TIME

A Benchmark and Evaluation of Automated Language of Study Extraction from Computational Linguistics Publications (2026.eacl-srw)

Challenge:	Existing approaches to capture global context dependencies in sequence modeling suffer from quadratic complexity in time and memory usage.
Approach:	They propose an efficient Transformer architecture for fast long-range sequence modeling with a sparse attention matrix and a hidden state cross module.
Outcome:	The proposed architecture outperforms the standard multi-head attention and its variants in various long-sequence tasks with low computational costs.

Copied to clipboard

Henry Gagnier, Ashwin Kirubakaran

Coding Open-Ended Responses using Pseudo Response Generation by Large Language Models (2024.naacl-srw)

Challenge:	Language of study extraction is an aspect of computational linguistics papers that is useful for analyses of trends and diversity in computational linguists.
Approach:	They propose to benchmark and evaluate automated language of study extraction from computational linguistics papers.
Outcome:	The proposed language extraction benchmarks show that they can extract languages from papers with accuracy without high computational costs.

Copied to clipboard

Yuki Zenimoto, Ryo Hasegawa, Takehito Utsuro, Masaharu Yoshioka, Noriko Kando

CoRefi: A Crowd Sourcing Suite for Coreference Annotation (2020.emnlp-demos)

Challenge:	Existing pipelines for survey research using open-ended responses require time and cost-consuming manual tasks.
Approach:	They propose an LLM-based method to automate parts of the grounded theory approach . they generate and annotate pseudo open-ended responses and use them as training data .
Outcome:	The proposed method is highly efficient andcost-saving compared to human-based methods.

Copied to clipboard

Ari Bornstein, Arie Cattan, Ido Dagan

Basreh or Basra? Geoparsing Historical Locations in the Svoboda Diaries (2024.acl-srw)

Challenge:	Using a web-based coreference annotation suite, we demonstrate that non-expert annotators can be trained to perform and review coreference resolution tasks.
Approach:	They propose a web-based coreference annotation suite oriented for crowdsourcing that provides guided onboarding and a novel algorithm for a reviewing phase.
Outcome:	The proposed tool provides guided onboarding and a novel algorithm for a review phase.

Copied to clipboard

Jolie Zhou, Camille Cole, Annie Chen

SMILE: Single-turn to Multi-turn Inclusive Language Expansion via ChatGPT for Mental Health Support (2024.findings-emnlp)

Challenge:	In the historical domain, many geoparsing corpora are from large news collections.
Approach:	They propose a pipeline employing named entity recognition for geotagging and a map-based generate-and-rank approach incorporating candidate name augmentation and clustering of location context words for geocoding.
Outcome:	The proposed pipeline outperforms existing map-based geoparsers in terms of accuracy, lowest mean distance error, and number of locations correctly identified.

Copied to clipboard

Huachuan Qiu, Hongliang He, Shuai Zhang, Anqi Li, Zhenzhong Lan

Dialogue Systems & Conversational Agents

Challenge:	Developing specialized dialogue systems for mental health support requires multi-turn conversation data . data privacy protection, time and cost involved in crowdsourcing are challenges . a new method for rewriting public single-turn dialogues into multi-turned ones is needed .
Approach:	They propose a single-turn to multi-turn inclusive language expansion technique that prompts ChatGPT to rewrite public single-turned dialogues into multi-turned ones.
Outcome:	The proposed method generates a large-scale, lifelike, and diverse dialogue dataset . it also develops SMILECHAT, a mental health chatbot .

Unsupervised Quality Estimation for Neural Machine Translation (2020.tacl-1)

Copied to clipboard

Marina Fomicheva, Shuo Sun, Lisa Yankovskaya, Frédéric Blain, Francisco Guzmán, Mark Fishel, Nikolaos Aletras, Vishrav Chaudhary, Lucia Specia

Split-NER: Named Entity Recognition via Two Question-Answering-based Classifications (2023.acl-short)

Challenge:	Existing approaches require large amounts of expert annotated data, computation, and time for training.
Approach:	They propose an unsupervised approach to QE where no training is required . they use a dataset that enables work on both black-box and glass-box approaches .
Outcome:	The proposed approach rivals state-of-the-art supervised QE models in terms of correlation with human judgments of quality.

Copied to clipboard

Jatin Arora, Youngja Park

HULK: An Energy Efficiency Benchmark Platform for Responsible Natural Language Processing (2021.eacl-demos)

Challenge:	Named entity recognition (NER) is a foundational task for a variety of applications like question answering and machine translation.
Approach:	They propose to split entity recognition problem into two sub-tasks and optimize them separately for each sub-task.
Outcome:	The proposed system outperforms baselines on OntoNotes5.0, WNUT17 and a cybersecurity dataset and gives on-par performance on BioNLP13CG.

Copied to clipboard

Xiyou Zhou, Zhiyu Chen, Xiaoyong Jin, William Yang Wang

Beyond Abstracts: A New Dataset, Prompt Design Strategy and Method for Biomedical Synthesis Generation (2024.acl-srw)

Challenge:	Pretrained models have been taking the lead of many natural language processing benchmarks such as GLUE, but energy efficiency in the process of model training and inference becomes a critical bottleneck.
Approach:	They propose a multi-task energy efficiency benchmarking platform for responsible natural language processing that compares pretrained models’ energy efficiency from the perspectives of time and cost.
Outcome:	The proposed model improves on the fine-tuning efficiency of pretrained models from the perspectives of time and cost.

Copied to clipboard

James O’Doherty, Cian Nolan, Yufang Hou, Anya Belz

MergeIT: From Selection to Merging for Efficient Instruction Tuning (2026.findings-acl)

Challenge:	Existing methods to automate systematic reviews of papers are slow and incomplete . authors propose a new method to automating the systematic review process .
Approach:	They propose a method for automatic synthesis generation using a dataset and prompting-based method.
Outcome:	The proposed method improves the existing model and prompts the system to generate high-quality syntheses.

Copied to clipboard

Hongyi Cai, Yuqian Fu, Hongming Fu, Bo Zhao

Automatic Linking of Judgements to UK Supreme Court Hearings (2023.emnlp-industry)

Challenge:	Existing methods for instruction tuning rely on LLMs to score instruction quality . existing methods rely only on Llms to rank instruction quality, but this approach is expensive and time-consuming .
Approach:	They propose a novel LLM-based Merging strategy for better Instruction Tuning that shifts the focus from selection to synthesis.
Outcome:	The proposed method reduces time and computational cost while preserving diversity and reducing redundancy.

Copied to clipboard

Hadeel Saadany, Constantin Orasan

SACR: A Drag-and-Drop Based Tool for Coreference Annotation (L18-1)

Challenge:	a number of legal documents are archived in the UK, including the Supreme Court's decisions and video recordings of court hearings.
Approach:	They propose to link segments in the text judgement to semantically relevant timespans in the videos of the hearings.
Outcome:	The proposed tool links segments in the text judgement to semantically relevant timespans in the videos of the hearings.

Copied to clipboard

Bruno Oberle

LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning (2024.findings-emnlp)

Challenge:	Several annotation strategies have been proposed to balance scientific needs with annotation speed.
Approach:	They introduce SACR, an easy-to-use coreference chain annotation tool . it is used to annotate large corpora for natural language processing applications . paper compares several annotation schemes implemented in existing tools .
Outcome:	The proposed tool is used to annotate large corpora for natural language processing applications.

Copied to clipboard

Silin Meng, Yiwei Wang, Cheng-Fu Yang, Nanyun Peng, Kai-Wei Chang

Towards Boosting LLMs-driven Relevance Modeling with Progressive Retrieved Behavior-augmented Prompting (2025.coling-industry)

Challenge:	Existing path planning algorithms suffer from significant computational and memory inefficiencies as the state space grows . large language models excel in environmental analysis but fall short in detailed spatial and temporal reasoning .
Approach:	They propose a new path planning method that synergistically combines A* and LLMs to improve pathfinding efficiency.
Outcome:	The proposed method improves pathfinding efficiency while maintaining integrity of path validity in large-scale scenarios.

Copied to clipboard

Zeyuan Chen, Haiyan Wu, Kaixin Wu, Wei Chen, Mingjie Zhong, Jia Xu, Zhongyi Liu, Wei Zhang

Modeling language evolution and feature dynamics in a realistic geographic environment (2020.coling-main)

Challenge:	Existing approaches to relevance modeling have lacked generalization and accuracy . recent studies have focused on capturing the semantic relationships between queries and items .
Approach:	They propose a framework that integrates world knowledge stored in LLMs with specialized domain knowledge represented by user behavior data for promising performance.
Outcome:	The proposed framework can handle full-scale search traffics of Alipay with acceptable cost and latency.

Copied to clipboard

Rhea Kapur, Phillip Rogers

Challenge:	a number of studies have examined the stability or biases of typological features within language families .
Approach:	They propose a model for simulating languages and their features over time in a realistic geographic environment.
Outcome:	The proposed model is flexible and realistic, and can be used to answer questions.

Subword-Delimited Downsampling for Better Character-Level Translation (2022.findings-emnlp)

Copied to clipboard

Lukas Edman, Antonio Toral, Gertjan van Noord

Machine Translation

Challenge:	Subword-level models are expensive in terms of time and computation, but character-level model with downsampling component can be used for machine translation.
Approach:	They propose a character-level downsampling method which is informed by subwords to improve model performance.
Outcome:	The proposed method outperforms existing methods and shows that it can be done without sacrificing quality.

FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use (2026.acl-demo)

Copied to clipboard

Suparno Roy Chowdhury, Tejas Anvekar, Manan Roy Choudhury, Muhammad Ali Khan, Kaneez Zahra Rubab Khakwani, M Bassam Sonbol, Irbaz Bin Riaz, Vivek Gupta

Programming Languages in NLP

Challenge:	Clinical trial databases are central to modern oncology research and drug development.
Approach:	FD-NL2SQL is a schema-aware clinical NL2sql assistant for SQLite-based oncology databases . it decomposes a natural-language question into predicate-level sub-questions and synthesizes executable SQL .
Outcome:	FD-NL2SQL synthesizes SQL based on decomposition, retrieved exemplars, and schema . clinical trial databases are central to modern oncology research and drug development .

Linear-time Constituency Parsing with RNNs and Dynamic Programming (P18-2)

Copied to clipboard

Juneki Hong, Liang Huang

Efficient Classification of Long Documents Using Transformers (2022.acl-short)

Challenge:	Existing span-based constituency parsers are too slow for longer sentences and for applications beyond sentence boundaries.
Approach:	They propose a linear-time constituency parser with RNNs and dynamic programming using graph-structured stack and beam search.
Outcome:	The proposed parser is faster for long sentences and faster for discourse parsing.

Copied to clipboard

Hyunji Park, Yogarshi Vyas, Kashif Shah

Reusable workflows for gender prediction (L18-1)

Challenge:	Several methods have been proposed for classifying long textual documents using Transformers, but there is a lack of consensus on a benchmark to enable a fair comparison among different approaches.
Approach:	They propose to use a dataset to evaluate the relative efficacy of various models for long document classification using Transformers.
Outcome:	The proposed models outperform simple baseline models and yield inconsistent performance across datasets.

Copied to clipboard

Matej Martinc, Senja Pollak

Challenge:	Existing systems for author profiling (AP) modeling require extensive feature engineering and testing.
Approach:	They propose to implement a system for author profiling (AP) modeling that reduces the complexity and time of building a sophisticated model for a number of different AP tasks.
Outcome:	The proposed model achieves comparable results to state of the art models for cross-genre gender prediction, but lags when genre of test set is different from genre of train set.

Happy Are Those Who Grade without Seeing: A Multi-Task Learning Approach to Grade Essays Using Gaze Behaviour (2020.aacl-main)

Copied to clipboard

Sandeep Mathias, Rudra Murthy, Diptesh Kanojia, Abhijit Mishra, Pushpak Bhattacharyya

CogCompNLP: Your Swiss Army Knife for NLP (L18-1)

Challenge:	Using gaze behaviour to solve automatic essay grading tasks is costly in terms of time and money.
Approach:	They propose to collect gaze behaviour from 48 essays and learn gaze behaviour for the rest of the essays using a multi-task learning framework.
Outcome:	The proposed approach achieves a statistically significant improvement over the state-of-the-art system for the essay sets where gaze data is available.

Copied to clipboard

Daniel Khashabi, Mark Sammons, Ben Zhou, Tom Redman, Christos Christodoulopoulos, Vivek Srikumar, Nicholas Rizzolo, Lev Ratinov, Guanheng Luo, Quang Do, Chen-Tse Tsai, Subhro Roy, Stephen Mayhew, Zhili Feng, John Wieting, Xiaodong Yu, Yangqiu Song, Shashank Gupta, Shyam Upadhyay, Naveen Arivazhagan, Qiang Ning, Shaoshi Ling, Dan Roth

Challenge:	a corpus-reader module supports popular corpora, feature extraction and annotation modules for semantic and syntactic tasks.
Approach:	They propose a library that provides modules to address different challenges . they provide a corpus-reader module that supports popular corpora in the NLP community .
Outcome:	The proposed library simplifies the process of design and development of NLP applications by providing modules to address different challenges.

Lil: Less is Less When Applying Post-Training Sparse-Attention Algorithms in Long-Decode Stage (2026.findings-acl)

Copied to clipboard

Junhao Hu, Fangze Li, Mingtao Xu, Feifan Meng, Shiju Zhao, Tiancheng Hu, Ting Peng, Anmin Liu, Wenrui Huang, Chenxu Liu, Ziyue Hua, Tao Xie

Challenge:	Prior work typically decomposes inference into prefill and decode stages, with the decode stage dominating total latency.
Approach:	They propose an algorithm that detects threshold where information loss exceeds information gain during sparse decoding to reduce token consumption by up to 90% and a marginal accuracy degradation of less than 2%.
Outcome:	The proposed algorithm reduces token consumption by 90% with a marginal accuracy degradation of less than 2% across reasoning-intensive benchmarks.

Strong Baselines for Neural Semi-Supervised Learning under Domain Shift (P18-1)

Copied to clipboard

Sebastian Ruder, Barbara Plank

Compact Personalized Models for Neural Machine Translation (D18-1)

Challenge:	Existing neural models for learning under domain shifts only evaluate on a single task, on proprietary datasets, or compare to weak baselines.
Approach:	They propose a multi-task tri-training method that reduces time and space complexity of classic bootstrapping approaches.
Outcome:	The proposed method outperforms the state-of-the-art for sentiment analysis on two benchmarks.

Copied to clipboard

Joern Wuebker, Patrick Simianer, John DeNero

Machine Translation

Challenge:	a large proportion of model parameters can be frozen during adaptation with minimal or no reduction in translation quality.
Approach:	They propose gradient-based domain adaptation methods for self-attentive machine translation models . they encourage structured sparsity in the set of offset tensors during learning .
Outcome:	The proposed method achieves high space and time efficiency using sparse models . the results compare the proposed method with incremental adaptation .

Examining Temporality in Document Classification (P18-2)

Copied to clipboard

Xiaolei Huang, Michael J. Paul

Temporal Attention for Language Models (2022.findings-naacl)

Challenge:	a recent study examines how document classification models trained during one time period perform on documents trained during other time periods.
Approach:	They propose to use a domain adaptation approach to adjust for changes in time to improve document classification.
Outcome:	The proposed model improves on documents trained on time intervals even on future time interval intervals.

Copied to clipboard

Guy D. Rosin, Kira Radinsky

How much pretraining data do language models need to learn syntax? (2021.emnlp-main)

Challenge:	Pretrained language models are trained on corpora derived from the web, but ignore this information.
Approach:	They propose a time-aware self-attention mechanism that captures time-specific contextualized word representations and allows the transformer to capture this information.
Outcome:	The proposed model achieves state-of-the-art on three datasets in different languages (English, German, and Latin) that vary in time, size, and genre.

Copied to clipboard

Laura Pérez-Mayos, Miguel Ballesteros, Leo Wanner

Syntactic Text Processing

Challenge:	Pretraining methods are convenient, but expensive in terms of time and resources.
Approach:	They investigate the impact of pretraining data size on the syntactic capabilities of RoBERTa by using syntaktic structural probes to determine whether models pretrained on more data encode a higher amount of syntastic information.
Outcome:	The proposed models perform better on part-of-speech tagging, dependency parsing and paraphrase identification.

Hexatagging: Projective Dependency Parsing as Tagging (2023.acl-short)

Copied to clipboard

Afra Amini, Tianyu Liu, Ryan Cotterell

Syntactic Text Processing

Challenge:	Using a pretrained language model, we can train language models on increasingly large amounts of data.
Approach:	They propose a dependency parser that constructs dependency trees by tagging words with elements from a finite set of possible tags.
Outcome:	The proposed approach achieves state-of-the-art performance of 96.4 LAS and 97.4 UAS on the Penn Treebank test set.

RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoning (2025.findings-acl)

Copied to clipboard

Junhao Hu, Wenrui Huang, Weidong Wang, Zhenwen Li, Tiancheng Hu, Zhixia Liu, Xusheng Chen, Tao Xie, Yizhou Shan

Reasoning

Challenge:	Large Language Models (LLMs) have demonstrated strong capabilities across various domains, but their large-scale deployment faces a major obstacle: the high computational cost of long-sequence inference.
Approach:	They propose an algorithm that retains key-value vectors until they are no longer needed to solve reasoning tasks.
Outcome:	The proposed algorithm achieves high accuracy with O(L) time but O(N) memory complexities.

Sequence Parallelism: Long Sequence Training from System Perspective (2023.acl-long)

Copied to clipboard

Shenggui Li, Fuzhao Xue, Chaitanya Baranwal, Yongbin Li, Yang You

Crake: Causal-Enhanced Table-Filler for Question Answering over Large Scale Knowledge Base (2022.findings-naacl)

Challenge:	Existing work on memory-efficient parallelisms to reduce time and space complexity focuses on reducing time and complexity from system perspective.
Approach:	They propose a memory-efficient parallelism to reduce time and space complexity . they split input sequence into multiple chunks and feed each chunk into GPU .
Outcome:	The proposed approach is compatible with most existing parallelisms and makes 4D parallelismal possible.

Copied to clipboard

Minhao Zhang, Ruoyu Zhang, Yanzeng Li, Lei Zou

Vecalign: Improved Sentence Alignment in Linear Time and Space (D19-1)

Challenge:	Existing methods for knowledge base question answering lack causality modeling . previous work fails to model such causalities in their pipeline .
Approach:	They propose a causal-enhanced table-filler to overcome sequence-modelling issues . they propose an efficient beam-search algorithm to scale complex queries on large-scale KBs.
Outcome:	Experiments on LC-QuAD 1.0 show that the proposed method surpasses state-of-the-arts by a large margin while remaining time and space efficient.

Copied to clipboard

Brian Thompson, Philipp Koehn

Multilinguality

Challenge:	Sentence-aligned bitext is used to train nearly all machine translation systems.
Approach:	They propose a bilingual sentence alignment method which is linear in time and space with respect to the number of sentences being aligned.
Outcome:	The proposed method outperforms the existing method by 5 F1 points on a German–French test set and improves downstream MT quality by 1.7 and 1.6 BLEU in Sinhala-English and Nepali-English, respectively.

Predicting Responses to Psychological Questionnaires from Participants’ Social Media Posts and Question Text Embeddings (2020.findings-emnlp)

Copied to clipboard

Huy Vu, Suhaib Abdurahman, Sudeep Bhatia, Lyle Ungar

When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants (2023.acl-short)

Challenge:	Existing data cannot be used to predict responses for new questions or participants.
Approach:	They propose a method that uses social media texts and the text of the question to predict a participant's questionnaire response.
Outcome:	The proposed method can be used to integrate new participants or new questions into psychological studies without costly data collection.

Copied to clipboard

Anuj Diwan, Eunsol Choi, David Harwath

LSDC: An Efficient and Effective Large-Scale Data Compression Method for Supervised Fine-tuning of Large Language Models (2025.findings-naacl)

Challenge:	Existing models focus on improving the efficiency of self-attention, but in practice they may be slower, especially given modest input lengths that are typical of many tasks.
Approach:	They propose a novel local-attention variant of a self-supervised speech model that uses input length thresholds to identify bottlenecks.
Outcome:	The proposed model is based on a self-attention-based model with a high input length threshold.

Copied to clipboard

Zhaoguang Long, Yuhao Zhou, Shangqing Zhao, Yupei Ren, Li Cai, Chenghao Jia, Zhe Chen, Zhe Fang, Yuxiang Song, Man Lan

Boosting Low-Resource Biomedical QA via Entity-Aware Masking Strategies (2021.eacl-main)

Challenge:	Large Language Models (LLMs) are expanding in scale and size, increasing computational costs . large-scale data compression techniques can reduce the size of training datasets while maintaining data integrity.
Approach:	They propose a large-scale data compression method to reduce the size of training data . they use a bifurcated quantization strategy to maximize the diversity of samples .
Outcome:	The proposed method significantly reduces the size of training data while maximizing the submodular gain.

Copied to clipboard

Gabriele Pergola, Elena Kochkina, Lin Gui, Maria Liakata, Yulan He

ClusterFormer: Neural Clustering Attention for Efficient and Effective Transformer (2022.acl-long)

Challenge:	Biomedical question-answering (QA) provides users with high-quality information from a vast scientific literature.
Approach:	They propose to use a biomedical entity-aware masking strategy to fine-tune masked language models to their domains.
Outcome:	The proposed approach is an adaptation process for masked LMs, not memory or components.

Copied to clipboard

Ningning Wang, Guobing Gan, Peng Zhang, Shuai Zhang, Junqiu Wei, Qun Liu, Xin Jiang

DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models (2023.emnlp-main)

Challenge:	Existing sparse attention methods use fixed patterns to select words without considering similarities between words.
Approach:	They propose a neural clustering method which integrates into the Self-Attention Mechanism in Transformer and integrates it into the target task.
Outcome:	The proposed method outperforms two typical sparse attention methods on translation, text classification, and text matching tasks while having a comparable or even better time and memory efficiency.

Copied to clipboard

Xinwei Wu, Junzhuo Li, Minghui Xu, Weilong Dong, Shuangzhi Wu, Chao Bian, Deyi Xiong

Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection (2023.findings-emnlp)

Challenge:	Existing studies have demonstrated that pretrained language models memorize and regurgitate a significant portion of training data, including atypical data points that appear only once in the training data.
Approach:	They propose a method to locate and erase risky neurons in order to eliminate the impact of privacy data in the model in batches.
Outcome:	The proposed method eliminates the impact of privacy data in the model in batches without affecting the model's performance.

Copied to clipboard

Zhengyuan Liu, Hai Chieu, Nancy Chen

Sentiment Analysis

Challenge:	Existing methods for data-driven annotations require domain-specific and task-aligned supervision.
Approach:	They propose a multi-label and multi-target sampling strategy to optimize the annotation quality.
Outcome:	The proposed method significantly improves performance and learning efficacy on the benchmark stance detection corpora.

Towards Interactive Annotation for Hesitation in Conversational Speech (2020.lrec-1)

Copied to clipboard

Jane Wottawa, Marie Tahon, Apolline Marin, Nicolas Audibert

A Reference-free Segmentation Quality Index (SegReFree) (2023.findings-emnlp)

Challenge:	recognizing affects in spontaneous, non acted speech is expensive in both human resources and time.
Approach:	They aim to automatize the labeling of hesitant speech as a marker of expressed uncertainty.
Outcome:	The proposed method shows that the number of filled pauses and vowel duration increases with the degree of hesitation, and that automatic prediction of the hesitation degree reaches encouraging RMSE results of 1.6.

Copied to clipboard

Evan Lucas, Dylan Kangas, Timothy Havens

Challenge:	Topic segmentation is the process of finding boundaries in sentences that separate groups of adjacent sentences at shifts in semantic meaning.
Approach:	They propose a reference-free segmentation quality index to assess segmentation . metric uses a modified cluster validity metric with semantic embeddings of the sentences .
Outcome:	The proposed metric uses a modified cluster validity metric with semantic embeddings of the sentences to determine the quality of the segmentation.

Semi-Automatic Construction and Refinement of an Annotated Corpus for a Deep Learning Framework for Emotion Classification (2020.lrec-1)

Copied to clipboard

Jiajun Xu, Kyosuke Masuda, Hiromitsu Nishizaki, Fumiyo Fukumoto, Yoshimi Suzuki

Transfer Learning and Distant Supervision for Multilingual Transformer Models: A Study on African Languages (2020.emnlp-main)

Challenge:	Existing methods for emotion classification are expensive and require a large corpus of data.
Approach:	They propose a method for creating a semi-automatically constructed emotion corpus by correcting errors in the corpus.
Outcome:	The proposed method improves the quality of the emotion labels by correcting errors.

Copied to clipboard

Michael A. Hedderich, David Adelani, Dawei Zhu, Jesujoba Alabi, Udia Markus, Dietrich Klakow

Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack (2025.naacl-long)

Challenge:	Recent studies show that results from high-resource languages cannot be easily transferred to realistic, low-resourced scenarios.
Approach:	They analyse performance of multilingual transformer models using available resources for Hausa, isiXhosa and NER and topic classification.
Outcome:	The proposed models can achieve with as little as 10 or 100 labeled sentences the same performance as baselines with much more supervised training data.

Copied to clipboard

Cheng Wang, Yiwei Wang, Yujun Cai, Bryan Hooi

Joint Reasoning for Temporal and Causal Relations (P18-1)

Challenge:	Existing methods for crafting adversarial passages are slow and computationally expensive, requiring either access to retriever’s gradients or large computational resources.
Approach:	They propose a method that leverages two key characteristics of retrievers: insensitivity to token order and bias towards influential tokens to generate effective adversarial passages.
Outcome:	The proposed method achieves superior efficiency and scalability compared to existing methods while maintaining comparable or better attack success rates across multiple datasets.

Copied to clipboard

Qiang Ning, Zhili Feng, Hao Wu, Dan Roth

Reasoning

Challenge:	a cause must occur earlier than its effect, temporal and causal relations are closely related . a joint inference framework is developed for studying temporal, causal relations .
Approach:	They propose a joint inference framework for temporal and causal relations . they use constraints inherent in time and causality to enforce constraints .
Outcome:	The proposed framework improves extraction of temporal and causal relations from text.

Harnessing the power of LLMs: Evaluating human-AI text co-creation through the lens of news headline generation (2023.findings-emnlp)

Copied to clipboard

Zijian Ding, Alison Smith-Renner, Wenjuan Zhang, Joel Tetreault, Alejandro Jaimes

Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video Understanding (2025.acl-long)

Challenge:	Recent advances in Large Language Models (LLMs) have shattered the ceiling of human-like text generation.
Approach:	They compared human-AI interaction types in LLM-assisted news headline generation to determine whether humans can best leverage them for writing.
Outcome:	The guiding and selecting model outputs added the most benefit with the lowest cost (in time and effort) Furthermore, AI assistance did not harm participants’ perception of control compared to freeform editing.

Copied to clipboard

Daoze Zhang, Yuze Zhao, Jintao Huang, Yingda Chen

MorphMark: Flexible Adaptive Watermarking for Large Language Models (2025.acl-long)

Challenge:	Existing multimodal large language models (LLMs) have shown impressive performance on the video understanding task, but extremely long videos still pose significant challenges to their context length, memory consumption, and computational complexity.
Approach:	They propose a vision-language model named Sophia for long video understanding which can efficiently handle hour-scale long videos.
Outcome:	The proposed model exhibits competitive performance compared to existing video understanding baselines across various benchmarks for long video understanding with reduced time and memory consumption.

Copied to clipboard

Zongqi Wang, Tianle Gu, Baoyuan Wu, Yujiu Yang

ILDAE: Instance-Level Difficulty Analysis of Evaluation Data (2022.acl-long)

Challenge:	Existing methods for tracing text origins struggle with a watermark effectiveness dilemma . weaker watermarks preserve text quality, while stronger ones enhance effectiveness .
Approach:	They propose a method that adjusts watermark strength in response to changes in a key factor . they first formalize the problem within a multi-objective trade-off analysis framework .
Outcome:	The proposed method improves watermark effectiveness but reduces text quality . the proposed method prioritizes flexibility and time and space efficiency .

Copied to clipboard

Neeraj Varshney, Swaroop Mishra, Chitta Baral

Text Complexity

Challenge:	Instance-level difficulty analysis of evaluation data is a new field of research that focuses on leveraging instance difficulty in natural language processing.
Approach:	They conduct Instance-Level Difficulty Analysis of Evaluation data in a large-scale setup of 23 datasets and demonstrate its five novel applications.
Outcome:	The proposed model improves efficiency and accuracy, improves quality and improves Out-of-Domain performance.

ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary (2025.coling-main)

Copied to clipboard

Yutong Li, Lu Chen, Aiwei Liu, Kai Yu, Lijie Wen

Single Model Ensemble using Pseudo-Tags and Distinct Vectors (2020.acl-main)

Challenge:	Literature review is an indispensable step in the research process, but literature summary is challenging and time consuming.
Approach:	They propose an LLM agent with human workflow guidance for comparative literature summary . they use a human workflow to extract key elements from relevant literature and generate summaries .
Outcome:	The proposed method outperforms the CoT model in several dimensions.

Copied to clipboard

Ryosuke Kuwabara, Jun Suzuki, Hideki Nakayama

Challenge:	Existing methods for model ensembles require time, memory, and management effort to perform tasks.
Approach:	They propose a method that replicates the effects of a model ensemble with a single model.
Outcome:	The proposed method emulates or outperforms a traditional model ensemble with 1/K-times fewer parameters on text classification and sequence labeling tasks.

Is a Question Decomposition Unit All We Need? (2022.emnlp-main)

Copied to clipboard

Pruthvi Patel, Swaroop Mishra, Mihir Parmar, Chitta Baral

Overlooked Data in Typological Databases: What Grambank Teaches Us About Gaps in Grammars (2022.lrec-1)

Challenge:	Large Language Models (LMs) have achieved state-of-the-art performance on many NLP benchmarks.
Approach:	They propose to decompose a hard question into simpler questions that are easier for models to answer.
Outcome:	The proposed approach significantly improves model performance (24% for GPT3 and 29% for RoBERTa-SQuAD along with a symbolic calculator) by decomposing a hard question into simpler questions that are easier for models to answer.

Copied to clipboard

Jakob Lesage, Hannah J. Haynie, Hedvig Skirgård, Tobias Weber, Alena Witzlack-Makarevich

Syntactic Text Processing

Challenge:	Typological databases can contain a wealth of information beyond the collection of linguistic properties across languages.
Approach:	They use a typological database Grambank to classify and quantify the comments that accompany coded values and aggregate these comments and coded value to derive a level of description for 17 grammatical domains.
Outcome:	The proposed model can estimate the description level of 17 grammatical domains in the available resources for the given language.

Forgotten Knowledge: Examining the Citational Amnesia in NLP (2023.acl-long)

Copied to clipboard

Janvijay Singh, Mukund Rungta, Diyi Yang, Saif Mohammad

Easy First Relation Extraction with Information Redundancy (D19-1)

Challenge:	a recent study examines how far back in time we tend to cite papers . citation patterns are correlated with age, age, and other factors .
Approach:	They analyze citation patterns across time and examine temporal changes . they find that 62% of cited papers are from the immediate five years prior to publication .
Outcome:	The authors show that citing papers is the primary method of scientific writing . they show that the trend has reversed and current papers have low temporal diversity .

Copied to clipboard

Shuai Ma, Gang Wang, Yansong Feng, Jinpeng Huai

Cross-Cultural Transfer Learning for Text Classification (D19-1)

Challenge:	Existing relation extraction models make decisions globally using integer linear programming . Existing approaches require time and memory to encode redundant information for ILP .
Approach:	They propose an easy first approach for relation extraction with information redundancies embedded in local sentence extractors to resolve conflict decisions with domain and uniqueness constraints.
Outcome:	The proposed approach outperforms both ILP and neural network-based methods in relation extraction (RE) studies have shown that the proposed approach improves the efficiency and accuracy of RE models.

Copied to clipboard

Dor Ringel, Gal Lavee, Ido Guy, Kira Radinsky

Text Classification

Challenge:	a large dataset is required to achieve competitive performance in most natural language tasks. large datasets are expensive, time consuming, and error-prone.
Approach:	They propose a transfer-learning framework that leverages bilingual corpora for natural language text classification using no task-specific data.
Outcome:	The proposed framework can achieve good performance on formality classification and sarcasm detection tasks without any task-specific labeled data.

Temporal Alignment of Time Sensitive Facts with Activation Engineering (2025.findings-emnlp)

Copied to clipboard

Sanjay Govindan, Maurice Pagnucco, Yang Song

StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing (2024.findings-acl)

Challenge:	Large Language Models are trained on diverse and conflicting knowledge spanning multiple domains and time periods.
Approach:	They propose a method for temporally aligning large language models to improve factual recall without training.
Outcome:	The proposed method improves factual recall without training.

Copied to clipboard

Gaoxiang Cong, Yuankai Qi, Liang Li, Amin Beheshti, Zhedong Zhang, Anton Hengel, Ming-Hsuan Yang, Chenggang Yan, Qingming Huang

Sampling Bias in Deep Active Classification: An Empirical Study (D19-1)

Challenge:	Existing methods for movie dubbing break phonemes in scripts, resulting in incomplete phoneme pronunciation and poor identity stability.
Approach:	They propose a method that switches dubbing learning from frame level to phoneme level . it uses a multimodal style adaptor to learn pronunciation style from audio .
Outcome:	The proposed method improves on two benchmarks, V2C and Grid, and is available on github.

Copied to clipboard

Ameya Prabhu, Charles Dognin, Maneesh Singh

PARSE: An Efficient Search Method for Black-box Adversarial Text Attacks (2022.coling-1)

Challenge:	Existing studies on active learning identify sampling bias in large datasets . cost and time needed for labeling and model training are bottlenecks preventing new and/or better models from being trained .
Approach:	They propose to use active learning to identify representative data samples for training . they propose to create tiny datasets that can be used for cheap training if needed .
Outcome:	The proposed model outperforms the state-of-the-art on active text classification using small representative datasets with active learning.

Copied to clipboard

Pengwei Zhan, Chao Zheng, Jing Yang, Yuxiang Wang, Liming Wang, Yang Wu, Yunjian Zhang

Semi-Supervised Reward Modeling via Iterative Self-Training (2024.findings-emnlp)

Challenge:	Neural networks are vulnerable to adversarial examples, i.e., under a black-box scenario.
Approach:	They propose a word-level search algorithm that searches for subareas under dynamic search space following the subarea importance.
Outcome:	The proposed algorithm can achieve comparable success rates to complex search methods while saving numerous queries and time.

Copied to clipboard

Yifei He, Haoxiang Wang, Ziyan Jiang, Alexandros Papangelis, Han Zhao

Adapting Unsupervised Syntactic Parsing Methodology for Discourse Dependency Parsing (2021.acl-long)

Challenge:	Reward models capture values and preferences of humans and are used in Reinforcement Learning with Human Feedback (RLHF) Traditionally, training large language models relies on extensive human-annotated preference data, which poses significant challenges in terms of scalability and cost.
Approach:	They propose a method that enhances RM training using unlabeled data.
Outcome:	The proposed approach improves reward models without incurring additional labeling costs on unlabeled datasets.

Copied to clipboard

Liwen Zhang, Ge Wang, Wenjuan Han, Kewei Tu

SHIELD: Defending Textual Neural Networks against Multiple Black-Box Adversarial Attacks with Stochastic Multi-Expert Patcher (2022.acl-long)

Challenge:	Discourse dependency parsing is a task that requires a large amount of training data, but there is little research on it.
Approach:	They propose to adapt unsupervised syntactic dependency parsing methods for unsupervised discourse dependency parses using unlabeled training data.
Outcome:	The proposed methods outperform existing methods in semi-supervised and supervised settings and outperformed existing methods.

Copied to clipboard

Thai Le, Noseong Park, Dongwon Lee

Robustness in NLP

Challenge:	Existing methods to defend textual neural network models against adversarial attacks often require retraining and retrain . e.g., BERT, RoBERTa require great time and computation resources.
Approach:	They propose an algorithm that modifies and re-trains only the last layer of a textual NN and transforms it into a stochastic weighted ensemble of multi-expert prediction heads.
Outcome:	The proposed algorithm outperforms existing models against black-box attacks by 15%–70% . the proposed algorithm is based on a novel algorithm from software engineering .

Exploring Data Augmentation Strategies for Hate Speech Detection in Roman Urdu (2022.lrec-1)

Copied to clipboard

Ubaid Azam, Hammad Rizwan, Asim Karim

EmoProgress: Cumulated Emotion Progression Analysis in Dreams and Customer Service Dialogues (2024.lrec-main)

Challenge:	a number of social media platforms are generating hateful content, a new study finds . augmentation techniques are needed to improve the performance of the models .
Approach:	They evaluate different data augmentation techniques for the improvement of hate speech detection in Roman Urdu.
Outcome:	The proposed techniques improve hate speech detection in Roman Urdu on two datasets.

Copied to clipboard

Eileen Wemmer, Sofie Labat, Roman Klinger

PyrEval: An Automated Method for Summary Content Analysis (L18-1)

Challenge:	Emotion analysis often involves categorization of isolated textual units, but these are parts of longer discourses, like dialogues or stories.
Approach:	They propose a novel annotation setup for emotion categorization corpora that allows to annotate the emotion up to the annotated sentence.
Outcome:	The proposed annotation setup allows to answer the question which emotion is presumably experienced at a specific moment in time.

Copied to clipboard

Yanjun Gao, Andrew Warner, Rebecca Passonneau

Summarization

Challenge:	PyrEval automates manual summarization evaluation of abstractive summarizing systems . extractive summaries that select complete sentences have shifted in recent years .
Approach:	They propose a method for automatic summarization evaluation that automates the manual pyramid method by using pre-trained vectors and a greedy algorithm to evaluate the pyramid content.
Outcome:	The proposed method can be applied to human and machine summaries with no retraining and in excellent time.

Denoising Large-Scale Image Captioning from Alt-text Data Using Content Selection Models (2022.coling-1)

Copied to clipboard

Khyathi Raghavi Chandu, Piyush Sharma, Soravit Changpinyo, Ashish V. Thapliyal, Radu Soricut

Privacy at Scale: Introducing the PrivaSeer Corpus of Web Privacy Policies (2021.acl-long)

Challenge:	Recent approaches to training large-scale image captioning (IC) models often fall short in terms of performance in leveraging noisy datasets in favor of clean annotations.
Approach:	They propose a technique that breaks down the task into two smaller, more controllable tasks - skeleton prediction and skelet-based caption generation.
Outcome:	The proposed method can generate better and denoised captions when using noisy datasets.

Copied to clipboard

Mukund Srinath, Shomir Wilson, C Lee Giles

A Semi-supervised Approach for De-identification of Swedish Clinical Text (2020.lrec-1)

Challenge:	Existing tools to interpret privacy policies have been used to understand them but there is a lack of large privacy policy corpora to simplify the process.
Approach:	They propose to use a corpus of 1,005,380 English language privacy policies collected from the web to create semi-supervised and unsupervised models to interpret and simplify privacy policies.
Outcome:	The proposed model outperforms all other publicly available privacy policy corpora and is ten times larger than the next largest public collection of privacy policies combined.

Copied to clipboard

Hanna Berg, Hercules Dalianis

Revisiting Over-Smoothness in Text to Speech (2022.acl-long)

Challenge:	An abundance of electronic health records (EHRs) is produced every day within healthcare.
Approach:	They propose a semi-supervised method for automatically creating high-quality training data for de-identification using annotated data for training and annotations that are costly in time and human resources.
Outcome:	The proposed method improves recall from 84.75% to 89.20% without sacrificing precision to the same extent, dropping from 95.73% to 94.20%.

Copied to clipboard

Yi Ren, Xu Tan, Tao Qin, Zhou Zhao, Tie-Yan Liu

Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation (2025.findings-emnlp)

Challenge:	Non-autoregressive text to speech models ignore correlation in time and frequency domains, causing blurry results.
Approach:	They revisit the problem of over-smoothness in non-autoregressive text to speech models . they use methods that reduce complexity of data distributions and improve modeling methods .
Outcome:	The proposed models achieve better voice quality and faster inference speed than autoregressive models.

Copied to clipboard

Zhenglin Hua, Jinghan He, Zijun Yao, Tianxu Han, Haiyun Guo, Yuheng Jia, Junfeng Fang

Arabic Dialect Identification in the Context of Bivalency and Code-Switching (L18-1)

Challenge:	Existing approaches to address hallucinations in large vision-language models require substantial computational cost and time.
Approach:	They propose to leverage sparse autoencoders to identify semantic directions closely associated with faithfulness or hallucination, extracting more precise and disentangled hallucinian-related representations.
Outcome:	The proposed method outperforms existing decoding approaches while maintaining transferability across different model architectures with negligible additional time overhead.

Copied to clipboard

Mahmoud El-Haj, Paul Rayson, Mariam Aboelezz

Code-Switching

Challenge:	Existing methods for identifying Arabic dialects require significant amounts of annotated training data which is costly and time consuming to produce.
Approach:	They propose a novel approach to Arabic dialect identification using language bivalency and written code-switching to identify Arabic dialects.
Outcome:	The proposed method can reach more than 76% and score well (66%) when tested on unseen data.

SharedCon: Implicit Hate Speech Detection using Shared Semantics (2024.findings-acl)

Copied to clipboard

Hyeseon Ahn, Youngwook Kim, Jungin Kim, Yo-Sub Han

An Automated Framework for Fast Cognate Detection and Bayesian Phylogenetic Inference in Computational Historical Linguistics (P19-1)

Challenge:	Recent studies suggest that classifying hateful posts in a binary manner may not address nuanced task of detecting implicit hate speech.
Approach:	They propose a contrastive learning approach that leverages shared semantics among data to detect implicit hate speech.
Outcome:	The proposed approach is based on a clustering-based contrastive learning approach with human-written implications or machine-generated augmented data.

Copied to clipboard

Taraka Rama, Johann-Mattis List

Challenge:	Existing methods for phylogenetic reconstruction of large datasets require time and computational power.
Approach:	They propose a workflow for phylogenetic reconstruction on large datasets using two methods . they use a method for fast detection of cognates and a Bayesian method for inference . their results show that the methods take less than a few minutes to process language families .
Outcome:	The proposed methods are fast and easy to use and close to gold standard cognate judgments and expert language family trees.

MixPAVE: Mix-Prompt Tuning for Few-shot Product Attribute Value Extraction (2023.findings-acl)

Copied to clipboard

Li Yang, Qifan Wang, Jingang Wang, Xiaojun Quan, Fuli Feng, Yu Chen, Madian Khabsa, Sinong Wang, Zenglin Xu, Dongfang Liu

Dynamic Human Evaluation for Relative Model Comparisons (2022.lrec-1)

Challenge:	Existing methods for product attribute value extraction focus on extracting values for a set of known attributes with sufficient training data.
Approach:	They propose a prompt tuning approach to extract attributes from product information using mixed prompts.
Outcome:	The proposed approach improves on two product benchmarks and shows parameter-efficient training and avoids model overfitting.

Copied to clipboard

Thórhildur Thorleiksdóttir, Cedric Renggli, Nora Hollenstein, Ce Zhang

Competence-Level Prediction and Resume & Job Description Matching Using Context-Aware Transformer Models (2020.emnlp-main)

Challenge:	Automated metrics have reported flaws when applied to measure quality aspects of generated text and have been shown to correlate poorly with human judgements.
Approach:	They propose an agent-based framework to measure the required number of human annotations when evaluating generated outputs in relative comparison settings.
Outcome:	The proposed model can be compared with a crowdsourced case study and a simulation with simulated human judgements.

Copied to clipboard

Changmao Li, Elaine Fisher, Rebecca Thomas, Steve Pittard, Vicki Hertzberg, Jinho D. Choi

Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples! (2023.findings-emnlp)

Challenge:	a new method for resume classification reduces the time and labor needed to screen applications . the current method of screening applications involves reviewing individual resumes via string/regex matching .
Approach:	They propose to use transformer-based resume classification to reduce time and labor needed to screen applications.
Outcome:	The proposed models reduce time and labor needed to screen applications while improving the selection of suitable candidates.

Copied to clipboard

Yubo Ma, Yixin Cao, Yong Hong, Aixin Sun

Figure Me Out: A Gold Standard Dataset for Metaphor Interpretation (2020.lrec-1)

Challenge:	Large Language Models have made remarkable strides in various tasks, but whether they are competitive few-shot solvers remains an open question.
Approach:	They propose an adaptive filter-then-rerank paradigm to combine the strengths of LLMs and SLMs.
Outcome:	The proposed system achieves promising improvements on various IE tasks with acceptable time and cost investment.

Copied to clipboard

Omnia Zayed, John Philip McCrae, Paul Buitelaar

Explainability & Interpretability in NLP

Challenge:	Metaphor comprehension and understanding is a complex cognitive task that requires interpreting metaphors by grasping the interaction between the meaning of their target and source concepts.
Approach:	They propose an automatic retrieval approach to annotate verb-noun metaphors in text . they validated their approach by annotating around 1,500 metaphors from tweets .
Outcome:	The proposed method reduces the workload on annotators and maintains consistency . it can be used to interpret verb-noun metaphoric expressions in tweets .

SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026.findings-acl)

Copied to clipboard

Jiaming Wang, Zhe Tang, Zehao Jin, Hefei Chen, Yilin Jin, Peng Ding, Xiaoyu Li, Xuezhi Cao

CoRRPUS: Code-based Structured Prompting for Neurosymbolic Story Understanding (2023.findings-acl)

Challenge:	Large language models (LLMs) are widely deployed as domain-specific agents, but evaluation of their capabilities in such contexts has not been fully explored.
Approach:	They propose a benchmark to evaluate LLMs' ability to follow instructions and make decisions in real-world scenarios.
Outcome:	The proposed benchmark is constructed from real-world business data and adapted into 23 complex SOP scenarios.

Copied to clipboard

Yijiang Dong, Lara Martin, Chris Callison-Burch

An Empirical Analysis of Parameter-Efficient Methods for Debiasing Pre-Trained Language Models (2023.acl-long)

Challenge:	Story generation and understanding has seen a surge in neurosymbolic work . symbolic methods are expensive and require a lot of time and expertise .
Approach:	They use Code-LLMs to bootstrap the use of symbolic methods for story understanding . they show that they can beat current LLM techniques on pre-existing stories with minimal hand engineering .
Outcome:	The proposed system beats state-of-the-art structured LLM techniques on pre-existing story understanding tasks with minimal hand engineering.

Copied to clipboard

Zhongbin Xie, Thomas Lukasiewicz

Set the Clock: Temporal Alignment of Pretrained Language Models (2024.findings-acl)

Challenge:	Pre-trained language models inherit more human-like biases from the training corpora, causing computationally expensive problems.
Approach:	They propose parameter-efficient methods in combination with counterfactual data augmentation for bias mitigation.
Outcome:	The proposed methods are effective in mitigating gender bias, prompt tuning is more suitable for GPT-2 than BERT, and less effective when it comes to racial and religious bias.

Copied to clipboard

Bowen Zhao, Zander Brumbaugh, Yizhong Wang, Hannaneh Hajishirzi, Noah Smith

Language Models as Continuous Self-Evolving Data Engineers (2025.emnlp-main)

Challenge:	Language models (LMs) are trained on web text originating from many points in time and, in general, without any explicit temporal grounding.
Approach:	They construct a time-sensitive question dataset and use it to examine temporal alignment methods to align their internal knowledge to a target time.
Outcome:	The proposed methods improve LLaMa2's performance by 62% if they are fine tuned to the year 2022 .

Copied to clipboard

Peidong Wang, Ming Wang, Zhiming Ma, Xiaocui Yang, Shi Feng, Daling Wang, Yifei Zhang, Kaisong Song

TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Models (2025.emnlp-main)

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their further evolution is often hampered by the scarcity of high-quality training data and the heavy reliance of traditional methods on expert-labeled data.
Approach:	They propose a paradigm that enables LLMs to train themselves by generating, cleaning, reviewing and annotating data with preference information.
Outcome:	The proposed model can generate, clean, review, and annotate data with preference information significantly reducing time and cost of post-training data construction.

Copied to clipboard

Asif Hanif, Maha Tufail Agro, Fahad Shamshad, Karthik Nandakumar

TIMELINE: Exhaustive Annotation of Temporal Relations Supporting the Automatic Ordering of Events in News Articles (2023.emnlp-main)

Challenge:	Recent studies have shown that ALMs are vulnerable to adversarial attacks.
Approach:	They propose a backdoor attack tailored to the prompt-learning setting in frozen audio-language models.
Outcome:	The proposed method injects backdoors solely through learnable prompts, making it highly scalable and effective in few-shot settings.

Copied to clipboard

Sarah Alsayyahi, Riza Batista-Navarro

Evaluating Parameter-Efficient Finetuning Approaches for Pre-trained Models on the Financial Domain (2023.findings-emnlp)

Challenge:	Existing temporal relation extraction models have low inter-annotator agreement due to lack of specificity of annotation guidelines . authors propose a method for annotating all temporal relations, including long-distance ones, which automates the process .
Approach:	They propose a new annotation scheme that defines criteria for temporal relations to be annotated . scheme includes events even if they are not expressed as verbs, they argue .
Outcome:	The proposed method reduces time and manual effort on the part of annotators.

Copied to clipboard

Isabella Olariu, Cedric Lothritz, Jacques Klein, Tegawendé Bissyandé, Siwen Guo, Shohreh Haddadan

Around the World in 24 Hours: Probing LLM Knowledge of Time and Place (2025.acl-long)

Challenge:	Large-scale language models with millions, billions, or trillions of trainable parameters are becoming increasingly popular.
Approach:	They compare performance of financial BERT-like models to their fully fine-tuned counterparts by using parameter-efficient tuning methods.
Outcome:	The proposed approaches match full fine-tuning performance on common NLP tasks, but are less studied in finance.

Copied to clipboard

Carolin Holtermann, Paul Röttger, Anne Lauscher

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)

Challenge:	Existing studies have tested language models' ability to reason over time and space in isolation or only in simple or artificial environments.
Approach:	They present a dataset of 320k prompts covering 289 cities in 217 countries and 37 time zones to evaluate their ability to jointly reason over time and space.
Outcome:	The proposed models perform well on reasoning tasks involving only temporal knowledge, but performance remains constrained on tasks that require connecting temporal and geographic information.

Copied to clipboard

Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang

The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead? (2024.emnlp-main)

Challenge:	Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question .
Approach:	They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance .
Outcome:	The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered .

Copied to clipboard

Alexander Choi, Syeda Sabrina Akter, J.p. Singh, Antonios Anastasopoulos

Speech Analysis of Language Varieties in Italy (2024.lrec-main)

Challenge:	Large language models have shown capabilities close to human performance in various analytical tasks.
Approach:	They investigate the efficiency and accuracy of Large Language Models in specialized tasks . they integrate LLMs with expert annotators to observe the impact of LLM suggestions .
Outcome:	The proposed model improves task completion speed but introduces anchoring bias . the proposed model is not suitable for open-ended analysis, but is capable of handling specialized tasks.

Copied to clipboard

Moreno La Quatra, Alkis Koudounas, Elena Baralis, Sabato Marco Siniscalchi

A Spatio-Temporal Point Process for Fine-Grained Modeling of Reading Behavior (2025.acl-long)

Challenge:	Recent advances in self-supervised learning provide new opportunities to analyze Italy’s linguistic varieties using speech data alone.
Approach:	They propose to automatically identify the geographic region of origin of speech samples drawn from Italy's diverse language varieties.
Outcome:	The proposed model can identify regions from speech recording and improve classification accuracy and yields embeddings that distinctly separate regional varieties.

Copied to clipboard

Francesco Ignazio Re, Andreas Opedal, Glib Manaiev, Mario Giulianelli, Ryan Cotterell

Challenge:	Standard models that focus on fixation durations ignore spatial dynamics of reading . authors propose a model that captures how long fixations last, where they land and when .
Approach:	They propose a generative model that captures how long fixations last and where they land and when they occur.
Outcome:	The proposed model exhibits higher likelihood on held-out reading data than baselines.

HORIZON: A Benchmark for In-the-wild User Behaviour Modeling (2026.findings-acl)

Copied to clipboard

Arnav Goel, Pranjal A Chitale, Bhawna Paliwal, Bishal Santra, Amit Sharma

Robustness in NLP

Challenge:	Existing user modeling benchmarks focus on short sessions and next-item prediction within a single domain.
Approach:	They propose a benchmark that reformulates user modeling along three axes . it covers 54M users and 35M items, enabling pretraining and evaluation . they propose tasks and evaluation setups that better reflect real-world deployment scenarios .
Outcome:	The proposed benchmark covers 54M users and 35M items, and is based on Amazon Reviews.

Cross-MoE: An Efficient Temporal Prediction Framework Integrating Textual Modality (2025.emnlp-main)

Copied to clipboard

Ruizheng Huang, Zhicheng Zhang, Yong Wang