Low-resource domains are those where data or annotations are scarce. |
| Approach: | They propose a retrieval-based method for low-resource domains that trains without training . they use web-crawled databases to retrieve relevant textual information from query images . |
| Outcome: | The proposed method outperforms existing training-based methods in low-resource domains . it retrieves relevant textual information from large web-crawled databases . |
Reassessing Semantic Knowledge Encoded in Large Language Models through the Word-in-Context Task (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent advances in large language models (LLMs) have propelled significant progress, extending their application across various domains including dialogue systems, text generation, translation systems, and beyond. |
| Approach: | They propose to use the Word-in-Context (WiC) task to reassess the semantic knowledge encoded in large language models (LLMs) they prompt LLMs to generate natural language descriptions that contrast the meanings of the target word in two contextual sentences given in the WiC dataset. |
| Outcome: | The proposed model significantly improves the classification accuracy of the two models. |
Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifacts (2025.findings-acl)
Copied to clipboard
Sara Ghaboura, Ketan Pravin More, Ritesh Thawkar, Wafa Al Ghallabi, Omkar Thawakar, Fahad Shahbaz Khan, Hisham Cholakkal, Salman Khan, Rao Muhammad Anwer
| Challenge: | TimeTravel is a benchmark of 10,250 expert-verified historical artifact samples spanning 266 distinct cultures across 10 major historical regions. |
| Approach: | They evaluate contemporary AI models on TimeTravel, highlighting their strengths and identifying areas for improvement. |
| Outcome: | The timeTravel benchmark covers 266 cultures and 10 major historical regions and aims to establish AI as reliable partner in preserving cultural heritage. |
Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) pre-trained on massive text data in many languages are preferred solution for various Natural Language processing tasks. |
| Approach: | They compare tokenization parity and information parity as representational biases in pre-trained models . they find TP is better predictor of performance on tasks reliant on syntactic and morphological cues . |
| Outcome: | The proposed model improves on dialect classification, topic classification, and extractive question answering tasks. |
RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have brought a great breakthrough to the natural language processing community, but their high throughput demands make them difficult to handle concurrent queries. |
| Approach: | They propose a parameter-efficient data multiplexing framework that integrates a reversible design in the multiplexer and can be reused to perform reverse operations and restore individual samples for classification. |
| Outcome: | The proposed framework improves inference efficiency while maintaining satisfactory classification performance. |
FineCite: A Novel Approach For Fine-Grained Citation Context Analysis (2025.findings-acl)
Copied to clipboard
| Challenge: | citation context analysis (CCA) studies the role and purpose of citations in scientific discourse. |
| Approach: | They construct a first comprehensive context definition based on semantic properties of citing text . they use fine-grained semantic properties to evaluate the definition . |
| Outcome: | The proposed definition shows improvements of up to 25% over state-of-the-art methods. |
Using tournaments to calculate AUROC for zero-shot classification with LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models perform well on zero-shot classification tasks, but are difficult to compare to supervised classifiers due to the lack of a modifiable decision boundary. |
| Approach: | They propose a method that transforms binary classification tasks into pairwise comparisons between instances within a dataset. |
| Outcome: | The proposed method produces relative rankings of instances using the Elo rating system . |
RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models use full finetunation, but this is impractical as language models continue to scale up. |
| Approach: | They propose a parameter-efficient fine-tuning method for large language models based on updating only a few rows and columns of the weight matrices in transformers. |
| Outcome: | The proposed method gives comparable or better accuracies than state-of-the-art methods while being more memory and computation-efficient. |
Do Language Models Understand Honorific Systems in Javanese? (2025.acl-long)
Copied to clipboard
Mohammad Rifqi Farhansyah, Iwan Darmawan, Adryan Kusumawardhana, Genta Indra Winata, Alham Fikri Aji, Derry Tanti Wijaya
| Challenge: | Despite its cultural and linguistic significance, there has been limited progress in developing a comprehensive corpus to capture these variations for natural language processing (NLP) tasks. |
| Approach: | They propose to use a dataset to capture the nuances of Unggah-Ungguh Basa, the Javanese speech etiquette framework, to assess the ability of language models to process various levels of Javanesi honorifics. |
| Outcome: | The proposed dataset encapsulates the nuances of Unggah-Ungguh Basa, the Javanese speech etiquette framework. |
LGSA: Label Geometry Structuring and Aligning for Hierarchical Text Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Existing hierarchical text classification methods use prompt tuning or contrastive learning to implicitly learn label embeddings for classification, but this method fails to model hierarchy-aware geometric relations among labels. |
| Approach: | They propose a two-stage framework that transforms the label hierarchy from an implicit prior into an explicit embedding by using a general orthogonal frame. |
| Outcome: | The proposed framework outperforms existing state-of-the-art methods on three real-world HTC datasets. |
Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings (2025.findings-acl)
Copied to clipboard
| Challenge: | Prompt-based text embedding models generate task-specific embeddables but have thousands of dimensions . dimensionality reductions for embedded text can result in performance degradations of only the first 25% of the dimensions resulting in a very small degradation . |
| Approach: | They investigate how post-hoc dimensionality reduction affects performance of various tasks . they find that embeddings for classification and clustering exhibit lower intrinsic dimensionalities . |
| Outcome: | The proposed model generates task-specific embeddings upon receiving tailored prompts, but has thousands of dimensions and high storage costs. |
Beyond Negative Stereotypes – Non-Negative Abusive Utterances about Identity Groups and Their Semantic Variants (2025.acl-long)
Copied to clipboard
| Challenge: | implicitly abusive language is a language that could offend, demean or marginalize another person . a large portion of what is considered abusive language can be classified as implicitly abused . |
| Approach: | They propose to profile implicitly abusive language and use it to analyze a dataset of such utterances. |
| Outcome: | The proposed dataset identifies the type of abusive language that is not conveyed by unambiguously abusive words. |
Term-Driven Forward-Looking Claim Synthesis in Earnings Calls (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing arguments synthesis models excel in summarizing arguments, but lack accurate forward-looking perspectives. |
| Approach: | They propose a task called "forward-looking claim planning" that incorporates forward-looking perspectives. |
| Outcome: | The proposed method improves the existing models and improves performance. |
The Influence of Automatic Speech Recognition on Linguistic Features and Automatic Alzheimer’s Disease Detection from Spontaneous Speech (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing biomarkers for AD diagnosis can only be applied to relatively small sample sizes due to limited availability, excessive costs and invasive nature. |
| Approach: | They compare automatic speech recognition systems in terms of Word Error Rate (WER) using a publicly available benchmark dataset of speech recordings of AD patients and controls. |
| Outcome: | The proposed method improves classification performance by replacing manual transcriptions with ASR output. |
The Open-World Lottery Ticket Hypothesis for OOD Intent Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods of Out-of-Domain intent classification lack confidence in In- and Out- of-domain intents. |
| Approach: | They propose to prune overparameterized models to provide better confidence . they extend the Lottery Ticket Hypothesis to open-world scenarios . |
| Outcome: | The proposed model can be calibrated to distinguish In- and Out-of-domain intents . the model can also improve on open-world scenarios . |
Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on text embeddings focus less on how information is encoded. |
| Approach: | They find that truncating embedding dimensions causes an increase in performance when removed. |
| Outcome: | The proposed method improves performance across 6 state-of-the-art text encoders and 26 downstream tasks. |
Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy (2026.findings-acl)
Copied to clipboard
Vallabhaneni Raj Kumar, Ashwin S, Supriya Manna, Niladri Sett, Cheedella V S N M S Hema Harshitha, Kurakula Harshitha, Basina Deepakraj, Anand Kumar Sharma, Tanuj Sarkar, Samanthapudi Shakeer, Bondada Navaneeth Krishna
| Challenge: | a limited amount of annotated data has slowed progress in machine learning for low-resource languages . a sentiment label records an annotator's final decision, but it is not a valid record of the annotation's interpretation. |
| Approach: | They propose a large-scale Telugu sentiment classification dataset annotated with sentiment labels and human-selected rationales from multiple native speakers. |
| Outcome: | The proposed model improves classification performance, explanation quality, and social bias by incorporating human rationales. |
Lemmatization as a Classification Task: Results from Arabic across Multiple Genres (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing tools for lemmatization in morphologically rich languages with ambiguous orthography face inconsistent standards and limited genre coverage. |
| Approach: | They propose two new approaches that frame lemmatization as classification into a Lemma-POS-Gloss tagset, leveraging machine translation and semantic clustering. |
| Outcome: | The proposed models perform better than existing models and are more interpretable, the authors show. |
LETS-C: Leveraging Text Embedding for Time Series Classification (2025.acl-long)
Copied to clipboard
| Challenge: | Recent advances in language modeling have shown promising results when applied to time series data. |
| Approach: | They propose a method to fine-tune large language models for time series classification tasks using text embedding models and a simple classification head. |
| Outcome: | The proposed model outperforms the current SOTA model on a time series classification benchmark and uses only 14.5% of the trainable parameters. |
Prompting Across Time: Evaluating LLMs on Historical and Contemporary Offensive Language (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing research on large language models and hate speech detection has focused on contemporary data. |
| Approach: | They propose to use a modular prompt design to evaluate early-modern English invectives . they propose to widen the scope of NLP research on hate speech beyond the contemporary domain . |
| Outcome: | The proposed model outperforms a modern hate-speech benchmark on Early Modern English invectives . the results show that the model is more robust to contextual and contextual factors than the current model . |
Evaluation Pitfalls and Sparsity Limitations in LLM-based Confidence Estimates for Classification (2026.findings-acl)
Copied to clipboard
| Challenge: | Xuan et al., 2023) show that verbalization produces extremely sparse outputs for confidence estimation. |
| Approach: | They propose to standardize stepwise interpolation for a fairer comparison . they advocate standardizing stepwise intercepts for AUARC evaluation . |
| Outcome: | The proposed method achieves the best AUARC score (+2.3 points over vanilla verbalization) while requiring less inference cost. |
Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection (2026.acl-long)
Copied to clipboard
| Challenge: | Cognitive distortions are systematic errors in thinking that occur when individuals perceive and interpret external information, leading to a negative conclusion that does not correspond to reality. |
| Approach: | They propose a framework that combines Large Language Models with a Multiple-Instance Learning architecture to enhance interpretability and expression-level reasoning. |
| Outcome: | The proposed framework improves interpretability and expression-level reasoning on Korean and English datasets. |
PL-MTEB: Polish Massive Text Embedding Benchmark (2026.findings-acl)
Copied to clipboard
| Challenge: | Text embeddings are used in many NLP tasks, including document clustering, semantic search, question answering, and classification. |
| Approach: | They introduce the Polish Massive Text Embedding Benchmark (PL-MTEB) it is a comprehensive benchmark for text embeddings in the Polish language. |
| Outcome: | The proposed model is based on 30 different NLP tasks in the Polish language. |
Beyond Single Representations: Multi-Model Embedding Fusion for Stable Text Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Existing studies on embedding fusion have not evaluated the effectiveness of individual layers or the impact of combining embeddables from multiple models. |
| Approach: | They propose to combine embeddings from multiple models to improve performance across NLP tasks. |
| Outcome: | The proposed method improves performance on low-resource datasets and reduces the impact of any single model as the number of integrated models increases. |
Incomplete In-context Learning (2026.acl-long)
Copied to clipboard
Wenqiang Wang, Wen Yujia, Yan Xiao, Zhifeng Chen, Yangshijie Zhang, Peng Chen, Mingbo Yang, Xiaochun Cao
| Challenge: | Existing in-context learning assumes the retrieval dataset contains demonstrations for all output label spaces. |
| Approach: | They propose a framework with train-free and train-based variants to address IICL . they propose to integrate a dataset with labeled demonstrations for each output space . |
| Outcome: | The proposed framework outperforms existing methods under incomplete retrieval datasets and even outperformed ICL with complete labels. |
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Modern LLM deployments are rarely a single model in isolation. |
| Approach: | They propose a model that reuses computation already paid for by the serving LLM . they instantiate a template with pooling, a scoring-attention gate, and a downcast multi-head self-attention probe . |
| Outcome: | The proposed model improves safety and sentiment benchmarks on dense and mixture-of-experts architectures while preserving near-serving latency. |
BanHADEX: Towards Explainable HAte Speech Detection in Bangla Using Human Annotated EXplanation (2026.acl-long)
Copied to clipboard
Faisal Hossain Raquib, Akm Moshiur Rahman Mazumder, Md Fahim, Md Tahmid Hasan Fuad, Md Farhan Ishmam, Faria Sultana, M Ashraful Amin, Amin Ahsan Ali, Akmmahbubur Rahman
| Challenge: | Existing studies in Bangla focus on hate classification while overlooking interpretability. |
| Approach: | They propose to create a dataset with human-annotated labels for banla that contains 19,203 YouTube comments spanning April 2024–June 2025. |
| Outcome: | The proposed dataset outperforms existing datasets on open and closed-source LLMs on interpretability and better understanding of hate speech in linguistically rich yet under-resourced languages. |