Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)

Beyond the Gold Standard in Analytic Automated Essay Scoring (2025.acl-srw)

Challenge:	Accents play a pivotal role in shaping human communication, a new study finds . existing ASR systems often perform inadequately, even mispronouncing African names .
Approach:	They propose a method that uses epistemic uncertainty to automate annotation to reduce costs and human labor.
Outcome:	The proposed method reduces costs and human labor by reducing data annotation and epistemic uncertainty.

Copied to clipboard

Gabrielle Gaudeau

Confidence and Stability of Global and Pairwise Scores in NLP Evaluation (2025.acl-srw)

Challenge:	Automated Essay Scoring (AES) is a new approach to assessing writing practice . traditional holistic scoring methods are not reliable and lack formative feedback in the classroom.
Approach:	They propose to combine analytic and holistic AES to create a system that learns from individual raters instead of gold standard labels.
Outcome:	The proposed system learns from individual raters instead of gold standard labels.

Copied to clipboard

Georgii Levtsov, Dmitry Ustalov

Challenge:	Modern natural language processing benchmarks are often represented as pairwise comparison leaderboards, such as LMSYS Arena.
Approach:	They investigate the strengths and weaknesses of global scores and pairwise comparisons to aid decision-making in selecting appropriate model evaluation strategies.
Outcome:	The proposed method underestimates strong models with rare errors or low confidence, while relying on global scores can be more effective.

Zero-shot prompt-based classification: topic labeling in times of foundation models in German Tweets (2025.acl-srw)

Copied to clipboard

Simon Münker, Kai Kugler, Achim Rettinger

Rethinking Full Finetuning from Pretraining Checkpoints in Active Learning for African Languages (2025.acl-srw)

Challenge:	Recent advances in NLP have enabled the use of text-to-text annotation without providing training samples.
Approach:	They propose a text-to-text interface for automatic annotation using written guidelines without providing training samples.
Outcome:	The proposed approach is comparable with the fine-tuned BERT but without any training data.

Copied to clipboard

Bonaventure F. P. Dossou, Ines Arous, Jackie CK Cheung

HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization (2025.acl-srw)

Challenge:	Existing approaches to improve model performance are finetuning on all acquired data after each round, which is computationally expensive in multilingual and low-resource settings.
Approach:	They evaluate continual finetuning (CF) against full finetuned (FA) across 28 African languages using MasakhaNEWS and SIB-200.
Outcome:	The proposed approach outperforms full finetuning (FA) in 28 African languages, achieving up to 35% reductions in GPU memory, FLOPs, and training time.

Copied to clipboard

Enes Özeren, Yihong Liu, Hinrich Schuetze

SEPSIS: I Can Catch Your Lies – A New Paradigm for Deception Detection (2025.acl-srw)

Challenge:	Pre-trained language models exhibit suboptimal performance on mid- and low-resource languages due to limited exposure to these languages during pre-training.
Approach:	They propose a similarity-based subword embedding initialization heuristic that introduces new tokens specific to target languages, initializes their embedders, and applies continual pre-training on target-language data.
Outcome:	The proposed method outperforms random initialization baseline and matches or exceeds OFA in both continual pre-training convergence and downstream task performance.

Copied to clipboard

Anku Rani, Dwip Dalal, Shreya Gautam, Pankaj Gupta, Vinija Jain, Aman Chadha, Amit Sheth, Amitava Das

Challenge:	a new framework categorizes deception into three forms: lies of omission, lies of commission, and lies of influence . a novel framework for deception detection leveraging NLP techniques is proposed .
Approach:	They propose a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence.
Outcome:	The proposed framework achieves an impressive F1 score of 0.87 across all layers . it can be used to investigate lies of omission, lies of commission and lies of influence .

Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems? (2025.acl-srw)

Copied to clipboard

Md Tanzib Hosain, Md Kishor Morol

Do Androids Question Electric Sheep? A Multi-Agent Cognitive Simulation of Philosophical Reflection on Hybrid Table Reasoning (2025.acl-srw)

Challenge:	Among the hardest tasks for humans are those found in competitive programming . language models (LMs) have not received enough attention as a domain to assess .
Approach:	They develop and evaluate a variety of LM inference techniques for competitive programming with these resources.
Outcome:	The proposed LM inference technique can solve 17 out of 18 problems that were previously unsolvable by any model or technique with just a few specific instructions.

Copied to clipboard

Yiran Rex Ma

Grouped Sequency-arranged Rotation: Optimizing Rotation Transformation for Quantization for Free (2025.acl-srw)

Challenge:	Existing studies have observed that LLMs are wise enough to be thinkers of philosophical reflection.
Approach:	They conduct an exploratory simulation to investigate whether LLMs are wise enough to be thinkers of philosophical reflection.
Outcome:	The proposed frameworks underperform simpler end-to-end approaches, but they tend to overthink . the results shed light on a fundamental challenge shared by both human and machine intelligence .

Copied to clipboard

Euntae Choi, Sumin Song, Woosang Lim, Sungjoo Yoo

A Reproduction Study: The Kernel PCA Interpretation of Self-Attention Fails Under Scrutiny (2025.acl-srw)

Challenge:	Existing rotation-based methods struggle at low bit-widths, such as 2-bit weight quantization.
Approach:	They propose a training-free approach to construct an improved rotation matrix . they leverage the Walsh-Hadamard transform with sequency ordering to reduce quantization error .
Outcome:	The proposed method demonstrates robust performance on reasoning tasks and high Perplexity (PPL) score on WikiText-2.

Copied to clipboard

Karahan Sarıtaş, Çağatay Yıldız

Transforming Brainwaves into Language: EEG Microstates Meet Text Embedding Models for Dementia Detection (2025.acl-srw)

Challenge:	Recent studies suggest that self-attention implements kernel principal component analysis (KPCA) Across 10 transformer architectures, we conclude that the KPCA interpretation of self- attention lacks empirical support.
Approach:	They revisit claims that self-attention implements kernel principal component analysis . they argue that self attention projects queries onto principal component axes of key matrix K .
Outcome:	The proposed kernel principal component analysis does not match the proposed kernel . the proposed method is not able to detect the eigenvalues of the gram matrix .

Copied to clipboard

Quoc-Toan Nguyen, Linh Le, Xuan-The Tran, Dorothy Bai, Nghia Duong-Trung, Thomas Do, Chin-teng Lin

Neuron-Level Language Tag Injection Improves Zero-Shot Translation Performance (2025.acl-srw)

Challenge:	Dementia is recognised as the seventh leading cause of mortality globally and plays a major role in increasing disability and dependence among older adults.
Approach:	They propose to represent electroencephalography microstates as symbolic, language-like sequences and use text embedding and time-series deep learning models for classification.
Outcome:	The proposed method achieves a high accuracy of 94.31% on 1001 EEG data from multiple countries and eliminates fixed configurations and costly/invasive modalities.

Copied to clipboard

Jay Orten, Ammon Shurtz, Nancy Fulda, Stephen D. Richardson

Voices of Dissent: A Multimodal Analysis of Protest Songs through Lyrics and Audio (2025.acl-srw)

Challenge:	Language tagging is a method that trains models on specific language directions . injection is based on a language token embedded in the input layer .
Approach:	They propose a method whereby source and target inputs are prefixed with a unique language token and inject it into the input of every linear layer.
Outcome:	The proposed method improves translation performance with up to 2+ BLEU score point gain for certain language directions in a multilingual dataset.

Copied to clipboard

Utsav Shekhar, Radhika Mamidi

Your Pretrained Model Tells the Difficulty Itself: A Self-Adaptive Curriculum Learning Paradigm for Natural Language Understanding (2025.acl-srw)

Challenge:	linguistic and acoustic features that distinguish protest songs from non-protest ones remain understudied.
Approach:	They propose to use NLP and audio analysis to identify linguistic and acoustic features that distinguish protest songs from non-protest ones.
Outcome:	The proposed analysis of protest and non-protest songs reveals linguistic and acoustic features that differentiate them from non- protest songs.

Copied to clipboard

Qi Feng, Yihong Liu, Hinrich Schuetze

CausalGraphBench: a Benchmark for Evaluating Language Models capabilities of Causal Graph discovery (2025.acl-srw)

Challenge:	Existing curriculum learning approaches rely on manually defined difficulty metrics which may not accurately reflect the model’s own perspective.
Approach:	They propose a self-adaptive curriculum learning paradigm that prioritizes fine-tuning examples based on difficulty scores predicted by pre-trained language models (PLMs) they evaluate four datasets covering binary and multi-class classification tasks.
Outcome:	The proposed model leads to faster convergence and improved performance compared to standard random sampling.

Copied to clipboard

Nikolay Babakov, Ehud Reiter, Alberto Bugarín-Diz

Reasoning for Translation: Comparative Analysis of Chain-of-Thought and Tree-of-Thought Prompting for LLM Translation (2025.acl-srw)

Challenge:	Recent advances in large language models (LLMs) have expanded their applications into domains not traditionally associated with natural language processing.
Approach:	They propose a benchmark to evaluate the ability of large language models to construct Causal Graphs (CGs) they examine various methods for CG discovery and their performance across different graph sizes and complexity levels.
Outcome:	The proposed benchmark comprises 35 CGs sourced from publicly available repositories and academic papers.

Copied to clipboard

Lam Nguyen, Yang Xu

Machine Translation

Challenge:	Large Language Models (LLMs) have been used for specialized tasks but their application to machine translation has received little attention.
Approach:	They evaluate reasoning-based prompting strategies across multiple language pairs and domains and measure their effect on translation quality.
Outcome:	The proposed prompting strategies outperform traditional prompting methods across language pairs and domains and achieve improvements of up to 6.4 BLs.

iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop (2025.acl-srw)

Copied to clipboard

Jiahui Li, Roman Klinger

Evaluating Structured Output Robustness of Small Language Models for Open Attribute-Value Extraction from Clinical Notes (2025.acl-srw)

Challenge:	Prompt engineering has made significant contributions to the era of large language models, yet its effectiveness depends on the skills of a prompt author.
Approach:	They propose a novel approach to prompt optimization that bridges manual prompt engineering and automatic prompt optimization by providing task-specific guidance.
Outcome:	The proposed approach bridges manual prompt engineering and automatic prompt optimization while offering users the flexibility to assess evolving prompts.

Copied to clipboard

Nikita Neveditsin, Pawan Lingras, Vijay Kumar Mago

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Datasets Dependency (2025.acl-srw)

Challenge:	Comparative analysis of structured outputs generated by small language models for open attribute-value extraction from clinical notes . structure of outputs improves with targeted prompting and larger models, but declines for longer documents and certain note types.
Approach:	They compare the parsability of structured outputs generated by small language models for open attribute-value extraction from clinical notes.
Outcome:	The proposed model performs well in open attribute-value extraction tasks, but fails to parse for longer documents and note types.

Copied to clipboard

Seonglae Cho, Harryn Oh, Donghyun Lee, Luis Rodrigues Vieira, Andrew Bermingham, Ziad El Sayed

Explainability & Interpretability in NLP

Challenge:	Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features.
Approach:	They propose a method that trains SAEs on the model’s own synthetic dataset and a model-specific model to capture model-internal features.
Outcome:	The proposed method outperforms SAEs trained on web-based datasets and exhibits lower Fake Feature Ratio in 5 out of 7 models.

Translating Movie Subtitles by Large Language Models using Movie-meta Information (2025.acl-srw)

Copied to clipboard

Ashmari Pramodya, Yusuke Sakai, Justin Vasselli, Hidetaka Kamigaito, Taro Watanabe

Pun2Pun: Benchmarking LLMs on Textual-Visual Chinese-English Pun Translation via Pragmatics Model and Linguistic Reasoning (2025.acl-srw)

Challenge:	Large language models (LLMs) have advanced natural language processing by understanding, generating, and manipulating texts.
Approach:	They propose to use movie subtitle prompts to improve translation accuracy by incorporating movie meta-information into the models.
Outcome:	The proposed prompts improve translation accuracy and reduce computational effort.

Copied to clipboard

Yiran Rex Ma, Shan Huang, Yuting Xu, Ziyu Zhou, Yuanxi Wei

Small Models, Big Impact: Efficient Corpus and Graph-Based Adaptation of Small Multilingual Language Models for Low-Resource Languages (2025.acl-srw)

Challenge:	Current approaches resort to suboptimal compromises and computational methods remain inadequate for translation.
Approach:	They propose a Constant-Variable Optimization (CVO) model for translation strategy and an Ovl metric for translation quality assessment that adapts to Chinese and English.
Outcome:	The proposed model improves performance on textual and visual puns while maintaining linguistic mechanisms and humorous effects.

Copied to clipboard

Daniil Gurgurov, Ivan Vykopal, Josef Van Genabith, Simon Ostermann

Exploring the Effect of Nominal Compound Structure in Scientific Texts on Reading Times of Experts and Novices (2025.acl-srw)

Challenge:	Low-resource languages (LRLs) face significant challenges in natural language processing due to limited data.
Approach:	They evaluate adapter-based methods for adapting mLMs to low-resource languages . they use unstructured text and structured knowledge from ConceptNet to evaluate adapters .
Outcome:	The proposed methods outperform large language models and LLaMA-3 and deepSeek-R1 models on low training data.

Copied to clipboard

Isabell Landwehr, Marie-Pauline Krielke, Stefania Degaetano-Ortlieb

Challenge:	Using a corpus of eye-tracking data of German native speakers, we find that some compound types are associated with longer reading times.
Approach:	They use a corpus containing eye-tracking data of german native speakers reading scientific texts.
Outcome:	The authors show that some compound types are associated with longer reading times and that experts may have an advantage while reading in-domain texts, but also while reading out-of-domain.

Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks (2025.acl-srw)

Copied to clipboard

Amir Saeidi, Shivanshu Verma, Md Nayem Uddin, Chitta Baral

Reasoning

Challenge:	Large Language Models (LLMs) excel in math reasoning problemsolving, text generation, summarization, creative writing, among other tasks.
Approach:	They evaluate Direct Preference Optimization and its variants for aligning Large Language Models with human preferences.
Outcome:	The proposed alignment methods achieve near-optimal performance even with smaller subsets of training data.

From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems (2025.acl-srw)

Copied to clipboard

Youngjoon Jang, Seongtae Hong, Junyoung Son, Sungjin Park, Chanjun Park, Heuiseok Lim

Information Extraction & Text Mining

Challenge:	Retrieval-augmented generation (RAG) is a key framework in natural language processing . however, the effectiveness of RAG is often hindered by coreferential complexity in retrieved documents .
Approach:	They investigate how entity coreference affects document retrieval and generative performance in RAG-based systems.
Outcome:	The proposed model improves QA performance and retrieval relevance and contextual understanding.

Quantifying the Influence of Irrelevant Contexts on Political Opinions Produced by LLMs (2025.acl-srw)

Copied to clipboard

Samuele D’Avenia, Valerio Basile

Challenge:	Recent studies have examined the generation of large language models (LLMs) on subjective topics such as political opinions and attitudinal questionnaires.
Approach:	They use a Political Compass Test questionnaire to quantify how irrelevant information can systematically bias model opinions in specific directions.
Outcome:	The results show that even seemingly unrelated contexts alter model responses in predictable ways.

Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset (2025.acl-srw)

Copied to clipboard

Seunguk Yu, Kyeonghyun Kim, JungMin Yun, YoungBin Kim

Challenge:	Despite advances in LLMs, there are still concerns about their effectiveness with low-resource agglutinative languages compared to English.
Approach:	They evaluated 11 LLMs to assess their understanding of Korean sentence endings . they found that explicitly considering linguistic features improved performance .
Outcome:	The evaluated LLMs were able to understand Korean sentences better than other languages.

Towards Multi-Perspective NLP Systems: A Thesis Proposal (2025.acl-srw)

Copied to clipboard

Benedetta Muscato

Enhancing Software Requirements Engineering with Language Models and Prompting Techniques: Insights from the Current Research and Future Directions (2025.acl-srw)

Challenge:	Existing approaches to resolving disagreements ignore individual opinions and can result in the marginalization of minority perspectives.
Approach:	They propose to preserve individual labels in human-annotated datasets for subjective tasks and propose solutions for developing Perspective-Aware by design systems.
Outcome:	The proposed framework will be used to develop more responsible and inclusive models.

Copied to clipboard

Moemen Ebrahim, Shawkat Guirguis, Christine Basta

Question Decomposition for Retrieval-Augmented Generation (2025.acl-srw)

Challenge:	Large Language Models (LLMs) offer transformative potential for Software Requirements Engineering (SRE), but they face challenges such as domain ignorance, hallucinations, and high computational costs.
Approach:	They propose a conceptual framework that integrates Small Language Models and Knowledge-Augmented LMs with LangChain to address these limitations systematically.
Outcome:	The proposed framework addresses six technical challenges and two research gaps through a systematic review of LLM applications in software requirements engineering.

Copied to clipboard

Paul J. L. Ammann, Jonas Golde, Alan Akbik

Information Retrieval

Challenge:	Retrieval-augmented generation (RAG) is effective for question answering tasks . multi-hop questions, such as "Which company among NVIDIA, Apple, and Google made the biggest profit in 2023?" challenge RAG because relevant facts are often distributed across multiple documents .
Approach:	They propose a pipeline that incorporates question decomposition to ground large language models in verifiable external sources.
Outcome:	The proposed approach improves retrieval and answer accuracy over standard RAG . multi-hop questions often require multiple documents to support the model .

Neural Machine Translation for Agglutinative Languages via Data Rejuvenation (2025.acl-srw)

Copied to clipboard

Chen Zhao, Yatu Ji, Ren Qing-Dao-Er-Ji, Nier Wu, Lei Shi, Fu Liu, Yepai Jia

StRuCom: A Novel Dataset of Structured Code Comments in Russian (2025.acl-srw)

Challenge:	Recent years, advances in Neural Machine Translation (NMT) heavily rely on large-scale parallel corpora.
Approach:	They propose to combine fine-grained inactive sample identification with target-side rejuvenation to improve translation quality from agglutinative languages.
Outcome:	The proposed framework improves on four low-resource agglutinative language tasks.

Copied to clipboard

Maria Dziuba, Valentin Malykh

A Semantic Uncertainty Sampling Strategy for Back-Translation in Low-Resources Neural Machine Translation (2025.acl-srw)

Challenge:	Existing machine learning models for code comment generation are poorly suited for Russian . existing datasets that contain simple comments and docstrings in English are not suitable for function-level documentation generation.
Approach:	They propose a dataset specifically designed for Russian code documentation.
Outcome:	The first large-scale dataset specifically designed for Russian code documentation is based on human-written comments from GitHub repositories with synthetically generated ones.

Copied to clipboard

Yepai Jia, Yatu Ji, Xiang Xue, Shilei@imufe.edu.cn Shilei@imufe.edu.cn, Qing-Dao-Er-Ji Ren, Nier Wu, Na Liu, Chen Zhao, Fu Liu

Spanish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and BERT Embeddings (2025.acl-srw)

Challenge:	Back-translation methods rely on large-scale parallel corpora to enhance performance, but ignore the semantic quality of monolingual data.
Approach:	They propose a method which prioritizes sentences with higher semantic uncertainty as training samples by computationally evaluating the complexity of unannotated monolingual data.
Outcome:	The proposed method improves translation accuracy and fluency by +1.7 on all three translation tasks.

Copied to clipboard

Laura Zeidler, Chris Jenkins, Filip Miletić, Sabine Schulte Im Walde

SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains (2025.acl-srw)

Challenge:	Existing models for automatic dialect classification use bag-of-words unigram features instead of linguistic knowledge.
Approach:	They propose to use dialect-specific unigram features to train machine learning models . they also use a transformer-based model to find potentially useful dialect-related features .
Outcome:	The proposed model outperforms existing models but sacrifices explainability and interpretability.

Copied to clipboard

Bijoy Ahmed Saiem, MD Sadik Hossain Shanto, Rakib Ahsan, Md Rafi Ur Rashid

A Dual-Layered Evaluation of Geopolitical and Cultural Bias in LLMs (2025.acl-srw)

Challenge:	SequentialBreak enables LLMs to bypass safety mechanisms by arranging malicious prompts in a single query.
Approach:	They propose a single-query jailbreak technique that arranges multiple benign prompts in sequence with a hidden malicious instruction among them to bypass safety mechanisms.
Outcome:	The proposed technique outperforms baselines on open-source and closed-source models.

Copied to clipboard

Sean Kim, Hyuhng Joon Kim

Challenge:	Large language models exhibit cultural and geopolitical biases when their outputs shape public opinion or reinforce dominant narratives.
Approach:	They define two types of bias in large language models: model bias and inference bias through a two-phase evaluation.
Outcome:	The proposed framework evaluates large language models on factual and disputable questions across four languages and question types.

MA-COIR: Leveraging Semantic Search Index and Generative Models for Ontology-Driven Biomedical Concept Recognition (2025.acl-srw)

Copied to clipboard

Shanshan Liu, Noriki Nishida, Rumana Ferdous Munne, Narumi Tokunaga, Yuki Yamagata, Kouji Kozaki, Yuji Matsumoto

LibVulnWatch: A Deep Assessment Agent System and Leaderboard for Uncovering Hidden Vulnerabilities in Open-Source AI Libraries (2025.acl-srw)

Challenge:	Existing concepts recognition methods that rely on explicit mention identification fail to capture complex concepts not explicitly stated in the text.
Approach:	They propose a framework that reformulates concept recognition as an indexing-recognition task.
Outcome:	The proposed framework reduces computational requirements and improves recognition efficiency in low-resource settings.

Copied to clipboard

Zekun Wu, Seonglae Cho, Umar Mohammed, Cristian Enrique Munoz Villalobos, Kleyton Da Costa, Xin Guan, Theo King, Ze Wang, Emre Kazim, Adriano Koshiyama

Challenge:	Open-source AI libraries present significant, underexamined risks spanning security, licensing, maintenance, supply chain integrity, and regulatory compliance.
Approach:	They propose a system that leverages large language models and agentic workflows to perform deep, evidence-based evaluations of open-source AI libraries.
Outcome:	The proposed system covers up to 88% of OpenSSF Scorecard checks and uncovers 19 additional risks per library.

Interactive Text Games: Lookahead Is All You Need! (2025.acl-srw)

Copied to clipboard

Hosein Rezaei, James Alfred Walker, Frank Soboczenski

Challenge:	Existing approaches to ground LLMs in textual interactions have been limited due to low computational efficiency and limited performance.
Approach:	They propose to use Lookahead models to ground LLMs in interactive text-based games to investigate their language grounding capabilities.
Outcome:	The proposed model significantly improves training speed and performance relative to the size of the action space.

Evaluating Credibility and Political Bias in LLMs for News Outlets in Bangladesh (2025.acl-srw)

Copied to clipboard

Tabia Tanzin Prama, Md. Saiful Islam

The Evolution of Gen Alpha Slang: Linguistic Patterns and AI Translation Challenges (2025.acl-srw)

Challenge:	Large language models (LLMs) are widely used in search engines to provide direct an-swers, while AI chatbots retrieve updated infor-mation from the web.
Approach:	They audit nine Large Language Models from OpenAI, Google, and Meta to assess their ability to eval-uate the credibility and political bias of the top20 most popular news outlets in Bangladesh.
Outcome:	The proposed models show internal consistency in credibil-ity ratings, but misalignment with human experts.

Copied to clipboard

Ishita Ishita, Radhika Mamidi

Machine Translation

Challenge:	Generation Alpha (born 2010-2024) exhibits unique linguistic behaviours influenced by rampant online communication and platform-specific cultures.
Approach:	They construct a comprehensive slang corpus from online platforms and evaluate four AI translation systems on over 100 sling terms.
Outcome:	The proposed translation systems outperform four existing translation models on over 100 slang terms.

Light-Weight Hallucination Detection using Contrastive Learning for Conditional Text Generation (2025.acl-srw)

Copied to clipboard

Miyu Yamada, Yuki Arase

Fact from Fiction: Finding Serialized Novels in Newspapers (2025.acl-srw)

Challenge:	Existing methods for hallucination detection are limited to the scenario where we can access the LLMs that have generated the outputs.
Approach:	They propose a hallucination detection method that uses contrastive learning to pull faithful outputs and input contexts together while pushing hallucinous outputs apart.
Outcome:	The proposed method outperforms GPT-4o prompting in binary hallucination detection.

Copied to clipboard

Pascale Feldkamp, Alie Lassche, Katrine Frøkjær Baunvig, Kristoffer Nielbo, Yuri Bizzoni

Challenge:	Among underrepresented but widely read forms are serialized fiction and feuilleton novels embedded in newspapers rather than published as standalone volumes.
Approach:	They propose to annotate 1,394 articles and evaluate classification pipelines using both selected linguistic features and embeddings to identify serialized fiction and feuilleton fiction.
Outcome:	The proposed methods achieve F1-scores of 0.91 in an annotated dataset of 1,394 articles and support the construction of alternative literary corpora and contribute to work on modeling the fiction–nonfiction boundary at scale.

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

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.

A Computational Framework to Identify Self-Aspects in Text (2025.acl-srw)

Copied to clipboard

Jaya Caporusso, Matthew Purver, Senja Pollak

Prompting the Muse: Generating Prosodically-Correct Latin Speech with Large Language Models (2025.acl-srw)

Challenge:	a Ph.D. proposal aims to identify Self-aspects in text, which are underexplored in natural language processing . many aspects of the Self align with psychological and other well-researched phenomena .
Approach:	They propose to develop a computational framework to identify Self-aspects in text . they will use an ontology of Self-facets and an annotated gold-standard dataset .
Outcome:	The proposed framework will evaluate discriminative models, generative large language models, embedding-based retrieval approaches against four main criteria: interpretability, ground-truth adherence, accuracy, and computational efficiency.

Copied to clipboard

Michele Ciletti

Can a Large Language Model Keep My Secrets? A Study on LLM-Controlled Agents (2025.acl-srw)

Challenge:	a workflow compels an audio-enabled large language model to recite Latin poetry with metrically accurate stress.
Approach:	They propose a workflow that compels an audio-enabled large language model to recite Latin poetry with metrically accurate stress.
Outcome:	The proposed model can recite Latin poetry with metrically accurate stress.

Copied to clipboard

Niklas Hemken, Sai Koneru, Florian Jacob, Hannes Hartenstein, Jan Niehues

Chart Question Answering from Real-World Analytical Narratives (2025.acl-srw)

Challenge:	Using large language models, agents can assist with natural language tasks when given access to confidential data.
Approach:	They created a synthetic dataset consisting of confidentiality-aware planning and deduction tasks in organizational access control.
Outcome:	The proposed model can perform tasks similar to humans when given access to confidential data.

Copied to clipboard

Maeve Hutchinson, Radu Jianu, Aidan Slingsby, Jo Wood, Pranava Madhyastha

Natural Language Interfaces

Challenge:	a dataset for chart question answering is constructed from visualization notebooks . data visualizations are an essential modality for communicating complex information about data.
Approach:	They propose a dataset for chart question answering constructed from visualization notebooks . they use real-world, multi-view charts paired with natural language questions .
Outcome:	The proposed dataset is constructed from student-authored visualization notebooks . it features real-world, multi-view charts paired with natural language questions . initial evaluations highlight significant performance gaps .

Low-Perplexity LLM-Generated Sequences and Where To Find Them (2025.acl-srw)

Copied to clipboard

Arthur Wuhrmann, Andrei Kucharavy, Anastasiia Kucherenko

Challenge:	Large Language Models (LLMs) are increasingly applied across various domains, but the ways they leverage their training data during inference remains only partially understood.
Approach:	They propose a systematic approach that analyzes low-perplexity sequences and traces them back to their sources in the training data.
Outcome:	The proposed pipeline extracts low-perplexity sequences across diverse topics while avoiding degeneration, then trace them back to their sources in the training data.

CoLeM: A framework for semantic interpretation of Russian-language tables based on contrastive learning (2025.acl-srw)

Copied to clipboard

Kirill Tobola, Nikita Dorodnykh

Mitigating Hallucination by Integrating Knowledge Graphs into LLM Inference – a Systematic Literature Review (2025.acl-srw)

Challenge:	Existing methods for semantic interpretation of tables in Russian lack explicit semantics . tabular data are one of the key formats for presenting structured information in various domains ranging from scientific research to business analytics.
Approach:	They propose a contrastive learning approach to minimize reliance on manual labeling and enhance the accuracy of column annotation for rare semantic types.
Outcome:	The proposed method minimizes reliance on manual labeling and improves column annotation accuracy for rare semantic types.

Copied to clipboard

Robin Wagner, Emanuel Kitzelmann, Ingo Boersch

Structured Data in NLP

Challenge:	Large Language Models (LLMs) have made significant progress on different language tasks, but they tend to "hallucinate" plausible but factually incorrect answers.
Approach:	They propose to integrate knowledge graphs (KGs) into LLM inference to reduce hallucinations by searching online and applying a selection process.
Outcome:	The proposed integration improves performance on benchmark datasets and also to mitigate hallucinations.

Semantic alignment in hyperbolic space for fine-grained emotion classification (2025.acl-srw)

Copied to clipboard

Ashish Kumar, Durga Toshniwal

Information Retrieval

Challenge:	Existing approaches to fine-grained emotion classification operate in Euclidean space, where the flat geometry makes it difficult to distinguish semantically similar label labels.
Approach:	They propose a semantic alignment framework that leverages the Lorentz model of hyperbolic space to embed text and label representations into hyperbolical space via the exponential map.
Outcome:	The proposed framework improves on two benchmark FEC datasets.

I Speak for the Árboles: Developing a Dependency Treebank for Spanish L2 and Heritage Speakers (2025.acl-srw)

Copied to clipboard

Emiliana Pulido, Robert Pugh, Zoey Liu

Syntactic Text Processing

Challenge:	Existing dependency treebanks for learner writing are limited due to morphosyntactic features.
Approach:	They propose to use a dependency treebank for Spanish learner writing from the UC Davis COWSL2H corpus to incorporate lemmatization, POS tagging, and syntactic dependencies.
Outcome:	The proposed treebanks are openly accessible to motivate future development of learner-oriented language technologies.

Evaluating Tokenizer Adaptation Methods for Large Language Models on Low-Resource Programming Languages (2025.acl-srw)

Copied to clipboard

Georgy Andryushchenko, Vladimir V. Ivanov

Learning and Enforcing Context-Sensitive Control for LLMs (2025.acl-srw)

Challenge:	Large language models (LLMs) trained on high-resource programming languages perform sub-optimally for low-resourced programming languages (LRPLs).
Approach:	They evaluate the impact of tokenizer adaptation methods on improving code generation for LRPLs.
Outcome:	The proposed methods outperform the original models and fine-tuned models in LRPLs, but performance declines in non-target languages like Python after tokenizer adaptation.

Copied to clipboard

Mohammad Albinhassan, Pranava Madhyastha, Mark Law, Alessandra Russo

Challenge:	Large Language Models (LLMs) have been able to achieve syntactic correctness but ensuring semantic validity requires additional mechanisms.
Approach:	They propose a framework that automatically learns context-sensitive constraints from LLM interactions through syntactic exploration and constraint exploitation.
Outcome:	The proposed framework outperforms larger models and state-of-the-art models in learning and generation of large LLMs.

When Will the Tokens End? Graph-Based Forecasting for LLMs Output Length (2025.acl-srw)

Copied to clipboard

Grzegorz Piotrowski, Mateusz Bystroński, Mikołaj Hołysz, Jakub Binkowski, Grzegorz Chodak, Tomasz Jan Kajdanowicz

Only for the Unseen Languages, Say the Llamas: On the Efficacy of Language Adapters for Cross-lingual Transfer in English-centric LLMs (2025.acl-srw)

Challenge:	Large Language Models (LLMs) are typically trained to predict the next token in a sequence. However, their internal representations encode signals that go beyond immediate next-token prediction.
Approach:	They propose an aggregation-based model that combines hidden states from multiple transformer layers l 8, dots, 15 using element-wise operations such as mean or sum.
Outcome:	The proposed model reduces NMAE by over 50% on the Alpaca dataset.

Copied to clipboard

Julian Schlenker, Jenny Kunz, Tatiana Anikina, Günter Neumann, Simon Ostermann

Green & Sustainable NLP

Challenge:	Most state-of-the-art large language models (LLMs) are trained mainly on English data, limiting their effectiveness on non-English, especially low-resource, languages.
Approach:	They train language adapters for 13 languages and evaluate their effectiveness on downstream tasks using either task adapters or in-context learning.
Outcome:	The proposed language adapters improve performance for languages not seen during pretraining, but provide negligible benefit for seen languages.

HyILR: Hyperbolic Instance-Specific Local Relationships for Hierarchical Text Classification (2025.acl-srw)

Copied to clipboard

Ashish Kumar, Durga Toshniwal

Information Extraction & Text Mining

Challenge:	Hierarchical text classification models rely on capturing global label hierarchy, which contains static and redundant relationships.
Approach:	They propose a method which captures hierarchical relationships without encoding global hierarchy . they use hyperbolic geometry to model instance-specific local relationships using Lorentz model .
Outcome:	The proposed model captures hierarchical relationships without encoding global hierarchy . the proposed model is superior to baseline methods on four benchmark datasets .

Are LLMs Truly Graph-Savvy? A Comprehensive Evaluation of Graph Generation (2025.acl-srw)

Copied to clipboard

Ege Demirci, Rithwik Kerur, Ambuj Singh

Pragmatic Perspective on Assessing Implicit Meaning Interpretation in Sentiment Analysis Models (2025.acl-srw)

Challenge:	Large language models have demonstrated impressive capabilities across diverse tasks . however, their ability to generate valid graph structures remains underexplored .
Approach:	They evaluate large language models on five specialized graph generation tasks . they also test the models using 3 different prompt types: direct, iterative feedback, and program-augmented.
Outcome:	The proposed models solve twice as many tasks as general-purpose models, compared to their general-usage peers.

Copied to clipboard

Rashid Mustafin

Explainability & Interpretability in NLP

Challenge:	Using pragmatic theories of implicature, interpreting texts with implicit meaning correctly is essential for precise natural language understanding.
Approach:	They propose to use transformer models fine-tuned for sentiment analysis to illustrate the challenges in computational interpretation of implicatures.
Outcome:	The proposed model classifications reveal the limitations of supervised machine learning methods in detecting implicit sentiments.

Foundations of PEERS: Assessing LLM Role Performance in Educational Simulations (2025.acl-srw)

Copied to clipboard

Jasper Meynard Arana, Kristine Ann M. Carandang, Ethan Robert Casin, Christian Alis, Daniel Stanley Tan, Erika Fille Legara, Christopher Monterola

Challenge:	In education, peer instruction is widely recognized as an effective active learning strategy, but evaluations of PI are limited by logistical constraints and variability in classroom settings.
Approach:	They propose a simulation framework that integrates Agent-Based Modeling, Large Language Models, and Bayesian Knowledge Tracing to emulate student learning dynamics.
Outcome:	The proposed framework integrates Agent-Based Modeling, Large Language Models, and Bayesian Knowledge Tracing to emulate student learning dynamics in real classrooms.

The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering (2025.acl-srw)

Copied to clipboard

Yi-Jie Cheng, Oscar Chew, Yun-Nung Chen

Bridging the Embodiment Gap in Agricultural Knowledge Representation for Language Models (2025.acl-srw)

Challenge:	Existing methods to integrate knowledge graphs into large language models often rely on proprietary or extremely large models .
Approach:	They propose to integrate knowledge graphs into reasoning processes of large language models . they propose to use simple and efficient exploration modules to handle knowledge graph traversal .
Outcome:	The proposed modules improve the performance of small language models on knowledge graph question answering tasks.

Copied to clipboard

Vasu Jindal, Huijin Ju, Zili Lyu

Building Japanese Creativity Benchmarks and Applying them to Enhance LLM Creativity (2025.acl-srw)

Challenge:	a paper quantifies the “embodiment gap” between disembodied language models and embodied agricultural knowledge communication . agronomists and researchers examined the embodiment gap in 78 farmers .
Approach:	They propose a framework that integrates linguistic patterns from five domains of agricultural expertise and a new metric for evaluating embodied knowledge representation in language models.
Outcome:	The proposed frameworks reduce the embodiment gap by 47.3% across agricultural domains . the proposed framework improves tool usage discourse and soil assessment terminology .

Copied to clipboard

So Fukuda, Hayato Ogawa, Kaito Horio, Daisuke Kawahara, Tomohide Shibata

Towards Robust Sentiment Analysis of Temporally-Sensitive Policy-Related Online Text (2025.acl-srw)

Challenge:	a recent study evaluated the creativity of large language models (LLMs) in Japanese based on a Torrance test of creative thinking . previous research on LLM creativity focused on English, but differences exist in how it manifests and is evaluated across languages and cultures.
Approach:	They construct three benchmarks to evaluate LLM creativity in Japanese . they use Japanese Creativity Questions (JCQ), Divergent Association Task (DAT) and Story Alteration Task (SAT)
Outcome:	The benchmarks evaluate the creativity of large language models (LLMs) in Japanese . the benchmarks are Japanese Creativity Questions (JCQ), Divergent Association Task (DAT), and Story Alteration Task (SAT).

Copied to clipboard

Charles Alba, Benjamin C Warner, Akshar Saxena, Jiaxin Huang, Ruopeng An

Robustness in NLP

Challenge:	Existing methods fail to adequately capture the temporal volatility inherent in policy-related sentiments, arguing that continuous time-series clustering and model merging achieve superior performance.
Approach:	They propose to use continuous time-series clustering to select data points for annotation based on temporal trends and then apply model merging techniques.
Outcome:	The proposed methods outperform existing methods by an average F1-score of 2.71% on temporally representative data.

Is Partial Linguistic Information Sufficient for Discourse Connective Disambiguation? A Case Study of Concession (2025.acl-srw)

Copied to clipboard

Takuma Sato, Ai Kubota, Koji Mineshima

Challenge:	Discourse relations are often not linguistically marked, but there are various connectives that explicitly signal discourse relations.
Approach:	They analyze linguistic features that play an important role in disambiguation of polysemous connectives in Japanese by performing a neural language model.
Outcome:	The proposed model performed well after removal of one of the two arguments that constitute the discourse relation, but significantly degraded disambiguation performance.

Semantic Frame Induction from a Real-World Corpus (2025.acl-srw)

Copied to clipboard

Shogo Tsujimoto, Kosuke Yamada, Ryohei Sasano

Lost and Found: Computational Quality Assurance of Crowdsourced Knowledge on Morphological Defectivity in Wiktionary (2025.acl-srw)

Challenge:	Existing studies on semantic frame induction have demonstrated that pre-trained language models (PLMs) have led to more accurate results.
Approach:	They conduct semantic frame induction using the Colossal Clean Crawled Corpus and assess the applicability of existing frame inducing methods to real-world data.
Outcome:	The proposed methods outperform existing methods on real-world data and can induce frames corresponding to novel concepts.

Copied to clipboard

Jonathan Sakunkoo, Annabella Sakunkoo

Morphology

Challenge:	a recent study shows that wikis are not reliable for linguistic knowledge of defects in understudied languages.
Approach:	They customize a neural morphological analyzer to annotate Latin and Italian corpora . they validated morphology using crowd-sourced data from Wiktionary to find defects .
Outcome:	The proposed algorithm annotates Latin and Italian corpora using crowd-sourced data . results show that 7% of Latin lemmata listed as defective show strong corpus evidence of being non-defective.

Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error Correction (2025.acl-srw)

Copied to clipboard

Takumi Goto, Justin Vasselli, Taro Watanabe

Proposal: From One-Fit-All to Perspective Aware Modeling (2025.acl-srw)

Challenge:	Existing evaluation metrics for Grammatical error correction lack explainability . lack of explainability hinders researchers from analyzing strengths and weaknesses of models .
Approach:	They propose to assign sentence-level scores to individual edits to improve GEC performance . they use Shapley values, from cooperative game theory, to compute contribution of each edit .
Outcome:	The proposed method shows that the evaluation metrics are consistent across edits and human evaluations.

Copied to clipboard

Leixin Zhang

Challenge:	Variation in human annotation and human perspectives has drawn increasing attention in natural language processing research.
Approach:	They propose to use annotation formats that better capture granularity and uncertainty of individual judgments and annotation modeling that leverages socio-demographic features to better represent and predict underrepresented or minority perspectives.
Outcome:	The proposed tasks aim to advance natural language processing research towards more faithfully reflecting the diversity of human interpretation, enhancing both inclusiveness and fairness in language technologies.

Controlling Language Confusion in Multilingual LLMs (2025.acl-srw)

Copied to clipboard

Nahyun Lee, Yeongseo Woo, Hyunwoo Ko, Guijin Son

Grammatical Error Correction via Sequence Tagging for Russian (2025.acl-srw)

Challenge:	Large language models suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages.
Approach:	They propose a supervised fine-tuning methodology which optimizes the likelihood of correct tokens without explicitly penalizing undesired outputs such as cross-lingual mixing.
Outcome:	The proposed model suppresses language-confused generation while maintaining strong language consistency even under high decoding temperatures while preserving general QA performance.

Copied to clipboard

Regina Nasyrova, Alexey Sorokin

Syntactic Text Processing

Challenge:	Several types of models have been suggested for grammatical error correction . despite being successful, the difference between GEC and machine translation is not taken into account .
Approach:	They propose a modified sequence tagging architecture for the Russian language to be used for grammatical error correction.
Outcome:	The proposed model outperforms previous approaches on two Russian GEC benchmarks while achieving competitive performance on RULEC-GEC.

DRUM: Learning Demonstration Retriever for Large MUlti-modal Models (2025.acl-srw)

Copied to clipboard

Ellen Yi-Ge, Jiechao Gao, Wei Han, Wei Zhu

GerMedIQ: A Resource for Simulated and Synthesized Anamnesis Interview Responses in German (2025.acl-srw)

Challenge:	Recent studies have shown that large language models (LLMs) have impressive capabilities in dealing with new tasks with the help of in-context learning (ICL).
Approach:	They propose to concate the image and text embeddings to enhance the retrieval performance of a visual-language task and to calculate a list-wise ranking loss for training the embeddable model.
Outcome:	The proposed framework fine-tunes the CLIP embedding model to better meet the needs of the large vision-language models.

Copied to clipboard

Justin Hofenbitzer, Sebastian Schöning, Belle Sebastian, Jacqueline Lammert, Luise Modersohn, Martin Boeker, Diego Frassinelli

Unstructured Minds, Predictable Machines: A Comparative Study of Narrative Cohesion in Human and LLM Stream-of-Consciousness Writing (2025.acl-srw)

Challenge:	Text corpora in non-English clinical contexts is scarce due to privacy restrictions and restricted access to secure environments.
Approach:	They propose to use Large Language Models to generate synthetic data using a German medical interview questions corpus.
Outcome:	The proposed dataset generates comparable responses to human-generated questions.

Copied to clipboard

Nellia Dzhubaeva, Katharina Trinley, Laura Pissani

Exploiting contextual information to improve stance detection in informal political discourse with LLMs (2025.acl-srw)

Challenge:	Stream-of-consciousness narratives are a challenge for large language models (LLMs) authors examined differences between human and LLM-generated narratives to assess narrative coherence and personality expression.
Approach:	They generate SoC narratives by prompting LLMs with the first half of SoC-essays while either providing the models with the personality characteristics (Big Five) or omitting them.
Outcome:	The proposed models showed low similarity between LLM-generated continuations and original human texts, as measured by cosine similarity, perplexity, and BLEU scores.

Copied to clipboard

Arman Engin Sucu, Yixiang Zhou, Mario A. Nascimento, Tony Mullen

Sentiment Analysis

Challenge:	Political stance detection is an increasingly relevant part of analyzing the flow of ideas in online environments where discourse is informal and implicitly expressed.
Approach:	They evaluate large language models for political stance detection in informal online discourse by analyzing user profiles derived from historical posts.
Outcome:	The proposed model improves accuracy by up to 74% on a political forum dataset.

A Framework for Fine-Grained Complexity Control in Health Answer Generation (2025.acl-srw)

Copied to clipboard

Daniel Jorge Bernardo Ferreira, Tiago Almeida, Sérgio Matos

Natural Language Interfaces

Challenge:	Health literacy is the ability to obtain, process, and understand basic health information.
Approach:	They propose a framework for automatically generating health answers at multiple, precisely controlled complexity levels.
Outcome:	The proposed framework allows users to generate health questions at multiple complexity levels.

QA Analysis in Medical and Legal Domains: A Survey of Data Augmentation in Low-Resource Settings (2025.acl-srw)

Copied to clipboard

Benedictus Kent Rachmat, Thomas Gerald, Zheng Zhang Slb, Cyril Grouin

Time-LlaMA: Adapting Large Language Models for Time Series Modeling via Dynamic Low-rank Adaptation (2025.acl-srw)

Challenge:	Large Language Models (LLMs) have revolutionized natural language processing, but their success remains limited to high-resource domains.
Approach:	They analyze the coverage and representativeness of specialized-domain QA datasets against large-scale reference datasets.
Outcome:	The proposed methods and evaluations highlight the challenges faced by LLMs in low-resource domains.

Copied to clipboard

Juyuan Zhang, Jiechao Gao, Wenwen Ouyang, Wei Zhu, Hui Yi Leong

RusConText Benchmark: A Russian Language Evaluation Benchmark for Understanding Context (2025.acl-srw)

Challenge:	Recent studies have demonstrated that large language models possess robust pattern recognition and semantic understanding capabilities over time series data.
Approach:	They propose a time series model that converts time series input into token embeddings and aligns time sequence embeddables with text prompts.
Outcome:	The proposed framework achieves the state-of-the-art (SOTA) performance and has potentials for wide industrial usages.

Copied to clipboard

Andrey Chirkin, Svetlana Kuznetsova, Maria Volina, Anna Dengina

Challenge:	a new context understanding benchmark is proposed for short-context understanding in Russian . the benchmarks focus on broad reasoning tasks or long-concept comprehension, but are limited in their ability to perceive subtle nuances of context.
Approach:	They propose a new benchmark for evaluating short-context understanding in Russian . they propose to use four tasks to assess model performance from a specific perspective .
Outcome:	The proposed benchmark is adapted to Russian-language data.

GenDLN: Evolutionary Algorithm-Based Stacked LLM Framework for Joint Prompt Optimization (2025.acl-srw)

Copied to clipboard

Pia Chouayfati, Niklas Herbster, Ábel Domonkos Sáfrán, Matthias Grabmair

Sign Language Video Segmentation Using Temporal Boundary Identification (2025.acl-srw)

Challenge:	Large Language Models (LLMs) are increasingly replacing traditional classification and inference models due to their generality, ability to perform a wide range of tasks, and seemingly advanced "reasoning" prompt optimization is a promising alternative to manual/human prompt engineering, but the cost of using LLMs for prompt optimization via commercial APIs remains high.
Approach:	They propose an open-source, efficient genetic algorithm-based prompt pair optimization framework that leverages commercial APIs.
Outcome:	The proposed approach allows teams with limited resources to efficiently use commercial LLMs for prompt optimization.

Copied to clipboard

Kavu Maithri Rao, Yasser Hamidullah, Eleftherios Avramidis

LIP-NER: Literal Patterns Benefit LLM-Based NER (2025.acl-srw)

Challenge:	Sign language segmentation focuses on identifying temporal boundaries within video . previous methods have relied on frame-level and phrase-level segmentation.
Approach:	They propose to use synchronized subtitle data to facilitate temporal boundary recognition by a sequence-to-sequence model with and without attention for subtitle boundary identification.
Outcome:	The proposed model outperforms baseline models on optical flow data and aligned subtitles from BOBSL and YouTube-ASL.

Copied to clipboard

Ruiqi Li, Li Chen

Information Extraction & Text Mining

Challenge:	Existing methods for Named Entity Recognition (NER) use semantic information, but it is non-trivial to obtain literal patterns written in natural language.
Approach:	They propose an LLM-based NER framework that utilizes Literal Patterns to acquire literal patterns in natural language.
Outcome:	The proposed framework reduces human labor and provides a more efficient way to acquire literal patterns.

Testing English News Articles for Lexical Homogenization Due to Widespread Use of Large Language Models (2025.acl-srw)

Copied to clipboard

Sarah Fitterer, Dominik Gangl, Jannes Ulbrich