PREDICTION ACCURACY

Distance-Free Modeling of Multi-Predicate Interactions in End-to-End Japanese Predicate-Argument Structure Analysis (C18-1)

Challenge:	Existing methods to extract unseen relations require laborious manual annotation . a new approach uses fine-grained matching to reduce manual annotation cost .
Approach:	They propose an efficient multi-grained matching approach that uses virtual entity matching to reduce manual annotation cost.
Outcome:	The proposed approach outperforms the state-of-the-art methods and achieves inference efficiency and accuracy in zero-shot relation extraction tasks.

Copied to clipboard

Yuichiroh Matsubayashi, Kentaro Inui

Challenge:	Existing models for analyzing PASs in Japanese are lacking in identifying elliptical arguments.
Approach:	They propose to extend the input and last layers of a bidirectional recurrent neural network model to capture the potential interactions among multiple PASs.
Outcome:	The proposed models improve prediction accuracy on a benchmark corpus and achieve state-of-the-art on standardized corpus.

Concealed Data Poisoning Attacks on NLP Models (2021.naacl-main)

Copied to clipboard

Eric Wallace, Tony Zhao, Shi Feng, Sameer Singh

GeoIndia: A Seq2Seq Geocoding Approach for Indian Addresses (2024.emnlp-industry)

Challenge:	In contrast, adversarial attacks can cause model errors by modifying inputs, such as the universal triggers attack.
Approach:	They propose a data poisoning attack that allows an adversary to control model predictions whenever a desired trigger phrase is present in the input.
Outcome:	The proposed attack can cause model errors by modifying inputs, but it can also cause extra human annotation.

Copied to clipboard

Bhavuk Singhal, Anshu Aditya, Lokesh Todwal, Shubham Jain, Debashis Mukherjee

Interpretable Rationale Augmented Charge Prediction System (C18-2)

Challenge:	a new geocoding system for Indian addresses addresses is needed for logistics, urban planning and location-based services.
Approach:	They propose a geocoding system for Indian addresses using hierarchical H3-cell prediction using a Seq2Seq framework.
Outcome:	The proposed system outperforms existing geocoding platforms in accuracy and reliability across multiple Indian states.

Copied to clipboard

Xin Jiang, Hai Ye, Zhunchen Luo, WenHan Chao, Wenjia Ma

PG-GSQL: Pointer-Generator Network with Guide Decoding for Cross-Domain Context-Dependent Text-to-SQL Generation (2020.coling-main)

Challenge:	Existing studies treat charge prediction as a text classification problem, but in the field of justice, every decision may be a matter of life and death.
Approach:	They propose to extract readable rationales from text and then create a rationale augmented classification model to enhance the prediction accuracy.
Outcome:	The proposed system can extract readable rationales in a high consistency with manual annotation and is comparable with the attention model in prediction accuracy.

Copied to clipboard

Huajie Wang, Mei Li, Lei Chen

Multimodality

Challenge:	Existing approaches to text-to-SQL generation depend on interaction history and current utterances.
Approach:	They propose an encoder-decoder model based on interaction-level encoder to capture historical information of SQL query and reuse the previous SQL query tokens.
Outcome:	The proposed model outperforms the previous state-of-the-art model on the SParC benchmark . it achieves 34.0% question matching accuracy and 19.0% interaction matching accuracy .

EDM3: Event Detection as Multi-task Text Generation (2024.starsem-1)

Copied to clipboard

Ujjwala Anantheswaran, Himanshu Gupta, Mihir Parmar, Kuntal Pal, Chitta Baral

Cross-Genre Learning for Old English Poetry POS Tagging (2025.acl-srw)

Challenge:	Existing methods for Event Detection (ED) cannot easily leverage pre-trained semantic knowledge.
Approach:	They propose to decompose and reformulate ED and fine-tune over its atomic subtasks to enhance knowledge transfer while mitigating prediction error propagation inherent in pipelined approaches.
Outcome:	The proposed method achieves state-of-the-art performance on RAMS, MAVEN, and MLEE, while achieving 90% accuracy over rare event types.

Copied to clipboard

Irene Miani, Sara Stymne, Gregory R. Darwin

Syntactic Text Processing

Challenge:	a recent study highlights the linguistic differences between Old English poetry and prose . linguistic analysis tools struggle to address these differences, says a researcher .
Approach:	They analyze annotated corpora representing each genre to find similarities between poetry and prose . they find that there are several types of structural differences between the two genres .
Outcome:	The results show that integrating small amounts of target data improves prediction accuracy compared to excluding it entirely.

Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study (2026.acl-short)

Copied to clipboard

Ali El Lahib, Ying-Jieh Xia, Zehan Li, Yuxuan Wang, Xinyu Pi

Information Retrieval

Challenge:	Search-engine date filters are widely used to enforce pre-cutoff retrieval in retrospective evaluations of search-augmented forecasters.
Approach:	They propose stronger retrieval safeguards or evaluation on frozen, time-stamped web snapshots to prevent post-cutoff leakage.
Outcome:	The proposed approach is unreliable across two major search engines, and the results are inflated.

Synergizing LLMs with Global Label Propagation for Multimodal Fake News Detection (2025.acl-long)

Copied to clipboard

Shuguo Hu, Jun Hu, Huaiwen Zhang

Ethical NLP

Challenge:	Large Language Models (LLMs) can assist multimodal fake news detection by predicting pseudo labels, but their effective integration is non-trivial.
Approach:	They propose a global label propagation network with LLM-based pseudo labels for multimodal fake news detection which integrates LLM capabilities via label propagations.
Outcome:	The proposed model outperforms state-of-the-art models on benchmark datasets showing that it can propagate pseudo labels among all samples.

Efficient Reasoning for LLMs through Speculative Chain-of-Thought (2026.findings-acl)

Copied to clipboard

Jikai Wang, Juntao Li, Jianye Hou, Yan Bowen, Lijun Wu, Min Zhang

Reasoning

Challenge:	Existing methods for efficient reasoning focus on reducing the number of model parameters or shortening the chain-of-thought length.
Approach:	They propose a speculative chain-of-thought (SCoT) method to reduce reasoning latency by accelerating average reasoning speed through large and small model collaboration.
Outcome:	The proposed method reduces reasoning latency by 48%66% and 21%49% on GSM8K, MATH, GaoKao, CollegeMath and Olympiad datasets.

Uncertainty Modelling in Under-Represented Languages with Bayesian Deep Gaussian Processes (2025.coling-main)

Copied to clipboard

Ubaid Azam, Imran Razzak, Shelly Vishwakarma, Shoaib Jameel

Challenge:	Existing methods for NLP modeling underrepresented languages are limited due to lack of training data and language complexities.
Approach:	They propose a new method that integrates prior knowledge and leverages kernel functions to quantify uncertainty in under-represented languages.
Outcome:	The proposed method improves prediction accuracy and measurement of uncertainty in under-represented languages.

Automatic Estimation of Simultaneous Interpreter Performance (P18-2)

Copied to clipboard

Craig Stewart, Nikolai Vogler, Junjie Hu, Jordan Boyd-Graber, Graham Neubig

Multilinguality

Challenge:	Existing methods to predict interpreter confidence and the adequacy of the interpreted message are lacking.
Approach:	They propose to extend a QE pipeline to estimate interpreter performance by using five settings in three language pairs.
Outcome:	The proposed method can predict interpreter confidence and adequacy over five settings in three language pairs and improves interpretation strategy and evaluation measures.

Improving Model Generalization: A Chinese Named Entity Recognition Case Study (2021.acl-short)

Copied to clipboard

Guanqing Liang, Cane Wing-Ki Leung

Information Extraction & Text Mining

Challenge:	Named Entity Recognition (NER) is a fundamental building block for various downstream natural language processing tasks due to the ambiguous word boundaries and complex composition.
Approach:	They propose to resample entities within the same category to encourage a model to leverage both name and context knowledge in the training process.
Outcome:	The proposed method significantly improves a model’s ability to detect unseen entities, especially for company, organization and position categories.

Research Replication Prediction Using Weakly Supervised Learning (2020.findings-emnlp)

Copied to clipboard

Tianyi Luo, Xingyu Li, Hainan Wang, Yang Liu

Collaborative Performance Prediction for Large Language Models (2024.emnlp-main)

Challenge:	Existing methods to predict scientific claims’ replicability use only hand-extracted statistics features without utilizing research papers’ text information.
Approach:	They propose two weakly supervised learning approaches that use automatically extracted text information of research papers to improve the prediction accuracy of research replication using both labeled and unlabeled datasets.
Outcome:	The proposed methods achieve an accuracy of 75.76% over real-world datasets.

Copied to clipboard

Qiyuan Zhang, Fuyuan Lyu, Xue Liu, Chen Ma

Selective-LAMA: Selective Prediction for Confidence-Aware Evaluation of Language Models (2023.findings-eacl)

Challenge:	Large language models (LLMs) are one of the most important AI research powered by largescale parameters, high computational resources, and massive training data.
Approach:	They propose a framework that leverages historical performance of large language models and other design factors to improve prediction accuracy.
Outcome:	The proposed framework surpasses scaling laws in predicting performance of large language models . it also facilitates a detailed analysis of factor importance, an area previously overlooked .

Copied to clipboard

Hiyori Yoshikawa, Naoaki Okazaki

Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt Styles (2025.acl-long)

Challenge:	Recent studies suggest that neural language models learn and store a large amount of facts and commonsense knowledge from training data.
Approach:	They propose a benchmark task that evaluates the amount of relational knowledge stored in pre-trained language models.
Outcome:	The proposed evaluations show that the selection of confidence functions is more robust to simple guesses than the accuracy-based evaluation.

Copied to clipboard

Yuxi Xia, Pedro Henrique Luz De Araujo, Klim Zaporojets, Benjamin Roth

Rethinking Network Pruning – under the Pre-train and Fine-tune Paradigm (2021.naacl-main)

Challenge:	Existing studies neglect to measure the generalization of their methods to other prompt styles and different sizes of LLMs.
Approach:	They propose a framework that trains an auxiliary model for confidence estimation that aggregates responses from multiple LLMs to capture inter-model agreement.
Outcome:	The proposed framework integrates response agreement and focal loss with binary cross-entropy to improve calibration from baselines.

Copied to clipboard

Dongkuan Xu, Ian En-Hsu Yen, Jinxi Zhao, Zhibin Xiao

Probabilistic Robustness for Data Filtering (2023.eacl-main)

Challenge:	Existing pruning results on benchmark transformers, such as BERT, are not as remarkable as those of convolutional neural networks.
Approach:	They propose to apply a knowledge-aware pruning process to transformer-based pre-trained language models to reduce model size and model weight.
Outcome:	The proposed pruning method outperforms the leading competitors with a 20-times weight/FLOPs compression and neglectable loss in prediction accuracy.

Copied to clipboard

Yu Yu, Abdul Rafae Khan, Shahram Khadivi, Jia Xu

Unsupervised Extractive Summarization-Based Representations for Accurate and Explainable Collaborative Filtering (2021.acl-long)

Challenge:	Modern machine learning works with massive amounts of data on a range of tasks like language modeling, object detection, and data mining.
Approach:	They propose a probabilistic robustness rewarded data optimization approach to enhance the model's generalization power by selecting training data that optimizes probabilistic metrics.
Outcome:	The proposed approach achieves +17.2% increase of accuracy and -28.05 decrease of perplexity on unknown-domain test sets.

Copied to clipboard

Reinald Adrian Pugoy, Hung-Yu Kao

Blockwise Self-Attention for Long Document Understanding (2020.findings-emnlp)

Challenge:	Existing extractive summarization-based collaborative filtering models learn accurate representations of users and items based on user-given numeric ratings, but employing them is an oversimplification of user preferences and item characteristics.
Approach:	They propose to use BERT, K-Means embedding clustering, and multilayer perceptron to learn sentence embeddations, representation-explanations, and user-item interactions to create extractive summaries.
Outcome:	The proposed model improves rating prediction accuracy and user/item explainability.

Copied to clipboard

Jiezhong Qiu, Hao Ma, Omer Levy, Wen-tau Yih, Sinong Wang, Jie Tang

GLProtein: Global-and-Local Structure Aware Protein Representation Learning (2025.findings-emnlp)

Challenge:	Recent advances in pre-training and fine-tuning methods have drastically reshaped the landscape of natural language processing research.
Approach:	They propose a lightweight BERT model that introduces sparse block structures into the attention matrix to reduce memory consumption and training/inference time.
Outcome:	The proposed model uses 18.7-36.1% less memory and 12.0-25.1% more time to learn compared to an advanced BERT-based model, RoBERTa.

Copied to clipboard

Yunqing Liu, Wenqi Fan, Xiaoyong Wei, Li Qing

Representation Learning

Challenge:	Despite advances in protein sequence analysis, there remains potential for further exploration in integrating protein structural information.
Approach:	They propose a framework that integrates global structural similarity and local amino acid details to enhance protein pre-training.
Outcome:	The proposed framework outperforms existing methods in several bioinformatics tasks.

Entropy-Gated Branching for Efficient Test-Time Reasoning (2026.eacl-long)

Copied to clipboard

Xianzhi Li, Ethan Callanan, Abdellah Ghassel, Xiaodan Zhu

Reasoning

Challenge:	Empirical results show that branching at low uncertainty points can improve reasoning capabilities of large language models . however, these methods require substantially more computational resources, causing errors in high-stakes domains .
Approach:	They propose an inference technique that selectively expands prediction sequences at points of high uncertainty.
Outcome:	Empirical results show that the proposed method improves accuracy by 22.6% over standard inference while operating 31%-75% faster across math benchmarks.

Test-time Augmentation for Factual Probing (2023.findings-emnlp)

Copied to clipboard

Go Kamoda, Benjamin Heinzerling, Keisuke Sakaguchi, Kentaro Inui

Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding (2020.acl-main)

Challenge:	Existing methods to improve factual probing are relation-specific and do not generalize to unseen relation types.
Approach:	They propose to use test-time augmentation to augment and ensemble prompts at test time to reduce sensitivity to prompt variations.
Outcome:	The proposed method improves model confidence, but for other models, it leads to degradation.

Copied to clipboard

Yun Tang, Jing Huang, Guangtao Wang, Xiaodong He, Bowen Zhou

Recognition of Implicit Geographic Movement in Text (2020.lrec-1)

Challenge:	Existing knowledge graph embeddings have improved the knowledge graph link prediction task, but complex relations such as N-to-1, 1-to-N and N- to-N remain challenging to predict.
Approach:	They propose to extend RotatE from 2D complex domain to high dimensional space with orthogonal transforms to model relations.
Outcome:	The proposed method improves on N-to-1, 1-to-N and N- to-N cases while maintaining the capability for modeling symmetric/anti-symmetric, inverse and compositional relations.

Copied to clipboard

Scott Pezanowski, Prasenjit Mitra

Representation Learning

Challenge:	a growing field of research is analyzing the geographic movement of humans, animals, and other entities.
Approach:	They created a corpus of sentences labeled as describing geographic movement or not . they used hand labeling, crowd voting and machine learning to predict more labels .
Outcome:	a new method uses hand labeling, crowd voting and machine learning to predict more labels.

Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language Models (2025.acl-long)

Copied to clipboard

Mingyang Wang, Heike Adel, Lukas Lange, Yihong Liu, Ercong Nie, Jannik Strötgen, Hinrich Schuetze

Cold-Start and Interpretability: Turning Regular Expressions into Trainable Recurrent Neural Networks (2020.emnlp-main)

Challenge:	Multilingual language models store factual knowledge across languages but struggle to provide consistent responses to semantically equivalent prompts in different languages.
Approach:	They propose a linear shortcut method that bypasses computations in the final layers . this method improves accuracy and cross-lingual consistency .
Outcome:	The proposed method improves prediction accuracy and cross-lingual consistency.

Copied to clipboard

Chengyue Jiang, Yinggong Zhao, Shanbo Chu, Libin Shen, Kewei Tu

Understanding Spatial Relations through Multiple Modalities (2020.lrec-1)

Challenge:	Neural networks typically need large labeled data for training and are not easily interpretable.
Approach:	They propose a type of recurrent neural networks that combine neural networks and regular expression rules.
Outcome:	The proposed recurrent neural networks outperform previous neural approaches in low- and zero-shot scenarios and remain very competitive in rich-resource settings.

Copied to clipboard

Soham Dan, Hangfeng He, Dan Roth

Visual Data in NLP

Challenge:	Existing work on common sense reasoning and understanding of spatial relations is limited.
Approach:	They propose a spatial model that uses both textual and visual information to predict spatial relations between two entities in an image.
Outcome:	The proposed model improves prediction accuracy and coverage and deals with unseen subjects, objects and relations.

Expanding Abbreviations in a Strongly Inflected Language: Are Morphosyntactic Tags Sufficient? (L18-1)

Copied to clipboard

Piotr Żelasko

Syntactic Text Processing

Challenge:	In this paper, the problem of recovery of morphological information lost in abbreviated forms is addressed . correct inflected form of expanded abbrevation can be deduced from context words .
Approach:	They propose a deep bidirectional LSTM network with tag embedding to predict abbreviated words . they train on 10 million words from the Polish Sejm Corpus and achieve 74.2% prediction accuracy .
Outcome:	The proposed model achieves 74.2% accuracy on a smaller but more general corpus of Polish words.

A Sweet Rabbit Hole by DARCY: Using Honeypots to Detect Universal Trigger’s Adversarial Attacks (2021.acl-long)

Copied to clipboard

Thai Le, Noseong Park, Dongwon Lee

Mitigating Uncertainty in Document Classification (N19-1)

Challenge:	Existing adversarial examples can fool ML models by generating a fixed phrase that can drop the prediction accuracy of a textual neural network (NN) model to near zero on a target class.
Approach:	They propose a honeypot-based defense framework that greedily searches and injects multiple trapdoors into an NN model to “bait and catch” potential attacks.
Outcome:	The proposed algorithm detects attacks with 99% TPR and less than 2% FPR while maintaining prediction accuracy within 1% margin.

Copied to clipboard

Xuchao Zhang, Fanglan Chen, Chang-Tien Lu, Naren Ramakrishnan

Information Extraction & Text Mining

Challenge:	Existing models for uncertainty measurement are time-consuming and unable to handle large-scale data sets.
Approach:	They propose a new dropout-entropy method for uncertainty measurement and a metric learning method on feature representations to boost the performance of dropout based uncertainty methods.
Outcome:	The proposed method improves accuracy from 0.78 to 0.92 when 30% of the most uncertain predictions were handed over to human experts in “20NewsGroup” data.

Large Product Key Memory for Pretrained Language Models (2020.findings-emnlp)

Copied to clipboard

Gyuwan Kim, Tae Hwan Jung

From Scoring to Explanations: Evaluating SHAP and LLM Rationales for Rubric-based Teaching Quality Assessment (2026.findings-acl)

Challenge:	Existing product key memory (PKM) models that increase model capacity with insignificant computational overhead are limited to causal language modeling.
Approach:	They propose product key memory (PKM) that enables very efficient and exact nearest neighbor search in a large number of learnable memory slots.
Outcome:	The proposed product key memory improves model capacity and performance by replacing a feed-forward network with a model weighted model.

Copied to clipboard

Ivo Bueno, Babette Bühler, Philipp Stark, Tim Fütterer, Ulrich Trautwein, Dorottya Demszky, Heather Hill, Enkelejda Kasneci

Debiasing Multi-Entity Aspect-Based Sentiment Analysis with Norm-Based Data Augmentation (2024.lrec-main)

Challenge:	a framework for sentence-level interpretability of rubric-based scoring is proposed . aaron e. smith: automated scoring models provide little insight into why scores are produced .
Approach:	They propose a framework for sentence-level interpretability of rubric-based scoring that combines Shapley-value attributions with rationales generated by large language models.
Outcome:	The proposed framework compares fine-tuned pretrained language models with large language models . it shows that fine- tuned models outperform LLMs in prediction accuracy but exhibit label compression toward mid-scale scores .

Copied to clipboard

Scott Friedman, Joan Zheng, Hillel Steinmetz

Factual Probing Is [MASK]: Learning vs. Learning to Recall (2021.naacl-main)

Challenge:	Recent research has explored strategies for reduce measurable biases in NLP predictions while maintaining prediction accuracy on held-out test sets.
Approach:	They propose to augment training data with norm-based language templates derived from previous language resources to reduce biases in NLP models.
Outcome:	The proposed model reduces topical bias to less than half while maintaining prediction quality on held-out test sets.

Copied to clipboard

Zexuan Zhong, Dan Friedman, Danqi Chen

CERET: Cost-Effective Extrinsic Refinement for Text Generation (2024.naacl-long)

Challenge:	Existing methods for factual probing can interpret the model’s prediction accuracy as a lower bound on the amount of factual information it encodes.
Approach:	They propose a method which directly optimizes in continuous embedding space and can predict an additional 6.4% of facts in the LAMA benchmark.
Outcome:	The proposed method outperforms the best previous prompt method by 6.4% on the LAMA benchmark.

Copied to clipboard

Jason Cai, Hang Su, Monica Sunkara, Igor Shalyminov, Saab Mansour

Text Generation

Challenge:	Large Language Models (LLMs) generate incomplete, biased or misleading outputs in their initial attempts.
Approach:	They propose a method for refining text generation that takes into account semantic stability, entailment and inter-sample uncertainty measures.
Outcome:	The proposed method outperforms self-consistency and self-rerank baselines under various task setups by 1.6% and 3.5% respectively.

BBAEG: Towards BERT-based Biomedical Adversarial Example Generation for Text Classification (2021.naacl-main)

Copied to clipboard

Ishani Mondal

Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning (2024.emnlp-main)

Challenge:	Recent efforts to generate adversaries using rule-based synonyms and BERT-MLMs have been witnessed in general domain, but the ever-increasing biomedical literature poses unique challenges.
Approach:	They propose a black-box attack algorithm for biomedical text classification that uses rule-based synonyms and BERT-MLMs to generate adversarial examples.
Outcome:	The proposed algorithm performs stronger with better language fluency and semantic coherence than previous work.

Copied to clipboard

Jingyu Hu, Weiru Liu, Mengnan Du

Enhancing Recommendation Explanations through User-Centric Refinement (2025.findings-emnlp)

Challenge:	Recent studies highlight the effectiveness of using in-context learning (ICL) to steer large language models in processing tabular data.
Approach:	They propose a method that uses clustering and evolutionary strategies to curate a representative sample set from training data.
Outcome:	The proposed method significantly improves fairness across various metrics, showing its efficacy in real-world scenarios.

Copied to clipboard

Jingsen Zhang, Zihang Tian, Xueyang Feng, Xu Chen, Chong Chen

Learning Constraints for Structured Prediction Using Rectifier Networks (2020.acl-main)

Challenge:	Existing explanations for user reviews often fail to meet user-centric aspects, reducing their usefulness to users.
Approach:	They propose a paradigm that refines initial explanations generated by existing models during the inference stage to enhance their quality in multiple aspects.
Outcome:	The proposed model improves explanations generated by existing models during the inference stage to enhance their quality in multiple aspects.

Copied to clipboard

Xingyuan Pan, Maitrey Mehta, Vivek Srikumar

Challenge:	Various natural language processing tasks require domain expertise to design good constraints.
Approach:	They propose a framework for learning constraints in a network of linear inequalities over the output variables.
Outcome:	The proposed framework can be used to learn constraints from data on natural language processing tasks.

HermEs: Interactive Spreadsheet Formula Prediction via Hierarchical Formulet Expansion (2023.acl-long)

Copied to clipboard

Wanrong He, Haoyu Dong, Yihuai Gao, Zhichao Fan, Xingzhuo Guo, Zhitao Hou, Xiao Lv, Ran Jia, Shi Han, Dongmei Zhang

Challenge:	HermEs is a spreadsheet formula prediction language that is difficult for Excel users without programming experience to master.
Approach:	They propose a hierarchical approach to formula prediction via HiEraRchical forMulet ExpanSion . they propose generating formulas in a fixed order using hierarchically generated formulas .
Outcome:	The proposed approach improves formula prediction accuracy by guaranteeing correct grammar and streamlining token-level decoding with high-level Formulet.

Language models emulate certain cognitive profiles: An investigation of how predictability measures interact with individual differences (2024.findings-acl)

Copied to clipboard

Patrick Haller, Lena Bolliger, Lena Jäger

A Hierarchical Location Prediction Neural Network for Twitter User Geolocation (D19-1)

Challenge:	incorporating cognitive capacities increases predictive power of surprisal and entropy measures on reading data, whereas high performance in the psychometric tests is associated with lower sensitivity to predictability effects.
Approach:	They examine the predictive power (PP) of surprisal and entropy estimated from generative language models (LMs) on reading data from individuals who also completed a wide range of psychometric tests.
Outcome:	The LMs' predictive power is based on cognitive capacities and high performance in psychometric tests is associated with lower sensitivity to predictability effects.

Copied to clipboard

Binxuan Huang, Kathleen Carley

Jakiro: Boosting Speculative Decoding via Decoupled MoE (2026.acl-long)

Challenge:	Existing methods to estimate user location ignore hierarchical structure among locations.
Approach:	They propose a hierarchical location prediction neural network for Twitter user geolocation that first predicts the home country for a user, then uses the country result to guide the city-level prediction.
Outcome:	The proposed model can achieve state-of-the-art results over three common benchmarks under different feature settings and greatly reduces the mean error distance.

Copied to clipboard

Haiduo Huang, Fuwei Yang, Zhenhua Liu, Pengju Ren

Rationalizing Text Matching: Learning Sparse Alignments via Optimal Transport (2020.acl-main)

Challenge:	Existing methods to accelerate large language model inference have a fundamental limitation: candidates at the same tree layer share identical feature representations, constraining diversity and diminishing overall effectiveness.
Approach:	They propose a decoupled mixture of experts (MoE) into a draft model to generate diverse tokens from distinct feature spaces.
Outcome:	The proposed approach achieves significant speedups over strong baselines, with notable improvements in non-greedy scenarios where token diversity is crucial.

Copied to clipboard

Kyle Swanson, Lili Yu, Tao Lei

GREENER: Graph Neural Networks for News Media Profiling (2022.emnlp-main)

Challenge:	Existing models that use only rationales to explain a prediction are limited by the complexity of deep neural networks.
Approach:	They extend selective rationalization to text matching by using optimal transport to find a minimal cost alignment between inputs.
Outcome:	The proposed model achieves very sparse rationale selections with high fidelity while preserving prediction accuracy compared to strong attention baseline models.

Copied to clipboard

Panayot Panayotov, Utsav Shukla, Husrev Taha Sencar, Mohamed Nabeel, Preslav Nakov

Structured Data in NLP

Challenge:	a new method for profiling news media on the Web addresses the factuality of reporting and bias problem . a recent study has focused on text features but has focused primarily on text .
Approach:	They propose a model that models the similarity between media outlets based on their audience overlap . they propose GREENER, which builds a graph of inter-media connections based upon audience overlap.
Outcome:	The proposed model improves on state-of-the-art models on two datasets.

JPG - Jointly Learn to Align: Automated Disease Prediction and Radiology Report Generation (2022.coling-1)

Copied to clipboard

Jingyi You, Dongyuan Li, Manabu Okumura, Kenji Suzuki

Visual Data in NLP

Challenge:	Existing methods rarely consider cross-modal alignment between textual and visual features and ignore disease tags as auxiliary for report generation.
Approach:	They propose a "Jointly learning framework for automated disease Prediction and radiology report Generation" the framework integrates cross-modal alignment between textual and visual features and disease tags to improve the quality of reports.
Outcome:	The proposed framework improves the quality of radiology reports by combining the main task and auxiliary tasks.

DetectiveNN: Imitating Human Emotional Reasoning with a Recall-Detect-Predict Framework for Emotion Recognition in Conversations (2024.findings-emnlp)

Copied to clipboard

Simin Hong, Jun Sun, Taihao Li

Reasoning

Challenge:	Existing methods for Emotion Recognition in conversations are insufficient in understanding the rich historical emotional context.
Approach:	They propose a novel model that utilizes a "recall-detect-predict" framework to imitate human emotional reasoning by 'recalling' past interactions of a speaker to collect emotional cues.
Outcome:	The proposed model outperforms existing methods on three benchmark datasets and significantly outperformed existing methods.

Numeracy enhances the Literacy of Language Models (2021.emnlp-main)

Copied to clipboard

Avijit Thawani, Jay Pujara, Filip Ilievski

Dual Supervision Framework for Relation Extraction with Distant Supervision and Human Annotation (2020.coling-main)

Challenge:	Specialized number representations have shown improvements on numerical reasoning tasks like arithmetic word problems and masked number prediction.
Approach:	They propose to use six different number encoders to improve masked word prediction by avoiding conflating nominal and ordinal number occurrences.
Outcome:	The proposed representations improve masked word prediction accuracy and generalize to contexts without annotated numbers.

Copied to clipboard

Woohwan Jung, Kyuseok Shim

Information Extraction & Text Mining

Challenge:	Existing studies on relation extraction (RE) use labeled training data for relation extraction models but it is expensive and time-consuming.
Approach:	They propose a dual supervision framework which utilizes both types of data to train relation extraction models.
Outcome:	The proposed framework can predict labels by human annotation and distant supervision without labeling bias since it is expensive and time-consuming.

Back Attention: Understanding and Enhancing Multi-Hop Reasoning in Large Language Models (2025.emnlp-main)

Copied to clipboard

Zeping Yu, Yonatan Belinkov, Sophia Ananiadou

InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions (2023.emnlp-main)

Challenge:	Increasing the ability of large language models to perform latent multihop reasoning is crucial for reducing the cost and deployment challenges.
Approach:	They propose an interpretability method that traces how logits propagate across layers and positions toward the final prediction.
Outcome:	The proposed method improves accuracy on five reasoning datasets.

Copied to clipboard

Bodhisattwa Majumder, Zexue He, Julian McAuley

What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons (D19-1)

Challenge:	Debiasing methods in NLP models focus on isolating information related to a sensitive attribute (e.g., gender or race) but instead argue that a favorable debiaser should use sensitive information ‘fairly,’ with explanations, rather than blindly eliminating it.
Approach:	They propose that a favorable debiasing method should use sensitive information ‘fairly,’ with explanations, rather than blindly eliminating it.
Outcome:	The proposed approach reduces bias in explanations while maintaining the same prediction accuracy.

Copied to clipboard

Ji Xin, Jimmy Lin, Yaoliang Yu

Quantile Regression with Large Language Models for Price Prediction (2025.findings-acl)

Challenge:	Biological neural systems consist of a huge number of neurons, and can react to the environment in complicated ways.
Approach:	They propose a metric to quantify the sensitivity of neurons to each label and conduct experiments to prove it.
Outcome:	The proposed metric is based on a set of experiments that show that dropping an arbitrary neuron significantly degrades the accuracy of the model.

Copied to clipboard

Nikhita Vedula, Dushyanta Dhyani, Laleh Jalali, Boris N. Oreshkin, Mohsen Bayati, Shervin Malmasi

Mitigating Interviewer Bias in Multimodal Depression Detection: An Approach with Adversarial Learning and Contextual Positional Encoding (2025.findings-emnlp)

Challenge:	Existing approaches to structured prediction tasks focus on point estimates and lack systematic comparison across different methods.
Approach:	They propose a novel quantile regression approach that enables LLMs to produce full predictive distributions, improving upon traditional point estimates.
Outcome:	The proposed model outperforms encoder architectures, embedding-based methods, and few-shot learning methods in prediction accuracy and distributional calibration.

Copied to clipboard

Enshi Zhang, Christian Poellabauer

Causality-Guided Multi-Memory Interaction Network for Multivariate Stock Price Movement Prediction (2023.acl-long)

Challenge:	Clinical interviews are a standard method for assessing depression . however, these methods neglect the broader conversational context .
Approach:	They develop a multimodal dialogue-level transformer that captures the dynamics of dialogue within each interview . they also build an adversarial classifier with a gradient reversal layer to learn shared representations .
Outcome:	The proposed model captures the dynamics of dialogue within each interview using positional embedding and question context vectors.

Copied to clipboard

Di Luo, Weiheng Liao, Shuqi Li, Xin Cheng, Rui Yan

Multimodality

Challenge:	Existing models for stock price movement prediction use auxiliary data, but we assume other stocks should be utilized as auxiliary information to enhance performance.
Approach:	They propose a Causality-guided multi-memory interaction network for stock movement prediction which transforms basic attention into Causal Attention by calculating transfer entropy between multivariate stocks.
Outcome:	The proposed model outperforms existing models on three real-world datasets from the U.S. and Chinese markets.

Explainable Text Classification with LLMs: Enhancing Performance through Dialectical Prompting and Explanation-Guided Training (2025.findings-emnlp)

Copied to clipboard

Huaming Du, Lei Yuan, Cancan Feng, Guisong Liu, Gang Kou, Carl Yang

Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization (2021.emnlp-main)

Challenge:	Existing explanation methods that generate keywords may be less effective due to missing critical contextual information.
Approach:	They propose a new method to generate explanations for possible labels using LLMs and a dialectical prompt.
Outcome:	The proposed method significantly improves accuracy and explanation quality over state-of-the-art methods on multiple datasets from diverse domains.

Copied to clipboard

Yujian Gan, Xinyun Chen, Matthew Purver

Text Generation

Challenge:	Existing text-to-SQL models do not generalize when faced with domain knowledge that does not frequently appear in training data.
Approach:	They propose a human-curated dataset based on the Spider benchmark for text-to-SQL translation.
Outcome:	The proposed model performs better on unseen domains than existing models on public benchmarks.

Leveraging LLM-Generated Schema Descriptions for Unanswerable Question Detection in Clinical Data (2025.coling-main)

Copied to clipboard

Donghee Han, Seungjae Lim, Daeyoung Roh, Sangryul Kim, Sehyun Kim, Mun Yong Yi

NYAYAANUMANA and INLEGALLLAMA: The Largest Indian Legal Judgment Prediction Dataset and Specialized Language Model for Enhanced Decision Analysis (2025.coling-main)

Challenge:	Existing methods rely on model uncertainty but lack interpretability and data imbalance.
Approach:	They propose a lightweight model that predicts relevant database schemas to detect unanswerable questions, enhancing interpretability and addressing the data imbalance in binary classification tasks.
Outcome:	The proposed model improves interpretability and improves accuracy in binary classification tasks.

Copied to clipboard

Shubham Kumar Nigam, Deepak Patnaik Balaramamahanthi, Shivam Mishra, Noel Shallum, Kripabandhu Ghosh, Arnab Bhattacharya

Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems (2022.emnlp-main)

Challenge:	In India, a significant backlog of cases burdens the legal system.
Approach:	They present a corpus of 7,02,945 preprocessed Indian legal cases compiled for LJP . they use a domain-specific generative large language model tailored to the intricacies of the legal system .
Outcome:	The proposed dataset surpasses existing datasets like PredEx and ILDC, and improves prediction accuracy and comprehensible explanations.

Copied to clipboard

Neeraj Varshney, Chitta Baral

Green & Sustainable NLP

Challenge:	Pre-trained language models such as RoBERTa, ELECTRA, and T5 have a large number of parameters which makes them slow and computationally expensive.
Approach:	They propose a technique that utilizes a collection of models of varying capacities to accurately yet efficiently output predictions.
Outcome:	The proposed technique saves up to 88.93% computation cost and consistently achieves superior prediction accuracy with an improvement of up to 2.18%.

Tracking the Newsworthiness of Public Documents (2024.acl-long)

Copied to clipboard

Alexander Spangher, Serdar Tumgoren, Ben Welsh, Nanyun Peng, Emilio Ferrara, Jonathan May

Challenge:	a new method to model news coverage of local government is needed . we show that newsworthiness predictions can be useful for journalists seeking to keep abreast of local governments.
Approach:	They propose a method that explicitly models when and why stories get press attention . they use an annotated corpus of news articles to build models that predict if a policy item will get covered .
Outcome:	The proposed model outperforms retrieval-based methods with limited annotated data and language use between corpora.

Holistic Prediction on a Time-Evolving Attributed Graph (2023.acl-long)

Copied to clipboard

Shohei Yamasaki, Yuya Sasaki, Panagiotis Karras, Makoto Onizuka

Structured Data in NLP

Challenge:	Existing methods for predicting future links, nodes, and attributes of time-evolving attributed graphs are not accurate.
Approach:	They propose a framework that predicts node attributes and topology changes such as appearance and disappearance of links and the emergence and loss of nodes.
Outcome:	The proposed framework improves on existing methods that assume that each link, node, and attribute prediction is independent and fails to predict new nodes that were not observed in the past.

Do Large Language Models Have “Emotion Neurons”? Investigating the Existence and Role (2025.findings-acl)

Copied to clipboard

Jaewook Lee, Woojin Lee, Oh-Woog Kwon, Harksoo Kim

TextGenSHAP: Scalable Post-Hoc Explanations in Text Generation with Long Documents (2024.findings-acl)

Challenge:	Existing evaluations of LLMs' emotional capabilities have been criticized for not illuminating how emotion information is processed and represented within an LLM.
Approach:	They examine whether there are “emotion neurons” within large language models that selectively process and express certain emotions and what functional role they play.
Outcome:	The proposed model is based on the representative emotion theory of the six basic emotions and demonstrates that it is functionally significant to examine whether the prediction accuracy for a specific emotion decreases when the neurons are removed.

Copied to clipboard

James Enouen, Hootan Nakhost, Sayna Ebrahimi, Sercan Arik, Yan Liu, Tomas Pfister

When ”A Helpful Assistant” Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models (2024.findings-emnlp)

Challenge:	Large language models (LLMs) are difficult to explain and understand due to long input contexts and autoregressive output generation.
Approach:	They propose a post-hoc explanation method which incorporates LLM-specific techniques.
Outcome:	The proposed method improves retrieval recall and prediction accuracy significantly on open-domain question answering benchmarks.

Copied to clipboard

Mingqian Zheng, Jiaxin Pei, Lajanugen Logeswaran, Moontae Lee, David Jurgens

MALT-IT2: A New Resource to Measure Text Difficulty in Light of CEFR Levels for Italian L2 Learning (2020.lrec-1)

Challenge:	Commercial AI systems often define the role of the LLM in system prompts.
Approach:	They conduct a systematic evaluation of personas in system prompts by adding 162 roles covering 6 types of interpersonal relationships and 8 domains of expertise.
Outcome:	The proposed model does not improve performance in the system prompt setting where no persona is added.

Copied to clipboard

Luciana Forti, Giuliana Grego Bolli, Filippo Santarelli, Valentino Santucci, Stefania Spina

INarIG: Iterative Non-autoregressive Instruct Generation Model For Word-Level Auto Completion (2023.findings-emnlp)

Challenge:	Existing methods to assess text difficulty in second or foreign language classrooms are subjective . formal and quantitative characteristics of a text have a major role in determining comprehensibility .
Approach:	They propose a system that automatically classifies inputted texts according to CEFR levels . they describe the rationale of the project and the corpus and computational system it is based on .
Outcome:	The proposed system is able to predict text difficulty in Italian, and it is reliable, the authors say . they also identify the features which most influenced the predictions .

Copied to clipboard

Hengchao Shang, Zongyao Li, Daimeng Wei, Jiaxin Guo, Minghan Wang, Xiaoyu Chen, Lizhi Lei, Hao Yang

Text Generation

Challenge:	Existing models for word-level autocompletion (WLAC) only use human typed sequences as prefixes in decoding module.
Approach:	They propose a novel iterative nonautoregressive instruct generation model for WLAC task . it uses human typed sequences and iterating decoding with subwords to fully utilize input information.
Outcome:	The proposed model is more competent in dealing with low-frequency words, and achieves state-of-the-art results on the WMT22 and benchmark datasets.

CIKT: A Collaborative and Iterative Knowledge Tracing Framework with Large Language Models (2025.emnlp-main)

Copied to clipboard

Runze Li, Siyu Wu, Jun Wang, Wei Zhang

Does Reasoning Introduce Bias? A Study of Social Bias Evaluation and Mitigation in LLM Reasoning (2025.findings-emnlp)

Challenge:	Knowledge Tracing (KT) aims to model a student’s learning state over time and predict their future performance.
Approach:	They propose a framework that harnesses Large Language Models to enhance both prediction accuracy and explainability by a synergistic optimization loop.
Outcome:	The proposed framework improves both prediction accuracy and explainability by using a synergistic optimization loop.

Copied to clipboard

Xuyang Wu, Jinming Nian, Ting-Ruen Wei, Zhiqiang Tao, Hsin-Tai Wu, Yi Fang

DRES: Fake news detection by dynamic representation and ensemble selection (2025.emnlp-main)

Challenge:	Recent advances in large language models have enabled automatic generation of chain-of-thought reasoning . however, when reasoning steps reflect social stereotypes, they can reinforce harmful associations and lead to misleading conclusions.
Approach:	They propose a method that detects how model predictions change across incremental reasoning steps.
Outcome:	The proposed method outperforms a stereotype-free baseline and improves accuracy.

Copied to clipboard

Faramarz Farhangian, Leandro Augusto Ensina, George D C Cavalcanti, Rafael M. O. Cruz

From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent (2026.findings-acl)

Challenge:	Existing methods for text-based fake news detection are limited due to context sensitivity and generalization issues.
Approach:	They propose a method that leverages instance hardness measures to estimate the classification difficulty for each news article across multiple textual feature representations.
Outcome:	The proposed method significantly improves over state-of-the-art methods, confirming the effectiveness of representation selection based on instance hardness and dynamic ensemble selection.

Copied to clipboard

Mingyu Huang, Weiqing Min, Ying Jin, Yilin Wang, Shuqiang Jiang

Challenge:	Existing approaches to individualized glucose regulation are generic and do not account for individual-specific glucose dynamics.
Approach:	They propose a physio-feedback agentic loop that integrates individualized absorption modeling with dietary intervention to regulate glucose response.
Outcome:	The proposed system improves prediction accuracy and reduces glucose excursions.

Accurate and Data-Efficient Toxicity Prediction when Annotators Disagree (2024.emnlp-main)

Copied to clipboard

Harbani Jaggi, Kashyap Coimbatore Murali, Eve Fleisig, Erdem Biyik

Comparing Neighbors Together Makes it Easy: Jointly Comparing Multiple Candidates for Efficient and Effective Retrieval (2024.emnlp-main)

Challenge:	Disagreement among annotators can reveal nuances in subjective tasks that lack a simple ground truth .
Approach:	They propose three approaches to predict annotator ratings on the toxicity of text . they integrate annotators' history, demographics, survey information into their models .
Outcome:	The proposed approach outperforms other methods in toxicity rating prediction.

Copied to clipboard

Jonghyun Song, Cheyon Jin, Wenlong Zhao, Andrew McCallum, Jay-Yoon Lee

Information Retrieval

Challenge:	Experimental results show that using only bi-encoders as an intermediate reranker can improve top-1 accuracy with negligible slowdown (7%).
Approach:	They propose a framework that compares a query and multiple embeddings of similar candidates through shallow self-attention layers, delivering rich representations contextualized to each other.
Outcome:	The proposed framework compares a query and multiple embeddings of similar candidates through shallow self-attention layers, delivering rich representations contextualized to each other.

HyperKGR: Knowledge Graph Reasoning in Hyperbolic Space with Graph Neural Network Encoding Symbolic Path (2025.emnlp-main)

Copied to clipboard

Lihui Liu