Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Dynamic Label Name Refinement for Few-Shot Dialogue Intent Classification (2025.acl-short)

Challenge:	Large Language Models (LLMs) have shown remarkable capabilities in environmental perception, reasoning-based decision-making, and simulating complex human behaviors, particularly in interactive role-playing contexts.
Approach:	They propose a framework to assess LLMs' proficiency in portraying advanced human behaviors through murder mystery games using eight intricately crafted scripts.
Outcome:	The framework evaluates LLMs' performance in portraying advanced human behaviors through murder mystery games.

Copied to clipboard

Gyutae Park, Ingeol Baek, Byeongjeong Kim, Joongbo Shin, Hwanhee Lee

Dialogue Systems & Conversational Agents

Challenge:	Current intent classification systems face significant challenges due to the vast number of possible intents and significant semantic overlap among similar intent classes.
Approach:	They propose a dynamic label refinement method that retrieves relevant examples for a test input and leverages a large language model to dynamically refine intent labels based on semantic understanding.
Outcome:	The proposed method resolves confusion between semantically similar intents and generates more interpretable intent labels.

Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora (2025.acl-short)

Copied to clipboard

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

Automatic detection of dyslexia based on eye movements during reading in Russian (2025.acl-short)

Challenge:	Existing methods to efficiently filter large web corpora require GPU resources.
Approach:	They propose an ensemble approach that leverages two contrasting KenLMs to filter large web corpora.
Outcome:	The proposed method significantly reduces noisy content while preserving high-quality content compared to the traditional KenLM training method.

Copied to clipboard

Anna Laurinavichyute, Anastasiya Lopukhina, David Robert Reich

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 .

Doc-React: Multi-page Heterogeneous Document Question-answering (2025.acl-short)

Copied to clipboard

Junda Wu, Yu Xia, Tong Yu, Xiang Chen, Sai Sree Harsha, Akash V Maharaj, Ruiyi Zhang, Victor Bursztyn, Sungchul Kim, Ryan A. Rossi, Julian McAuley, Yunyao Li, Ritwik Sinha

ConECT Dataset: Overcoming Data Scarcity in Context-Aware E-Commerce MT (2025.acl-short)

Challenge:	Existing methods for integrating information across multiple modalities are suboptimal for multi-page, multimodal documents.
Approach:	They propose an adaptive iterative framework that balances information gain and uncertainty reduction at each step.
Outcome:	The proposed framework captures relevant multimodal content and achieves strong performance on complex QA tasks.

Copied to clipboard

Mikołaj Pokrywka, Wojciech Kusa, Mieszko Rutkowski, Mikołaj Koszowski

Machine Translation

Challenge:	Neural Machine Translation (NMT) has improved translation by using Transformer-based models, but still struggles with word ambiguity and context.
Approach:	They create a new Czech-to-polish e-commerce product translation dataset coupled with images and product metadata consisting of 11,400 sentence pairs.
Outcome:	The proposed model incorporates visual cues alongside textual data to improve translation quality.

A Measure of the System Dependence of Automated Metrics (2025.acl-short)

Copied to clipboard

Pius Von Däniken, Jan Milan Deriu, Mark Cieliebak

Machine Translation

Challenge:	Recent advances in machine translation evaluations are expensive and time-intensive.
Approach:	They propose a method to evaluate the correlation between human and metric scores . they argue that it is equally important to ensure that metrics treat all systems fairly and consistently.
Outcome:	The proposed method ignores a central requirement of the evaluation process, and ignores the need for a thorough evaluation procedure.

Call for Rigor in Reporting Quality of Instruction Tuning Data (2025.acl-short)

Copied to clipboard

Hyeonseok Moon, Jaehyung Seo, Heuiseok Lim

BQA: Body Language Question Answering Dataset for Video Large Language Models (2025.acl-short)

Challenge:	Instruction tuning is crucial for adapting large language models (LLMs) to user intentions.
Approach:	They propose to use hyperparameters for training models that are often selected arbitrarily without adequate justification to make arbitrary conclusions.
Outcome:	The results show that arbitrary hyperparameter decisions can make any arbitrary conclusion.

Copied to clipboard

Shintaro Ozaki, Kazuki Hayashi, Miyu Oba, Yusuke Sakai, Hidetaka Kamigaito, Taro Watanabe

Grounded, or a Good Guesser? A Per-Question Balanced Dataset to Separate Blind from Grounded Models for Embodied Question Answering (2025.acl-short)

Challenge:	a large part of human communication relies on nonverbal cues such as facial expressions, eye contact, and body language.
Approach:	They propose to validate whether video large language models can correctly interpret body language from short clips of body language.
Outcome:	The proposed model can correctly interpret emotions from short clips of body language.

Copied to clipboard

Miles Shelton, Nate Wingerd, Kritim K Rijal, Ayush Garg, Adelina Gutic, Brett Barnes, Catherine Finegan-Dollak

Learning Sparsity for Effective and Efficient Music Performance Question Answering (2025.acl-short)

Challenge:	Embodied question answering (EQA) is based on using perception and action in an environment to answer natural language questions.
Approach:	They propose a "per-question balanced" EQA dataset that uses two different environments to ground a model's answers in its environment.
Outcome:	The proposed model performs better than chance on the PQB-EQA benchmark, showing that it does not require the model to use perception, let alone to act in its environment to find the answer.

Copied to clipboard

Xingjian Diao, Tianzhen Yang, Chunhui Zhang, Weiyi Wu, Ming Cheng, Jiang Gui

Cross-Lingual Transfer of Cultural Knowledge: An Asymmetric Phenomenon (2025.acl-short)

Challenge:	Existing Music AVQA methods rely on dense and unoptimized representations, leading to inefficiencies in the isolation of key information, reduction of redundancy, and prioritization of critical samples.
Approach:	They propose a sparse learning framework specifically designed for Music AVQA to address these challenges.
Outcome:	The proposed framework reduces training time by 28.32% while maintaining accuracy while maintaining state-of-the-art performance on the Music AVQA datasets.

Copied to clipboard

Chen Zhang, Zhiyuan Liao, Yansong Feng

Cross-Lingual Transfer

Challenge:	Existing studies evaluate whether large language models handle global cultural diversity . however, mechanisms behind cultural knowledge acquisition remain unexplored .
Approach:	They propose an interpretable framework to study cultural knowledge transfer in large language models . they observe bidirectional cultural transfer between English and other high-resource languages .
Outcome:	The proposed framework ensures training data transparency and controls transfer effects.

Leveraging Human Production-Interpretation Asymmetries to Test LLM Cognitive Plausibility (2025.acl-short)

Copied to clipboard

Suet-Ying Lam, Qingcheng Zeng, Jingyi Wu, Rob Voigt

Explainability & Interpretability in NLP

Challenge:	Existing research on the linguistic capabilities of large language models has focused on their performance in language interpretation.
Approach:	They examine whether large language models (LLMs) process language similarly to humans . they use an empirically documented asymmetry between production and interpretation in humans a testbed .
Outcome:	The proposed model can replicate human-like distinctions between production and interpretation.

Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution’s Characteristics (2025.acl-short)

Copied to clipboard

Lorenzo Jaime Yu Flores, Ori Ernst, Jackie CK Cheung

Text Generation

Challenge:	Existing methods for estimating confidence in text generation do not account for many valid answers in generation tasks.
Approach:	They propose task-agnostic confidence metrics that rely solely on model probabilities without the need for further fine-tuning or heuristics.
Outcome:	The proposed models improve the accuracy of BART and Flan-T5 on summarization, translation, and question answering datasets.

KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education? (2025.acl-short)

Copied to clipboard

Tianshi Zheng, Weihan Li, Jiaxin Bai, Weiqi Wang, Yangqiu Song

Robustness in NLP

Challenge:	Existing knowledge discrepancies between textbooks and large language models can undermine RAG systems' performance.
Approach:	They propose to use a dataset to test RAG system robustness against knowledge discrepancies.
Outcome:	The proposed dataset shows that RAG systems suffer performance degradation when faced with knowledge discrepancies.

Improving Parallel Sentence Mining for Low-Resource and Endangered Languages (2025.acl-short)

Copied to clipboard

Shu Okabe, Katharina Hämmerl, Alexander Fraser

Low-Resource NLP

Challenge:	Parallel sentence mining is a technique used to find matching sentence pairs from a source and target language.
Approach:	They propose a benchmark dataset for parallel sentence mining on three low-resource languages . they apply alignment post-processing and cluster-based isotropy enhancement techniques to one of them .
Outcome:	The proposed datasets show better mining quality overall for low-resource languages . the proposed methods are crucial for optimizing parallel data extraction for low resource languages - a new study shows.

Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty? (2025.acl-short)

Copied to clipboard

Jiayu Liu, Qing Zong, Weiqi Wang, Yangqiu Song

Limited-Resource Adapters Are Regularizers, Not Linguists (2025.acl-short)

Challenge:	Large language models (LLMs) are increasingly used in high-stakes domains, but their confidence is inconsistent in out-of-distribution scenarios.
Approach:	They define "marker confidence" as the observed accuracy when a model employs an epistemic marker.
Outcome:	The proposed model generalizes well within the same distribution, but its confidence is inconsistent in out-of-distribution scenarios.

Copied to clipboard

Marcell Fekete, Nathaniel Romney Robinson, Ernests Lavrinovics, Djeride Jean-Baptiste, Raj Dabre, Johannes Bjerva, Heather Lent

LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks (2025.acl-short)

Challenge:	Existing studies show that cross-lingual transfer from high-resource languages is promising for low-resourced machine translation.
Approach:	They propose to use adapter souping and cross-attention fine-tuning to leverage language transfer for Creoles, an under-served group of low-resource languages.
Outcome:	The proposed method improves performance over baselines but not meaningfully with adapters.

Copied to clipboard

Anna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi, Desmond Elliott, Raquel Fernández, Albert Gatt, Esam Ghaleb, Mario Giulianelli, Michael Hanna, Alexander Koller, Andre Martins, Philipp Mondorf, Vera Neplenbroek, Sandro Pezzelle, Barbara Plank, David Schlangen, Alessandro Suglia, Aditya K Surikuchi, Ece Takmaz, Alberto Testoni

Challenge:	Existing evaluations of NLP models with LLMs are based on human judgments . however, there are concerns about their validity and reproducibility in proprietary models .
Approach:	They evaluate 11 current LLMs for their ability to replicate annotations. they show substantial variance across models and datasets.
Outcome:	The proposed model can replicate human annotations on 20 NLP datasets and show substantial variance across models and datasets.

FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference Rankings (2025.acl-short)

Copied to clipboard

Tong Liu, Xiao Yu, Wenxuan Zhou, Jindong Gu, Volker Tresp

Challenge:	Efficient preference optimization algorithms such as Direct Preference Optimization (DPO) have become a popular approach in aligning large language models with human preferences.
Approach:	They propose a preference optimization variant that instead down-weighs misranked preference pairs and prioritizes enhancing the model’s understanding of pairs that it can already rank correctly.
Outcome:	The proposed model outperforms DPO on benchmarks like Alpaca Eval 2.0 and Arena-Hard using mistral-base-7B and Llama-3-Instruct-8B with the introduced hyperparameter fixed.

Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs (2025.acl-short)

Copied to clipboard

Megh Thakkar, Quentin Fournier, Matthew Riemer, Pin-Yu Chen, Amal Zouaq, Payel Das, Sarath Chandar

Can Uniform Meaning Representation Help GPT-4 Translate from Indigenous Languages? (2025.acl-short)

Challenge:	Large language models (LLMs) excel in specific technical fields, but are not explicitly trained to be safe.
Approach:	They propose a model merging-based alignment method that allows for safer domain-specific models that preserve their utility.
Outcome:	The proposed method improves safety alignment on LLMs with minimal degradation on domain-specific benchmarks.

Copied to clipboard

Shira Wein

Subword models struggle with word learning, but surprisal hides it (2025.acl-short)

Challenge:	In this study, we examine the downstream utility of Uniform Meaning Representation (UMR) for low-resource languages.
Approach:	They explore the utility of Uniform Meaning Representation (UMR) for low-resource languages by incorporating it into GPT-4 prompts.
Outcome:	The proposed model performs better than existing models in Navajo, Arápaho, and Kukama with and without demonstrations and annotations.

Copied to clipboard

Bastian Bunzeck, Sina Zarrieß

LLM as Entity Disambiguator for Biomedical Entity-Linking (2025.acl-short)

Challenge:	Subword LMs struggle to discern words and non-words with high accuracy, character LM models do this easily and consistently.
Approach:	They propose to model word learning in subword and character language models with the psycholinguistic lexical decision task.
Outcome:	The results suggest that word learning and syntactic learning are separable in character LMs.

Copied to clipboard

Christophe Ye, Cassie S. Mitchell

Towards Geo-Culturally Grounded LLM Generations (2025.acl-short)

Challenge:	Entity linking involves normalizing a mention in medical text to a unique identifier in a knowledge base, such as UMLS or MeSH.
Approach:	They propose to use a large language model as an entity disambiguator to enhance the accuracy of alias-matching entity linking methods.
Outcome:	The proposed method surpasses existing methods on biomedical datasets by up to 16 points in accuracy.

Copied to clipboard

Piyawat Lertvittayakumjorn, David Kinney, Vinodkumar Prabhakaran, Donald Martin Jr., Sunipa Dev

MUSTS: MUltilingual Semantic Textual Similarity Benchmark (2025.acl-short)

Challenge:	Contemporary large language models (LLMs) are pretrained on huge corpora of natural language text and fine-tuned using human feedback to improve their quality.
Approach:	They compare the performance of standard LLMs, LLM augmented with retrievals from a bespoke knowledge base and LLM with retrieval from . a web search on multiple cultural awareness benchmarks.
Outcome:	The retrieval augmented generation and search grounding techniques improve LLMs' ability to display familiarity with various national cultures on cultural awareness benchmarks.

Copied to clipboard

Tharindu Ranasinghe, Hansi Hettiarachchi, Constantin Orasan, Ruslan Mitkov

Can Large Language Models Accurately Generate Answer Keys for Health-related Questions? (2025.acl-short)

Challenge:	Existing benchmarks for semantic textual similarity (STS) are limited to high-resource languages and do not include datasets annotated focusing on relatedness instead of similarity.
Approach:	They propose to evaluate multilingual semantic textual similarity benchmarks which span 13 languages and annotated datasets to evaluate and compare them.
Outcome:	The proposed method is the most comprehensive benchmark of multilingual STS methods.

Copied to clipboard

Davis Bartels, Deepak Gupta, Dina Demner-Fushman

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

Challenge:	Evaluating the factuality of LLM generated answers is challenging for many tasks, including question answering.
Approach:	They propose to use information nuggets to evaluate the factuality of LLM generated answers . they find providing an example and extracting nuggots from an answer is the best approach .
Outcome:	The proposed model performs best when compared to human nugget generation.

Copied to clipboard

Katherine Thai, Mohit Iyyer

A Little Human Data Goes A Long Way (2025.acl-short)

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

Copied to clipboard

Dhananjay Ashok, Jonathan May

Challenge:	Existing methods to replace human annotation are expensive and limited.
Approach:	They investigate the use of synthetic data in Fact Verification and Evidence-based Question Answering by replacing human-generated data with synthetic points on eight diverse datasets.
Outcome:	The proposed method shows promise but performance declines when replacing up to 90% of training data with synthetic data are severe . the proposed method can be used to improve models trained on purely synthetic data by including as few as 125 human-generated data points.

Seeking Rational Demonstrations for Large Language Models: A Domain Generalization Approach to Unsupervised Cross-Domain Keyphrase Generation (2025.acl-short)

Copied to clipboard

Guangzhen Zhao, Yu Yao, Dechang Kong, Zhenjiang Dong

LexKeyPlan: Planning with Keyphrases and Retrieval Augmentation for Legal Text Generation: A Case Study on European Court of Human Rights Cases (2025.acl-short)

Challenge:	Unsupervised cross-domain keyphrase generation is crucial in real-world natural language processing scenarios, but its accuracy is limited by the distribution shift between source and target domain.
Approach:	They propose to seek rational demonstrations from the source domain and to use them to improve their ability in the unsupervised cross-domain keyphrase generation setting.
Outcome:	The proposed model achieves state-of-the-art on widely used cross-domain KG benchmarks and the results are published in the journal Nature.

Copied to clipboard

Santosh T.y.s.s, Elvin Quero Hernandez

SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement (2025.acl-short)

Challenge:	Large language models excel at text generation but often produce hallucinations due to their sole reliance on parametric knowledge.
Approach:	They propose a framework that integrates anticipatory planning into legal text generation by generating keyphrases outlining future content serving as forward-looking plan.
Outcome:	The proposed framework improves factual accuracy and coherence by retrieving information aligned with the intended content.

Copied to clipboard

Runnan Fang, Xiaobin Wang, Yuan Liang, Shuofei Qiao, Jialong Wu, Zekun Xi, Ningyu Zhang, Yong Jiang, Pengjun Xie, Fei Huang, Huajun Chen

Challenge:	Using Large Language Models (LLMs)-based agents can enhance their understanding of environments and tasks.
Approach:	They propose a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search exploration to refine their action knowledge in the current environment.
Outcome:	The proposed framework synthesizes possible scenarios with multi-step action invocation within the action space and performs Monte Carlo Tree Search exploration to refine action knowledge in the current environment.

Enhancing Retrieval Systems with Inference-Time Logical Reasoning (2025.acl-short)

Copied to clipboard

Felix Faltings, Wei Wei, Yujia Bao

Using Subtext to Enhance Generative IDRR (2025.acl-short)

Challenge:	Existing retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity and static embeddings.
Approach:	They propose an inference-time logical reasoning framework that incorporates logical thinking into retrieval process.
Outcome:	The proposed method outperforms traditional retrieval methods on synthetic and real-world benchmarks on synthetic queries and datasets.

Copied to clipboard

Zhipang Wang, Yu Hong, Weihao Sun, Guodong Zhou

State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models (2025.acl-short)

Challenge:	Arguments contain subtexts, but they are connotative and need prompts to be recognized . a lightweight subtext generator is helpful when the prompt doesn't raise a complex CoT.
Approach:	They leverage LLaMA to generate subtexts for argument pairs and verify their effectiveness . they construct a baseline IDRR using the decoder-only backbone LLama .
Outcome:	The proposed approach achieves higher F1 scores on two benchmarks than previous models.

Copied to clipboard

Wonjun Kang, Kevin Galim, Yuchen Zeng, Minjae Lee, Hyung Il Koo, Nam Ik Cho

Internal and External Impacts of Natural Language Processing Papers (2025.acl-short)

Challenge:	State Space Models (SSMs) have emerged as efficient alternatives to Transformers, but their application to SSMs remains unexplored.
Approach:	They propose a state-based PEFT method that adjusts state directly instead of using external prompts.
Outcome:	The proposed method is based on state-offset tuning, which directly affects state at every timestep.

Copied to clipboard

Yu Zhang

An Effective Incorporating Heterogeneous Knowledge Curriculum Learning for Sequence Labeling (2025.acl-short)

Challenge:	a new study examines the impact of NLP research published in top-tier conferences from 1979 to 2024 . language modeling has the widest internal and external influence, while linguistic foundations have lower impacts .
Approach:	They analyze citations from research articles and external sources to determine how NLP topics are consumed internally and externally.
Outcome:	The findings show that language modeling has the widest internal and external influence . ethics, bias, and fairness show significant attention in policy documents with fewer academic citations .

Copied to clipboard

Xuemei Tang, Jun Wang, Qi Su, Chu-Ren Huang, Jinghang Gu

Accelerating Dense LLMs via L0-regularized Mixture-of-Experts (2025.acl-short)

Challenge:	Existing approaches to enhance sequence labeling models require data heterogeneity and additional modules.
Approach:	They propose a dual-stage curriculum learning framework specifically designed for sequence labeling tasks.
Outcome:	The proposed model improves training and accelerates training, mitigating the slow training issue of complex models.

Copied to clipboard

Zhenyu Zhang, JiuDong Yang, Taozhaowen Taozhaowen, Meng Chen

Do Multimodal Large Language Models Truly See What We Point At? Investigating Indexical, Iconic, and Symbolic Gesture Comprehension (2025.acl-short)

Challenge:	Existing methods for accelerating large language models (LLMs) suffer from slow and costly inference.
Approach:	They propose a lightweight MoE approach using cluster confusion matrix and dynamic batching to accelerate dense LLMs.
Outcome:	The proposed method achieves 2.5x speedup over dense models while maintaining competitive performance.

Copied to clipboard

Noriki Nishida, Koji Inoue, Hideki Nakayama, Mayumi Bono, Katsuya Takanashi

Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering (2025.acl-short)

Challenge:	In recent years, multimodal large language models (MLLMs) excel at integrating textual, auditory, and visual information, but their ability to accurately interpret gestures remains underexplored.
Approach:	They annotated five gesture type labels to 925 gesture instances from the Miraikan SC Corpus and analyzed gesture descriptions generated by state-of-the-art MLLMs, including GPT-4o.
Outcome:	The proposed models lack real-world referential understanding and are inconsistent in interpreting indexical gestures.

Copied to clipboard

Songtao Jiang, Chenyi Zhou, Yan Zhang, Yeying Jin, Zuozhu Liu

Can Community Notes Replace Professional Fact-Checkers? (2025.acl-short)

Challenge:	Current approaches generate visual markers for all questions, generating excessive visual markers.
Approach:	They propose a plug-and-play approach that adapts to the complexity of questions . they propose combining fast intuitive judgments with deliberate analytical reasoning .
Outcome:	The proposed approach improves performance on four benchmarks on ScienceQA, TextQA, VizWiz, and MME.

Copied to clipboard

Nadav Borenstein, Greta Warren, Desmond Elliott, Isabelle Augenstein

Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation Model (2025.acl-short)

Challenge:	Fact-checkers are crucial in combating misinformation on social media . however, community moderation is often employed in parallel due to the scale of misleading content shared online.
Approach:	They use language models to annotate Twitter/X community notes with attributes such as topic, cited sources, and whether they refute misinformation claims.
Outcome:	The results show that community notes cite fact-checking sources up to five times more than previously reported.

Copied to clipboard

Sihan Tan, Taro Miyazaki, Kazuhiro Nakadai

Multilinguality

Challenge:	Existing studies focus on translating a single SL into a spoken language (one-to-one SLT) however, multilingual SLT remains unexplored due to language conflicts and alignment difficulties across SLs and spoken languages.
Approach:	They propose a multilingual gloss-free model that can be used to translate a single SL into a spoken language and generate a token-level SL identification and spoken text.
Outcome:	The proposed model supports 10 SLs and handles one-to-one, many-to-1, and many- to-many SLT tasks.

Advancing Sequential Numerical Prediction in Autoregressive Models (2025.acl-short)

Copied to clipboard

Xiang Fei, Jinghui Lu, Qi Sun, Hao Feng, Yanjie Wang, Wei Shi, An-Lan Wang, Jingqun Tang, Can Huang

Challenge:	Autoregressive models are the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences.
Approach:	They propose a novel approach to entropy loss by extending the Earth Mover’s Distance to preserve ordinal relationships between numerical values and sequence-level to penalize the overall discrepancy between predicted and actual sequences.
Outcome:	Extensive experiments show that NTIL improves numerical prediction and integrates effectively with LLMs/MLLMs.

FEAT: A Preference Feedback Dataset through a Cost-Effective Auto-Generation and Labeling Framework for English AI Tutoring (2025.acl-short)

Copied to clipboard

Hyein Seo, Taewook Hwang, Yohan Lee, Sangkeun Jung

Challenge:	Existing algorithms for teacher feedback generation are time-consuming and costly to generate manually.
Approach:	They propose a framework for generating teacher feedback using LLMs and humans . they construct three datasets that are time-consuming and costly to generate manually . results show that incorporating a small portion of DM leads to superior performance .
Outcome:	The proposed framework performs better on three datasets compared to human-generated feedback and LLM-generated datasets.

ChronoSense: Exploring Temporal Understanding in Large Language Models with Time Intervals of Events (2025.acl-short)

Copied to clipboard

Duygu Sezen Islakoglu, Jan-Christoph Kalo

Human Alignment: How Much Do We Adapt to LLMs? (2025.acl-short)

Challenge:	Large Language Models (LLMs) still face significant challenges in reasoning and arithmetic.
Approach:	They propose a new benchmark to evaluate LLMs' temporal understanding that includes 16 tasks identifying the Allen relation between two temporal events and temporal arithmetic.
Outcome:	The proposed model handles Allen relations, even symmetrical ones, quite differently.

Copied to clipboard

Cazalets Tanguy, Ruben Janssens, Tony Belpaeme, Joni Dambre

Dynamic Order Template Prediction for Generative Aspect-Based Sentiment Analysis (2025.acl-short)

Challenge:	Large Language Models (LLMs) are becoming a common part of our lives, yet few studies have examined how they influence our behavior.
Approach:	They propose a cooperative language game in which players aim to converge on a word and play a game in a group.
Outcome:	The proposed game shows that humans notice and adapt to differences regardless of whether they are aware they are interacting with an LLM.

Copied to clipboard

Yonghyun Jun, Hwanhee Lee

Sentiment Analysis

Challenge:	Aspect-based sentiment analysis (ABSA) assesses sentiments towards aspects within texts, resulting in detailed sentiment tuples.
Approach:	They propose a dynamic order template method that dynamically creates an order template that contains only the necessary views for each instance.
Outcome:	The proposed method improves F1 scores on ASQP and ACOS datasets while significantly reducing inference time.

That doesn’t sound right: Evaluating speech transcription quality in field linguistics corpora (2025.acl-short)

Copied to clipboard

Eric Le Ferrand, Bo Jiang, Joshua Hartshorne, Emily Prud’hommeaux

Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering (2025.acl-short)

Challenge:	Automated speech recognition (ASR) is a popular tool for documenting languages, but field linguists do not have the data to train robust models.
Approach:	They propose to use fieldwork data to identify speech transcriptions that may be unsuitable for training ASR models.
Outcome:	The proposed measures can be used to identify transcriptions with characteristics common in field data but could be detrimental to ASR training.

Copied to clipboard

William Jurayj, Jeffrey Cheng, Benjamin Van Durme

Natural Language Interfaces

Challenge:	Existing evaluations of test-time scaling assume that a reasoning system should always give an answer to any question provided.
Approach:	They propose to increase compute budget at inference time to increase confidence in correct responses by considering settings with non-zero levels of response risk.
Outcome:	The proposed model can answer more questions correctly and have higher confidence in correct responses.

Acoustic Individual Identification of White-Faced Capuchin Monkeys Using Joint Multi-Species Embeddings (2025.acl-short)

Copied to clipboard

Álvaro Vega-Hidalgo, Artem Abzaliev, Thore Bergman, Rada Mihalcea

Representation Learning

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.

SELF-PERCEPT: Introspection Improves Large Language Models’ Detection of Multi-Person Mental Manipulation in Conversations (2025.acl-short)

Copied to clipboard

Danush Khanna, Pratinav Seth, Sidhaarth Sredharan Murali, Aditya Kumar Guru, Siddharth Shukla, Tanuj Tyagi, Sandeep Chaurasia, Kripabandhu Ghosh

A Variational Approach for Mitigating Entity Bias in Relation Extraction (2025.acl-short)

Challenge:	Mental manipulation is subtle yet pervasive form of abuse in interpersonal communication, making its detection critical for safeguarding potential victims.
Approach:	They propose a dataset of 220 multi-turn, multi-person dialogues balanced between manipulative and non-manipulative interactions drawn from reality shows that mimic real-life scenarios.
Outcome:	The proposed framework shows that it can detect multi-person, multi-turn mental manipulation in multi-people conversations.

Copied to clipboard

Samuel Mensah, Elena Kochkina, Jabez Magomere, Joy Prakash Sain, Simerjot Kaur, Charese Smiley

Information Extraction & Text Mining

Challenge:	Relation Extraction (RE) models often rely excessively on entities, resulting in poor generalization.
Approach:	They propose a Variational Information Bottleneck (VIB) framework to reduce entity bias in Relation Extraction (RE) . their method extracts relational information from unstructured data to improve generalization .
Outcome:	The proposed method achieves state-of-the-art on general and financial domain RE datasets, excelling in in-domain settings and out-of domain.

GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge Subtraction (2025.acl-short)

Copied to clipboard

Mohammadtaha Bagherifard, Sahar Rajabi, Ali Edalat, Yadollah Yaghoobzadeh

Multilinguality

Challenge:	Large language models (LLMs) struggle with zero-shot generalization due to entanglement of general knowledge and task-specific adaptations.
Approach:	They propose a modular framework that disentangles general knowledge and adaptations by constructing a library of task-specific LoRA modules alongside a general-domain LoRA.
Outcome:	The proposed framework disentangles general knowledge and task-specific adaptations . it generates residual modules that focus more exclusively on task-relevant information .

The Role of Abstract Representations and Observed Preferences in the Ordering of Binomials in Large Language Models (2025.acl-short)

Copied to clipboard

Zachary Nicholas Houghton, Kenji Sagae, Emily Morgan

Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs (2025.acl-short)

Challenge:	Using binomial ordering preferences, large language models learn abstract representations versus more superficial aspects of their training corpora.
Approach:	They examine binomial ordering preferences involving two conjoined nouns in English and examine whether large language models rely on observed binomialisms or on abstract ordering preferences.
Outcome:	The proposed model learning is based on the observed binomial ordering preferences in English, and not on human linguis-tic input.

Copied to clipboard

Payal Mohapatra, Akash Pandey, Xiaoyuan Zhang, Qi Zhu

Decoder-Only LLMs can be Masked Auto-Encoders (2025.acl-short)

Challenge:	Unvoiced electromyography (EMG) is an effective communication tool for individuals unable to produce vocal speech.
Approach:	They propose an EMG adaptor module that maps EMG features to an LLM's input space and achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task.
Outcome:	The proposed module achieves an average word error rate of 0.49 on a closed-vocabulary unvoiced EMG-to-text task.

Copied to clipboard

Dan Qiao, Yuan Gao, Zheming Yang, Di Yang, Ziheng Wu, Pengcheng Lu, Minghui Qiu, Juntao Li, Min Zhang

Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding (2025.acl-short)

Challenge:	Modern NLP workflows require different models for generation and embedding tasks.
Approach:	They propose a method that transforms an LLM into a Uni-Directional Masked Auto-Encoder.
Outcome:	The proposed method achieves state-of-the-art under unsupervised conditions with merely 100 training steps.

Copied to clipboard

Zikai Xiao, Ziyang Wang, Wen Ma, Yan Zhang, Wei Shen, WangYan WangYan, Luqi Gong, Zuozhu Liu

Challenge:	Current solutions incur prohibitive training costs, leaving statistical behaviors and cost-effective approaches underexplored.
Approach:	They propose a positional contrast decoding technique that contrasts long-aware attention with designed local-awn attention.
Outcome:	The proposed model achieves state-of-the-art performance on long-context benchmarks.

Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs (2025.acl-short)

Copied to clipboard

Xuan Zhang, Cunxiao Du, Sicheng Yu, Jiawei Wu, Fengzhuo Zhang, Wei Gao, Qian Liu

Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results (2025.acl-short)

Challenge:	Recent advances in Video Large Language Models (Video-LLMs) have achieved exceptional performance on tasks like video question answering and captioning.
Approach:	They propose a decoding strategy that leverages sparse top-K attention and dense full attention to accelerate Video-LLMs without loss.
Outcome:	The proposed approach achieves a 1.94 walltime speedup in video processing.

Copied to clipboard

Andrea Santilli, Adam Golinski, Michael Kirchhof, Federico Danieli, Arno Blaas, Miao Xiong, Luca Zappella, Sinead Williamson

Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation (2025.acl-short)

Challenge:	Language Models (LMs) produce factually incorrect outputs, or "hallucinations" Xiao and Wang et al., 2023) rely on AUROC to assess how well UQ methods distinguish correct from incorrect output.
Approach:	They propose to use length biases in correctness functions to skew UQ evaluations . they propose to employ LM-as-a-judge methods as the least length-biased .
Outcome:	The proposed method is least length-biased, offering a promising path for a fairer evaluation.

Copied to clipboard

Verna Dankers, Vikas Raunak

CoRet: Improved Retriever for Code Editing (2025.acl-short)

Challenge:	Memorization of noisy training data creates unexpected failure modes in neural machine translation models, thus presenting a reliability risk when deploying them in the real world.
Approach:	They propose a modification to sequence-level knowledge distillation (SeqKD) that intervenes in SeqKd to reduce memorization and hallucinations.
Outcome:	The proposed modification reduces memorization and hallucinations in the student model .

Copied to clipboard

Fabio James Fehr, Prabhu Teja S, Luca Franceschi, Giovanni Zappella

Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of Progress (2025.acl-short)

Challenge:	Existing encoder models perform poorly in repository-level retrieval for code-editing tasks.
Approach:	They propose a loss function for code retrieval that integrates code semantics, repository structure, and call-graph dependencies.
Outcome:	The proposed model significantly improves retrieval recall by at least 15 percentage points over existing models on SWE-bench and Long Code Arena’s bug localisation datasets.

Copied to clipboard

Lorenzo Proietti, Stefano Perrella, Roberto Navigli

Machine Translation

Challenge:	In machine translation evaluation, metric performance is assessed based on agreement with human judgments.
Approach:	They incorporate human baselines into the MT meta-evaluation to gain a clearer understanding of metric performance and establish an upper bound.
Outcome:	The results suggest human parity, but there are several reasons to caution .

Diffusion Directed Acyclic Transformer for Non-Autoregressive Machine Translation (2025.acl-short)

Copied to clipboard

Quan Nguyen-Tri, Cong Dao Tran, Hoang Thanh-Tung

Efficient Knowledge Editing via Minimal Precomputation (2025.acl-short)

Challenge:	Non-autoregressive transformers (NATs) often encounter performance challenges due to the multi-modality problem.
Approach:	They propose a direct-acyclic transformer (DAT) that captures multiple translation modalities to paths in a Directed Acyclic Graph (DAG) this allows the model to integrate latent variables into the model, which is crucial for DAT to achieve state-of-the-art performance.
Outcome:	The proposed model captures multiple translation modalities to paths in a Directed Acyclic Graph (DAG) but the collaboration with the latent variable introduced through the Glancing training is crucial for the model to attain state-of-the-art performance.

Copied to clipboard

Akshat Gupta, Maochuan Lu, Thomas Hartvigsen, Gopala Anumanchipalli

Green & Sustainable NLP

Challenge:	Knowledge editing methods like MEMIT require a one-time but significant computational cost.
Approach:	They propose to pre-compute 44 million hidden vectors per edited layer . authors show that this precomputation step is unnecessary .
Outcome:	The proposed methods can be performed by pre-computing a small portion of 44 million hidden vectors.

Meaning Variation and Data Quality in the Corpus of Founding Era American English (2025.acl-short)

Copied to clipboard

Dallas Card

MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location Awareness (2025.acl-short)

Challenge:	Legal scholars are increasingly using corpus based methods for assessing historical meaning . main corpus used in legal arguments is the Corpus of Founding Era American English .
Approach:	They demonstrate how NLP can be used to infer meaning change and variation using masked language models.
Outcome:	The proposed method can be used to infer meaning change and variation using advanced methods.

Copied to clipboard

Ye Wang, Xinrun Xu, Zhiming Ding

LLMs syntactically adapt their language use to their conversational partner (2025.acl-short)

Challenge:	Existing methods require pre-segmented article chunks, limiting reference flexibility like human memory.
Approach:	They propose a framework that leverages parameterized knowledge stored during the pre-training phase of large language models to recall reference passages from any starting position independently.
Outcome:	The proposed framework can recall reference passages from any starting position independently.

Copied to clipboard

Florian Kandra, Vera Demberg, Alexander Koller

Natural Language Interfaces

Challenge:	Adapting to the language of a communication partner is associated with increased success in goal-oriented conversations.
Approach:	They construct a corpus of conversations between large language models (LLMs) and measure their syntactic adaptation.
Outcome:	The proposed model can adapt to the language of the conversational partner in at least a rudimentary way.

TigerLLM - A Family of Bangla Large Language Models (2025.acl-short)

Copied to clipboard

Nishat Raihan, Marcos Zampieri

From Citations to Criticality: Predicting Legal Decision Influence in the Multilingual Swiss Jurisprudence (2025.acl-short)

Challenge:	linguistic disparity is particularly evident for Bangla, the 5th most spoken language . open-source Bangla LLMs have limited reproducibility and performance gaps .
Approach:	They propose a family of Bangla LLMs that outperform open-source alternatives and benchmarks and establish a new benchmark for future Bangla language modeling.
Outcome:	The proposed models outperform existing models and outperformed proprietary models across six benchmarks.

Copied to clipboard

Ronja Stern, Ken Kawamura, Matthias Stürmer, Ilias Chalkidis, Joel Niklaus

Revisiting LLMs as Zero-Shot Time Series Forecasters: Small Noise Can Break Large Models (2025.acl-short)

Challenge:	Existing approaches to evaluating the importance of legal cases are manual and resource-intensive.
Approach:	They propose a dataset that uses two-tier labels to evaluate case criticality . they use the LD-Label to identify cases published as Leading Decisions and the Citation-L Label to rank cases by their citation frequency and recency.
Outcome:	The Criticality Prediction dataset outperforms existing approaches to evaluate case criticality . the proposed model outperformed the existing models in a zero-shot setting .

Copied to clipboard

Junwoo Park, Hyuck Lee, Dohyun Lee, Daehoon Gwak, Jaegul Choo

Transferring Textual Preferences to Vision-Language Understanding through Model Merging (2025.acl-short)

Challenge:	Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training, fueling interest in their potential for time series forecasting.
Approach:	They evaluate the effectiveness of LLMs as zero-shot forecasters compared to state-of-the-art domain-specific models by encoding sequences directly within prompts.
Outcome:	The proposed models perform well across multiple domains while reducing the need for domain-specific training.

Copied to clipboard

Chen-An Li, Tzu-Han Lin, Yun-Nung Chen, Hung-yi Lee

ProgCo: Program Helps Self-Correction of Large Language Models (2025.acl-short)

Challenge:	Large vision-language models (LVLMs) perform outstandingly across multimodal tasks, but training them with preference data is computationally expensive.
Approach:	They propose to merge text-based reward models with LVLMs to create visionlanguage reward models (VLRMs) this approach offers an efficient method for incorporating textual preferences into LVRMs.
Outcome:	The proposed model improves over LVLMs’ scoring and text-based RMs, and offers an efficient method for incorporating textual preferences into LVRMs.

Copied to clipboard

Xiaoshuai Song, Yanan Wu, Weixun Wang, Jiaheng Liu, Wenbo Su, Bo Zheng

Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs (2025.acl-short)

Challenge:	Existing LLMs fail to self-correct and generate correct feedback, leading to misleading refinement and failure of self-refinement.
Approach:	They propose a program-driven self-correction approach that uses program-based verification to self-refine initial responses without external feedback.
Outcome:	The proposed model achieves self-correction and can be further enhanced when combined with real program tools.

Copied to clipboard

Ananth Muppidi, Abhilash Nandy, Sambaran Bandyopadhyay

Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese Grammar (2025.acl-short)

Challenge:	Large language models require fine-tuning, which is computationally expensive and challenging.
Approach:	They propose a method that generates soft prompts based on input tokens and attends different tokens with varying importance.
Outcome:	The proposed method is simple and efficient, keeping the number of trainable parameters small.

Copied to clipboard

Andrew Gambardella, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

Unique Hard Attention: A Tale of Two Sides (2025.acl-short)

Challenge:	Standard benchmarks for language models fail to capture nuanced capabilities such as the ability of language models to recognize and obey rare grammar points.
Approach:	They find that Weblab's uniformly bad tokenization is a possible root cause for its good performance .
Outcome:	The proposed model consistently assigns higher perplexity to ungrammatical psych predicate sentences than grammaticals.

Copied to clipboard

Selim Jerad, Anej Svete, Jiaoda Li, Ryan Cotterell

Enhancing Input-Label Mapping in In-Context Learning with Contrastive Decoding (2025.acl-short)

Challenge:	Understanding the expressive power of transformers has attracted attention . many studies analyze unique hard attention transformers, where attention selects a single position that maximizes the attention scores.
Approach:	They propose to use unique hard attention to select a single position that maximizes attention scores . they show that models with leftmost-hard attention are equivalent to soft attention .
Outcome:	The proposed models with leftmost-hard attention are equivalent to soft attention, suggesting they may better approximate real-world transformers than right-attention models.

Copied to clipboard

Keqin Peng, Liang Ding, Yuanxin Ouyang, Meng Fang, Yancheng Yuan, Dacheng Tao

Different Speech Translation Models Encode and Translate Speaker Gender Differently (2025.acl-short)

Challenge:	Prior research has found that large language models overlook input-label mapping information in ICL, relying more on their pre-trained knowledge.
Approach:	They propose a novel method that contrasts input-label mappings between positive and negative in-context examples to improve model performance.
Outcome:	The proposed method improves performance on 7 natural language understanding tasks without additional training.

Copied to clipboard

Dennis Fucci, Marco Gaido, Matteo Negri, Luisa Bentivogli, Andre Martins, Giuseppe Attanasio

Multilinguality

Challenge:	Recent studies on interpreting the hidden states of speech models have shown their ability to capture speaker-specific features, including gender.
Approach:	They propose to use probing methods to assess gender encoding across ST models.
Outcome:	The proposed models capture speaker-specific features, including gender, while older models do not . low gender encoding capabilities result in systems’ tendency toward a masculine default, a translation bias that is more pronounced in newer architectures.

Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints (2025.acl-short)

Copied to clipboard

Kaikai An, Shuzheng Si, Helan Hu, Haozhe Zhao, Yuchi Wang, Qingyan Guo, Baobao Chang

Quantifying Misattribution Unfairness in Authorship Attribution (2025.acl-short)

Challenge:	Semantic Parsing improves performance of smaller models, but it is unclear whether it extends similarly to large language models.
Approach:	They propose a prompting approach that embeds semantic hints within the prompt to improve LLM performance.
Outcome:	The proposed approach improves LLMs’ performance across various tasks, highlighting the potential of integrating semantic information to improve LLM capabilities.

Copied to clipboard

Pegah Alipoormolabashi, Ajay Patel, Niranjan Balasubramanian

Zero-Shot Text-to-Speech for Vietnamese (2025.acl-short)

Challenge:	Authorship misattribution can have profound consequences in real life . authors are considered as potential authors in forensic settings .
Approach:	They propose a measure to quantify the unfairness of authorship attribution systems . authors find that authors are more likely to be misattributed than others .
Outcome:	The proposed model shows that some authors are more likely to be misattributed than others.

Copied to clipboard

Thi Vu, Linh The Nguyen, Dat Quoc Nguyen

Can LLMs Generate High-Quality Test Cases for Algorithm Problems? TestCase-Eval: A Systematic Evaluation of Fault Coverage and Exposure (2025.acl-short)

Challenge:	Text-to-speech (TTS) synthesis has seen significant advancements in recent years.
Approach:	They propose to use PhoAudiobook to curated 941 hours of high-quality audio for Vietnamese text-to-speech models.
Outcome:	The proposed model improves on VALL-E, VoiceCraft, and XTTS-V2 models, highlighting their robustness in handling diverse linguistic contexts.

Copied to clipboard

Zheyuan Yang, Zexi Kuang, Xue Xia, Yilun Zhao

Challenge:	TestCase-Eval focuses on Fault Coverage and Fault Exposure tasks . authors provide insights into their strengths and limitations in generating effective test cases . correctness and robustness of algorithmic solutions hinge on quality of test suites .
Approach:	They introduce TestCase-Eval, a benchmark for systematic evaluation of LLMs in test-case generation.
Outcome:	The new benchmark measures the performance of LLMs in test-case generation.

Are Optimal Algorithms Still Optimal? Rethinking Sorting in LLM-Based Pairwise Ranking with Batching and Caching (2025.acl-short)

Copied to clipboard

Juan Wisznia, Cecilia Bolaños, Juan Tollo, Giovanni Franco Gabriel Marraffini, Agustín Andrés Gianolini, Noe Fabian Hsueh, Luciano Del Corro

TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination Evaluation (2025.acl-short)

Challenge:	a new framework for analyzing sorting algorithms in pairwise ranking prompting (PRP) is developed to re-center the cost model around LLM inferences rather than traditional pairwise comparisons.
Approach:	They propose a framework for analyzing sorting algorithms in pairwise ranking prompting (PRP) they propose to re-center the cost model around LLM inferences rather than traditional pairwise comparisons.
Outcome:	The proposed framework encourages strategies such as batching and caching to mitigate inference costs.

Copied to clipboard

Jialin Ouyang

WinSpot: GUI Grounding Benchmark with Multimodal Large Language Models (2025.acl-short)

Challenge:	Large language models (LLMs) can achieve near-human performance on benchmarks like GSM8K, yet their true reasoning ability remains disputed.
Approach:	They propose a synthetic dataset that generates infinite unanswerable math word problems and their answerable counterparts by representing each question as a tree and removing selected necessary conditions.
Outcome:	Experiments show TreeCut induces hallucinations in large language models, including GPT-4o and o3-mini, with rates of 64% and 44% in worst-case scenarios.

Copied to clipboard

Zheng Hui, Yinheng Li, Dan Zhao, Colby Banbury, Tianyi Chen, Kazuhito Koishida

Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models (2025.acl-short)

Challenge:	Existing GUI grounding data focuses on web-based elements, leaving a gap in real-world GUI interaction data for non-web applications.
Approach:	They propose a framework that leverages Large Language Models to generate large-scale GUI grounding data.
Outcome:	The framework validates and refines 5,000 GUI coordinate-instruction pairs and provides high-quality data for training and evaluating visual GUI agents.

Copied to clipboard

Fardin Ahsan Sakib, Ziwei Zhu, Karen Trister Grace, Meliha Yetisgen, Ozlem Uzuner

Enhancing NER by Harnessing Multiple Datasets with Conditional Variational Autoencoders (2025.acl-short)

Challenge:	Large language models (LLMs) rely on superficial cues leading to spurious predictions . recent work has highlighted how LLMs exploit spurious patterns rather than learning causal, generalizable features.
Approach:	They use a social history annotation corpus dataset to examine drug status extraction . they evaluate prompt engineering and chain-of-thought reasoning to reduce false positives .
Outcome:	The proposed model can predict drug use when alcohol or smoking is not present, while uncovering gender disparities in model performance.

Copied to clipboard

Taku Oi, Makoto Miwa

CHEER-Ekman: Fine-grained Embodied Emotion Classification (2025.acl-short)

Challenge:	Named Entity Recognition (NER) is a fundamental NLP task . supervised learning or full fine-tuning remains essential for high performance NER models.
Approach:	They propose to integrate CVAE into a span-based Named Entity Recognition model.
Outcome:	The proposed method achieves better performance on the BioRED dataset.

Copied to clipboard

Phan Anh Duong, Cat Luong, Divyesh Bommana, Tianyu Jiang

Text Classification

Challenge:	Emotions manifest through physical experiences and bodily reactions, yet identifying such embodied emotions in text remains understudied.
Approach:	They propose to extend existing binary embodied emotion dataset with Ekman’s six basic emotion categories.
Outcome:	The proposed dataset outperforms existing methods with large language models.

ScanEZ: Integrating Cognitive Models with Self-Supervised Learning for Spatiotemporal Scanpath Prediction (2025.acl-short)

Copied to clipboard

Ekta Sood, Prajit Dhar, Enrica Troiano, Rosy Southwell, Sidney K. DMello

Improving Fairness of Large Language Models in Multi-document Summarization (2025.acl-short)

Challenge:	ScanEZ framework provides a framework for predicting scanpaths during reading . masked modeling of eye movements and cognitive model simulations are used to kick-start training.
Approach:	They propose a framework for self-supervised learning that models scanpaths using synthetic data and a 3-D gaze objective inspired bymasked language modeling.
Outcome:	The proposed framework achieves state-of-the-art results on established datasets and is portable across different conditions.

Copied to clipboard

Haoyuan Li, Rui Zhang, Snigdha Chaturvedi

Ethical NLP

Challenge:	Recent studies focus on summary-level fairness, while corpus-level focuses on corpus of summaries.
Approach:	They propose a preference tuning method that focuses on both summary-level and corpus-level fairness in MDS.
Outcome:	The proposed method outperforms baselines while maintaining critical qualities of summaries.

Should I Believe in What Medical AI Says? A Chinese Benchmark for Medication Based on Knowledge and Reasoning (2025.acl-short)

Copied to clipboard

Yue Wu, Yangmin Huang, Qianyun Du, Lixian Lai, Zhiyang He, Jiaxue Hu, Xiaodong Tao

Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human? (2025.acl-short)

Challenge:	Large language models (LLMs) generate hallucinations when handling unfamiliar information.
Approach:	They propose a Chinese benchmark to evaluate large language models' knowledge and reasoning capabilities in medication tasks.
Outcome:	The proposed benchmark evaluates models in indication, dosage and administration, contraindicated population, mechanisms of action, drug recommendation, and drug interaction across six datasets.

Copied to clipboard

Takumi Goto, Yusuke Sakai, Taro Watanabe

Syntactic Text Processing

Challenge:	Existing automatic evaluation metrics are based on procedures that diverge from human evaluation.
Approach:	They propose to aggregate automatic evaluation metrics to bridge this gap . they propose to use edit-based metrics, -gram based metrics and sentence-level metrics to find the best ranking system.
Outcome:	The proposed method outperforms existing metrics on the SEEDA benchmark and improves edit-based metrics, -gram based metrics and sentence-level metrics.

Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form Generation (2025.acl-short)

Copied to clipboard

Chengwei Qin, Wenxuan Zhou, Karthik Abinav Sankararaman, Nanshu Wang, Tengyu Xu, Alexander Radovic, Eryk Helenowski, Arya Talebzadeh, Aditya Tayade, Sinong Wang, Shafiq Joty, Han Fang, Hao Ma

WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challenging (2025.acl-short)

Challenge:	Existing methods for detecting hallucination in long-form tasks focus on limited domains or rely heavily on external fact-checking tools, which may not always be available.
Approach:	They propose a new paradigm that augments fine-tuning with an auxiliary task for the model to jointly learn with the main task of hallucination detection.
Outcome:	The proposed method outperforms existing methods for detecting hallucination in open-domain long-form generation and is more accurate than random guessing.

Copied to clipboard

Ahmed Elhady, Eneko Agirre, Mikel Artetxe

Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning (2025.acl-short)

Challenge:	Multiple choice question (MCQ) benchmarks are widely used to evaluate Large Language Models (LLMs).
Approach:	They propose a method to increase the complexity of existing multiple-choice benchmarks by randomly replacing a choice with “None of the above”.
Outcome:	The proposed method can be applied to 6 popular benchmarks and evaluate 18 open-weight LLMs.

Copied to clipboard

Nathaniel Krasner, Nicholas Lanuzo, Antonios Anastasopoulos

LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token Filtering (2025.acl-short)

Challenge:	Multilingual alignment of sentence representations has mostly required bitexts to bridge the gap between languages.
Approach:	They propose to use image captions to implicitly align text representations between languages to make them usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval.
Outcome:	The proposed approach is usable for cross-lingual Natural Language Understanding (NLU) and bitext retrieval.

Copied to clipboard

Zhifan Ye, Zheng Wang, Kejing Xia, Jihoon Hong, Leshu Li, Lexington Whalen, Cheng Wan, Yonggan Fu, Yingyan Celine Lin, Souvik Kundu

Challenge:	Recent work attributes performance degradation to an exponential decay in hidden-state memory.
Approach:	They propose a token filtering strategy that is training-free and attention-guided . they propose 'LAMB' to preserve critical tokens during inference .
Outcome:	The proposed token filtering improves long-context performance by 30.35% over state-of-the-art methods on benchmarks.

Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models (2025.acl-short)

Copied to clipboard

Jongho Kim, Seung-won Hwang