ACCURACIES

“where is this relationship going?”: Understanding Relationship Trajectories in Narrative Text (2020.starsem-1)

Challenge:	Existing work on latent tree learning models shows they do not learn plausible grammars . a dataset is created to study the parsing ability of such models in natural language .
Approach:	They propose a toy dataset to study the parsing ability of latent tree learning models . they propose 'listops' toy that has a single correct parse strategy that a system needs to learn .
Outcome:	The proposed model outperforms existing models on sentence understanding tasks . it can learn grammars that conform to plausible semantics and syntactic formalisms .

Copied to clipboard

Keen You, Dan Goldwasser

Leveraging Dependency Forest for Neural Medical Relation Extraction (D19-1)

Challenge:	Existing models of human social relationships lack the syntactic and semantic signals needed to comprehend complex relationships.
Approach:	They propose two commonsense reasoning tasks to help people understand relationships . they use a dataset of 1250 stories documenting daily social interactions .
Outcome:	The proposed evaluation tasks parallel two real-life questions people frequently ponder upon as they navigate different social situations.

Copied to clipboard

Linfeng Song, Yue Zhang, Daniel Gildea, Mo Yu, Zhiguo Wang, Jinsong Su

Noise Robust Named Entity Understanding for Voice Assistants (2021.naacl-industry)

Challenge:	Existing methods for medical relation extraction use dependency syntax as a source of features.
Approach:	They propose a method to extract relational information from medical literature by using dependency forests.
Outcome:	The proposed method outperforms the standard tree-based methods in the medical domain.

Copied to clipboard

Deepak Muralidharan, Joel Ruben Antony Moniz, Sida Gao, Xiao Yang, Justine Kao, Stephen Pulman, Atish Kothari, Ray Shen, Yinying Pan, Vivek Kaul, Mubarak Seyed Ibrahim, Gang Xiang, Nan Dun, Yidan Zhou, Andy O, Yuan Zhang, Pooja Chitkara, Xuan Wang, Alkesh Patel, Kushal Tayal, Roger Zheng, Peter Grasch, Jason D Williams, Lin Li

Robustness in NLP

Challenge:	Named Entity Recognition and Entity Linking are challenging for voice assistants . utterances are relatively short, so there is not much context to help disambiguate .
Approach:	They propose a Named Entity Understanding system that combines NER and EL in a joint reranking module.
Outcome:	The proposed framework improves NER accuracy by up to 3.13% and EL accuracy by 3.6% in F1 score . it also leads to better accuracies in other natural language understanding tasks .

FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs (2025.naacl-short)

Copied to clipboard

Forrest Sheng Bao, Miaoran Li, Renyi Qu, Ge Luo, Erana Wan, Yujia Tang, Weisi Fan, Manveer Singh Tamber, Suleman Kazi, Vivek Sourabh, Mike Qi, Ruixuan Tu, Chenyu Xu, Matthew Gonzales, Ofer Mendelevitch, Amin Ahmad

Text Generation

Challenge:	Existing evaluations of hallucinations in large language models suffer from a lack of diversity and recency in the LLM and LLM families considered.
Approach:	They propose a summarization hallucination benchmark that challenges models to disagree on hallucines . they use models to generate answers or summaries from textual input .
Outcome:	The proposed model combines the best of 10 modern LLMs with ground truth annotations.

Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning (2026.eacl-long)

Copied to clipboard

Syeda Nahida Akter, Shrimai Prabhumoye, Matvei Novikov, Seungju Han, Ying Lin, Evelina Bakhturina, Eric Nyberg, Yejin Choi, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro

Learning Domain Representation for Multi-Domain Sentiment Classification (N18-1)

Challenge:	Prior work has successfully applied Reinforcement Learning (RL) to mathematical reasoning, but generalization to broader domains remains challenging due to limited data and lack of verifiable rewards for unstructured domains.
Approach:	They propose a framework that integrates multi-domain corpora into RL training to improve generalization across diverse reasoning tasks.
Outcome:	The proposed framework improves generalization across diverse reasoning tasks.

Copied to clipboard

Qi Liu, Yue Zhang, Jiangming Liu

Automatic Model Selection with Large Language Models for Reasoning (2023.findings-emnlp)

Challenge:	Training data for sentiment analysis is abundant in multiple domains, yet scarce for other domains.
Approach:	They propose to use domain-specific representations of input sentences to improve sentiment classification . they use a descriptor vector to map adversarially trained domain-general Bi-LSTM inputs into domain- specific representations .
Outcome:	The proposed model outperforms existing methods on multi-domain sentiment analysis significantly.

Copied to clipboard

James Zhao, Yuxi Xie, Kenji Kawaguchi, Junxian He, Michael Xie

Context Generation Improves Open Domain Question Answering (2023.findings-eacl)

Challenge:	Chain-of-Thought and Program-Aided Language Models offer different strengths and weaknesses.
Approach:	They propose a model selection method that uses a large language model to select between two different reasoning methods.
Outcome:	The proposed method shows significant performance improvements across eight reasoning datasets with Codex, ChatGPT, and GPT-4.

Copied to clipboard

Dan Su, Mostofa Patwary, Shrimai Prabhumoye, Peng Xu, Ryan Prenger, Mohammad Shoeybi, Pascale Fung, Anima Anandkumar, Bryan Catanzaro

Distill-C: Enhanced NL2SQL via Distilled Customization with LLMs (2025.naacl-industry)

Challenge:	Existing closed-book question answering methods do not fully exploit the parameterized knowledge.
Approach:	They propose a closed-book QA framework which uses a coarse-to-fine approach to extract the relevant knowledge and answer a question.
Outcome:	The proposed method outperforms open-book QA methods on three QA benchmarks.

Copied to clipboard

Cong Duy Vu Hoang, Gioacchino Tangari, Clemence Lanfranchi, Dalu Guo, Paul Cayet, Steve Siu, Don Dharmasiri, Yuan-Fang Li, Long Duong, Damien Hilloulin, Rhicheek Patra, Sungpack Hong, Hassan Chafi

Generalizing Unmasking for Short Texts (N19-1)

Challenge:	Domain- and customer-specific requirements complicate the problem of NL2SQL customization.
Approach:	They propose a distilled customization framework tailored for NL2SQL tasks.
Outcome:	The proposed framework outperforms teacher models on three benchmarks and achieves an average improvement of 36% in execution accuracy.

Copied to clipboard

Janek Bevendorff, Benno Stein, Matthias Hagen, Martin Potthast

Challenge:	Authorship verification is the problem of inferring whether two texts were written by the same author.
Approach:	They propose a generalized unmasking approach which allows for authorship verification of short texts with high precision at an adjustable recall tradeoff.
Outcome:	The proposed approach achieves accuracies of 75–80% while allowing for easy adjustment to forensic scenarios that require higher levels of confidence.

Teaching-Inspired Integrated Prompting Framework: A Novel Approach for Enhancing Reasoning in Large Language Models (2025.coling-industry)

Copied to clipboard

Wenting Tan, Dongxiao Chen, Jieting Xue, Zihao Wang, Taijie Chen

NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models (2025.findings-emnlp)

Challenge:	Large Language Models (LLMs) exhibit impressive performance across various domains but struggle with arithmetic reasoning tasks.
Approach:	They propose a Teaching-Inspired Integrated Prompting Framework which emulates the instructional process of a teacher guiding students.
Outcome:	The proposed framework improves reasoning accuracy on nine benchmarks.

Copied to clipboard

Chenlu Guo, Yi Chang, Yuan Wu

Fast and Accurate Deep Bidirectional Language Representations for Unsupervised Learning (2020.acl-main)

Challenge:	Parameter-efficient fine-tuning is essential for adapting large language models (LLMs). However, LoRA suffers from slow convergence and some recent LoRA variants, such as PiSSA, rely on Singular Value Decomposition (SVD) for initialization.
Approach:	They propose to introduce a small intermediate matrix between the low-rank matrices (A) and (B) and propose NyströmLoRA (NLoRA) which leverages Nyström-based initialization for SLoRA to improve its effectiveness and efficiency.
Outcome:	The proposed approach improves on 5 natural language generation tasks and 8 natural language understanding tasks with minimal parameter overhead.

Copied to clipboard

Joongbo Shin, Yoonhyung Lee, Seunghyun Yoon, Kyomin Jung

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

Challenge:	Existing deep bidirectional language models are limited by repetitive inferences on unsupervised tasks for the computation of contextual language representations.
Approach:	They propose a deep bidirectional language model called a Transformer-based Text Autoencoder (T-TA) it computes contextual language representations without repetition and shows competitive or even better accuracies than BERT .
Outcome:	The proposed model performs six times faster on a reranking task and twelve times faster in a semantic similarity task.

Copied to clipboard

Juneki Hong, Liang Huang

Real-time Factuality Assessment from Adversarial Feedback (2025.acl-long)

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

Sanxing Chen, Yukun Huang, Bhuwan Dhingra

From Phonology to Syntax: Unsupervised Linguistic Typology at Different Levels with Language Embeddings (N18-1)

Challenge:	Existing evaluations for assessing the factuality of news from conventional sources, such as claims on fact-checking websites, result in high accuracies over time for LLM-based detectors.
Approach:	They propose a pipeline that leverages natural language feedback from a RAG-based detector to iteratively modify real-time news into deceptive variants that challenge LLMs.
Outcome:	The proposed pipeline reduces the binary classification ROC-AUC by 17.5 percent for a strong RAG-based GPT-4o detector.

Copied to clipboard

Johannes Bjerva, Isabelle Augenstein

What Makes a Good Counselor? Learning to Distinguish between High-quality and Low-quality Counseling Conversations (P19-1)

Challenge:	linguistic typology is the classification of languages according to their linguistic properties.
Approach:	They learn distributed language representations which can be used to predict typological properties on a massively multilingual scale.
Outcome:	The proposed model can predict typological properties on a massively multilingual scale.

Copied to clipboard

Verónica Pérez-Rosas, Xinyi Wu, Kenneth Resnicow, Rada Mihalcea

Dialogue Systems & Conversational Agents

Challenge:	Qualitative counseling relies on active collaboration between clients and counselors .
Approach:	They propose to use linguistic features to capture differences between high- and low-quality counseling conversations to build automatic classifiers that can predict counseling quality with accuracies of up to 88%.
Outcome:	The proposed model can predict counseling quality with accuracies of up to 88%.

Self-Supervised Test-Time Learning for Reading Comprehension (2021.naacl-main)

Copied to clipboard

Pratyay Banerjee, Tejas Gokhale, Chitta Baral

Low-Resource NLP

Challenge:	Recent work on unsupervised question answering shows that models can be trained with procedurally generated question-answer pairs and achieve performance competitive with supervised methods.
Approach:	They propose a method that performs "test-time learning" on a given context . they use self-supervision to train models on synthetically generated question-answer pairs .
Outcome:	The proposed method outperforms current unsupervised methods and outperformed supervised methods.

Unbiased Math Word Problems Benchmark for Mitigating Solving Bias (2022.findings-naacl)

Copied to clipboard

Zhicheng Yang, Jinghui Qin, Jiaqi Chen, Xiaodan Liang

Numerical Reasoning

Challenge:	Existing solvers with data bias and learning bias only learn shallow heuristics rather than deep semantics for understanding problems.
Approach:	They propose a MWP dataset named UnbiasedMWP which is constructed by varying the grounded expressions in collected data and annotating them manually.
Outcome:	The proposed dataset has significantly fewer biases than its original data and other datasets, posing a promising benchmark for fairly evaluating the solvers’ reasoning skills rather than matching nearest neighbors.

Annotation and Classification of Relevant Clauses in Terms-and-Conditions Contracts (2024.lrec-main)

Copied to clipboard

Pietro Giovanni Bizzaro, Elena Della Valentina, Maurizio Napolitano, Nadia Mana, Massimo Zancanaro

Text Classification

Challenge:	Using Large Language Models (LLMs) as foundational models, we propose a new annotation scheme to classify different types of clauses in Terms-and-Conditions contracts.
Approach:	They propose to use a new annotation scheme to classify clauses in Terms-and-Conditions contracts to support legal experts in identifying and assessing problematic issues.
Outcome:	The proposed annotation scheme achieves accuracies ranging from .79 to .95 on validation tasks.

Gaussian Mixture Latent Vector Grammars (P18-1)

Copied to clipboard

Yanpeng Zhao, Liwen Zhang, Kewei Tu

Representation Learning

Challenge:	Existing models of latent variable grammars are not observable in treebanks, so latent variables are learned using expectation-maximization.
Approach:	They propose a new framework that extends latent variable grammars such that each nonterminal symbol is associated with a continuous vector space representing the set of (infinitely many) subtypes of the nonterminals.
Outcome:	The proposed framework can achieve competitive accuracies in part-of-speech tagging and constituency parsing.

JBLiMP: Japanese Benchmark of Linguistic Minimal Pairs (2023.findings-eacl)

Copied to clipboard

Taiga Someya, Yohei Oseki

Towards LLM Agents for Earth Observation (2026.findings-acl)

Challenge:	In this paper, we compare syntactic knowledge of language models across different languages.
Approach:	They introduce a dataset for targeted syntactic evaluations of language models in Japanese.
Outcome:	The proposed dataset compares the syntactic knowledge of language models across languages.

Copied to clipboard

Chia Hsiang Kao, Wenting Zhao, Cheryl Lam, Aarush Umap, Shreelekha Revankar, Samuel Speas, Snehal Bhagat, Rajeev Datta, Cheng Perng Phoo, Utkarsh Mall, Carl Vondrick, Kavita Bala, Bharath Hariharan

Challenge:	specialized automated systems for specific earth observation tasks lack flexibility for general-purpose, customized queries.
Approach:	They propose a coding benchmark of 408 yes/no questions from NASA Earth Observatory articles . they analyze the impact of using JavaScript API versus Python and the effect of providing documentation .
Outcome:	The proposed frameworks reduce errors by 60%, but are only marginally above random chance.

Sequence Shortening for Context-Aware Machine Translation (2024.findings-eacl)

Copied to clipboard

Paweł Maka, Yusuf Semerci, Jan Scholtes, Gerasimos Spanakis

Named Entity Recognition without Labelled Data: A Weak Supervision Approach (2020.acl-main)

Challenge:	Context-aware Machine Translation aims to improve translations of sentences by incorporating surrounding sentences as context.
Approach:	They propose to use latent representation of source sentence as context in a multi-encoder architecture to achieve higher accuracy on contrastive datasets.
Outcome:	The proposed architectures achieve comparable BLEU and COMET scores on contrastive datasets and comparable accuracies on the single- and multi-encoder approaches.

Copied to clipboard

Pierre Lison, Jeremy Barnes, Aliaksandr Hubin, Samia Touileb

Combining Event Semantics and Degree Semantics for Natural Language Inference (2020.coling-main)

Challenge:	Named Entity Recognition (NER) performance often degrades when applied to target domains that differ from the texts observed during training.
Approach:	They propose a method to learn NER models in the absence of labelled data through weak supervision by using a broad spectrum of labelling functions to automatically annotate texts from the target domain.
Outcome:	The proposed approach improves on two English datasets and shows that it improves by 7 percentage points on entity-level F1 scores compared to an out-of-domain neural NER model.

Copied to clipboard

Izumi Haruta, Koji Mineshima, Daisuke Bekki

Unsupervised Natural Language Inference Using PHL Triplet Generation (2022.findings-acl)

Challenge:	formal semantics has been used to account for the semantics of verb phrases and adverbial modifiers . but it is not clear whether these independent theories can be combined and extended to cases in which the phenomena in question interact.
Approach:	They propose a logic-based NLI system that combines event semantics and degree semantics.
Outcome:	The proposed system achieves high accuracies on linguistically challenging datasets . the proposed system can handle various combinations of linguistic phenomena without compromise .

Copied to clipboard

Neeraj Varshney, Pratyay Banerjee, Tejas Gokhale, Chitta Baral

Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology (P19-1)

Challenge:	In some cases, training samples may not be available or collecting them could be time-consuming and resource-intensive.
Approach:	They propose a procedural approach that leverages sentence transformations to collect PHL triplets for training NLI models.
Outcome:	The proposed model outperforms existing models on several NLI benchmarks with a set of sentence transformations.

Copied to clipboard

Ran Zmigrod, Sabrina J. Mielke, Hanna Wallach, Ryan Cotterell

Training Text-to-Text Transformers with Privacy Guarantees (2022.findings-acl)

Challenge:	Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems.
Approach:	They propose a method for converting between masculine-inflected and feminine-infflectes sentences in morphologically rich languages to reduce gender stereotyping by a factor of 2.5 without any sacrifice to grammaticality.
Outcome:	The proposed approach reduces gender stereotyping by 2.5 without any sacrifice to grammaticality.

Copied to clipboard

Natalia Ponomareva, Jasmijn Bastings, Sergei Vassilvitskii

Adaptive Learning of Local Semantic and Global Structure Representations for Text Classification (C18-1)

Challenge:	Recent advances in NLP often stem from large transformer-based pre-trained models.
Approach:	They propose differentially private (DP) training as a potential mitigation for models that can memorize parts of training data.
Outcome:	The proposed model can memorize parts of training data and mitigate memorization concerns.

Copied to clipboard

Jianyu Zhao, Zhiqiang Zhan, Qichuan Yang, Yang Zhang, Changjian Hu, Zhensheng Li, Liuxin Zhang, Zhiqiang He

Active Imitation Learning with Noisy Guidance (2020.acl-main)

Challenge:	Existing representation models for text classification learn little structure information or rely on pre-defined structures.
Approach:	They propose a sandwich neural network to learn local semantic and global structure representations without relying on parsers.
Outcome:	The proposed approach achieves competitive performance on several text classification tasks.

Copied to clipboard

Kianté Brantley, Amr Sharaf, Hal Daumé III

Low-Resource NLP

Challenge:	Structured prediction methods learn models to map inputs to complex outputs with internal dependencies.
Approach:	They propose an algorithm that mimics an expert's choice at any queried state . they apply LEAQI to three sequence labelling tasks to reduce query costs .
Outcome:	The proposed algorithm shows better accuracies over a passive approach.

Neural Combinatory Constituency Parsing (2021.findings-acl)

Copied to clipboard

Zhousi Chen, Longtu Zhang, Aizhan Imankulova, Mamoru Komachi

Dynamic Voting for Efficient Reasoning in Large Language Models (2023.findings-emnlp)

Challenge:	Existing approaches to constituency parsing are based on symbolic engineering, but they are simplified by their adaptive distributed representation.
Approach:	They propose two fast combinatory models for constituency parsing: binary and multibranching.
Outcome:	The proposed models achieve an F1 score of 92.54 on Penn Treebank, speeding at 1327.2 sents/sec.

Copied to clipboard

Mingfeng Xue, Dayiheng Liu, Wenqiang Lei, Xingzhang Ren, Baosong Yang, Jun Xie, Yidan Zhang, Dezhong Peng, Jiancheng Lv

UniGeo: Unifying Geometry Logical Reasoning via Reformulating Mathematical Expression (2022.emnlp-main)

Challenge:	Multi-path voting methods generate multiple reasoning paths for each problem, causing factual errors and illusion generation.
Approach:	They propose a multi-path voting technique that effectively reduces the number of reasoning paths during multi-path voting while preserving accuracies.
Outcome:	The proposed method outperforms Self-consistency using 24.7% of the number of paths on the LetterConcat task.

Copied to clipboard

Jiaqi Chen, Tong Li, Jinghui Qin, Pan Lu, Liang Lin, Chongyu Chen, Xiaodan Liang

Event-Driven Learning of Systematic Behaviours in Stock Markets (2020.findings-emnlp)

Challenge:	Existing work on geometry problem solving treats calculation and proving as two specific tasks hindering a deep model to unify reasoning ability on multiple math tasks.
Approach:	They propose a large-scale Unified Geometry problem benchmark to unify geometry on multiple math tasks.
Outcome:	The proposed framework outperforms the existing model with 5.6% and 3.2% accuracies on calculation and proving problems.

Copied to clipboard

Xianchao Wu

Analyzing Word Embedding Through Structural Equation Modeling (2020.lrec-1)

Challenge:	Using financial news, we can predict stock market behaviours by extracting financial events from the news and ranking the importance of the events.
Approach:	They propose to combine open information extraction and neural co-reference resolution to extract financial events from news streams and extend hierarchical attention networks that include attentions on event, news and temporal levels.
Outcome:	The proposed method achieves significantly better accuracies and higher simulated annualized returns than state-of-the-art models when being applied to predicting Standard&Poor 500, Dow Jones, Nasdaq indices and 10 individual stocks.

Copied to clipboard

Namgi Han, Katsuhiko Hayashi, Yusuke Miyao

Word Embedding Evaluation for Sinhala (2020.lrec-1)

Challenge:	Existing studies have shown that word embedding improves accuracy on NLP tasks.
Approach:	They propose a causal diagram based on the evaluation results of word embeddings using partial least squares path modeling.
Outcome:	The proposed model proves that word embedding contributes to solving downstream tasks.

Copied to clipboard

Dimuthu Lakmal, Surangika Ranathunga, Saman Peramuna, Indu Herath

Representation Learning

Challenge:	Word embeddings are a key component of the natural language processing process.
Approach:	They evaluate three standard word embedding models for Sinhala language using two evaluation methods: intrinsic evaluation and extrinsic evaluation.
Outcome:	The proposed models performed best in the three evaluation tasks, while FastText and Glove showed the lowest accuracies.

HLU: Human Vs LLM Generated Text Detection Dataset for Urdu at Multiple Granularities (2025.coling-main)

Copied to clipboard

Iqra Ali, Jesse Atuhurra, Hidetaka Kamigaito, Taro Watanabe

Text Generation

Challenge:	Using large language models (LLMs) to generate human-like text has raised concerns about misuse, especially in low-resource languages like Urdu.
Approach:	They propose a dataset that contains documents, paragraphs, and sentences . they conducted human evaluations and automated evaluations .
Outcome:	The proposed dataset shows that distinguishing between human and machine-generated text is challenging for both humans and LLMs.

Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis (2024.naacl-long)

Copied to clipboard

Nayeon Lee, Chani Jung, Junho Myung, Jiho Jin, Jose Camacho-Collados, Juho Kim, Alice Oh

A Challenge Set and Methods for Noun-Verb Ambiguity (D18-1)

Challenge:	Existing datasets for hate speech detection neglect the cultural diversity within a single language.
Approach:	They propose a CRoss-cultural English Hate* speech dataset that uses culturally hateful keywords to identify posts from four countries plus the United States.
Outcome:	The proposed dataset shows that only 56.2% of the posts in CREHate achieve consensus among all countries, with the highest pairwise label difference rate of 26%.

Copied to clipboard

Ali Elkahky, Kellie Webster, Daniel Andor, Emily Pitler

Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data (2021.findings-emnlp)

Challenge:	English part-of-speech taggers make egregious errors related to noun-verb ambiguity, despite having achieved 97%+ accuracy on the WSJ Penn Treebank since 2002.
Approach:	They propose to use a WSJ dataset to identify 30,000 examples of noun-verb ambiguity . they find that english part-of-speech taggers make egregious errors related to nouns and verbs .
Outcome:	The proposed model improves on the WSJ Penn Treebank by 14% and 52% relative to the previous model.

Copied to clipboard

Massimo Nicosia, Zhongdi Qu, Yasemin Altun

Multilinguality

Challenge:	Existing methods to improve semantic parsing performance on target languages are limited.
Approach:	They propose a Translate-and-Fill method that produces silver training data for a multilingual semantic parser.
Outcome:	The proposed method produces silver training data for a multilingual parser.

Insertion-based Tree Decoding (2021.findings-acl)

Copied to clipboard

Denis Lukovnikov, Asja Fischer

Automatic Detection of Fake News (C18-1)

Challenge:	Existing non-autoregressive decoders that are sub-linear can speed up inference for longer sequences.
Approach:	They propose a sub-linear nonautoregressive tree decoder that uses tree-based insertion operations to generate trees in sub-lines . they evaluate their approach on semantic parsing and compare it against strong baselines .
Outcome:	The proposed approach achieves competitive accuracies while reducing the number of decoding steps.

Copied to clipboard

Verónica Pérez-Rosas, Bennett Kleinberg, Alexandra Lefevre, Rada Mihalcea

Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention (2020.coling-main)

Challenge:	a growing number of fake news detection tools are needed to identify trustworthy news sources.
Approach:	They propose to use two novel datasets to automate the identification of fake news . they propose learning experiments to build accurate fake news detectors .
Outcome:	The proposed algorithms achieve accuracies of up to 76% and compare them with other tools . the proposed algorithms are based on satirical news sources and fact-checking websites .

Copied to clipboard

Philipp Dufter, Martin Schmitt, Hinrich Schütze

Conceptual Pacts for Reference Resolution Using Small, Dynamically Constructed Language Models: A Study in Puzzle Building Dialogues (2024.lrec-main)

Challenge:	SANs are an integral part of successful neural networks such as Transformer . training SAN on a task or pretraining them on language modeling requires large amounts of data and compute resources.
Approach:	They propose to modify SANs to enable faster learning, i.e., higher accuracies after fewer update steps.
Outcome:	The proposed modifications enable faster learning, i.e., higher accuracies after fewer update steps.

Copied to clipboard

Julian Hough, Sina Zarrieß, Casey Kennington, David Schlangen, Massimo Poesio

Navigating the Grey Area: How Expressions of Uncertainty and Overconfidence Affect Language Models (2023.emnlp-main)

Challenge:	Existing large language models can be fine-tuned offline but are large and resource-intensive.
Approach:	They propose to use a simple reference resolver to simulate a conceptual pact process over time with different conversation pairs.
Outcome:	The proposed model performs better than a pre-trained model with exhaustive retraining after each prediction, while being more transparent, faster and less resource-intensive.

Copied to clipboard

Kaitlyn Zhou, Dan Jurafsky, Tatsunori Hashimoto

Can Language Models Reason about Individualistic Human Values and Preferences? (2025.acl-long)

Challenge:	a recent study examines how epistemic markers of certainty, uncertainty, or evidentiality affect LMs' attitudes toward knowledge . accuracies of expressions of high certainty and low certainty are associated with questions . prior work focused on learning the mapping between internal probabilities of a model and an ordinal output .
Approach:	They develop a typology of epistemic markers and inject 50 markers into questions . they find that LMs are highly sensitive to epistemical markers in prompts .
Outcome:	The proposed model epistemology study shows that LMs are sensitive to epistemic markers in prompts . expressions of high certainty result in 7% decrease in accuracy, while factive verbs hurt performance .

Copied to clipboard

Liwei Jiang, Taylor Sorensen, Sydney Levine, Yejin Choi

Building a Task-oriented Dialog System for Languages with no Training Data: the Case for Basque (2020.lrec-1)

Challenge:	Existing methods and evaluation frameworks for achieving pluralistic alignment are limited by the diversity of people, which is pre-specified and coarsely categorized, papering over individuality.
Approach:	They propose to use a dataset transformed from the influential World Values Survey to study language models on the specific challenge of individualistic value reasoning.
Outcome:	The proposed model can predict individualistic values with accuracies between 55% and 65%, while a precise description of individualistic value judgments cannot be approximated only via demographic information.

Copied to clipboard

Maddalen López de Lacalle, Xabier Saralegi, Iñaki San Vicente

Causal Explanation Analysis on Social Media (D18-1)

Challenge:	a new approach to task-oriented dialog systems is proposed for less-resourced languages . the authors compare training data projection with direct model transfer strategies .
Approach:	They propose to project existing annotations in rich-resource languages and use NMT to project them.
Outcome:	The proposed system outperforms models trained on Basque projected data in intent classification and slot filling tasks.

Copied to clipboard

Youngseo Son, Nipun Bayas, H. Andrew Schwartz

Explainability & Interpretability in NLP

Challenge:	Understanding causal explanations is an important psychological factor linked to physical and mental health.
Approach:	They propose to automate causal explanation analysis by building on discourse parsing and using a hierarchy of Bidirectional LSTMs to identify the specific phrase that is the explanation.
Outcome:	The proposed subtasks achieve strong accuracies but differ in their approaches . the proposed sub task is compared with the previous task and is able to identify the specific phrase that is the explanation.

Contextual Inter-modal Attention for Multi-modal Sentiment Analysis (D18-1)

Copied to clipboard

Deepanway Ghosal, Md Shad Akhtar, Dushyant Chauhan, Soujanya Poria, Asif Ekbal, Pushpak Bhattacharyya

Sentiment Analysis

Challenge:	Existing methods for multi-modal sentiment analysis are limited due to the use of text, visual and acoustic inputs.
Approach:	They propose a recurrent neural network based multi-modal attention framework that leverages contextual information for utterance-level sentiment prediction.
Outcome:	The proposed framework performs better on two multi-modal sentiment analysis benchmark datasets with accuracies of 82.31% and 79.80% for the MOSI and MOSEI datasets.

The American Sign Language Knowledge Graph: Infusing ASL Models with Linguistic Knowledge (2025.findings-naacl)

Copied to clipboard

Lee Kezar, Nidhi Munikote, Zian Zeng, Zed Sehyr, Naomi Caselli, Jesse Thomason

Can You Follow Me? Testing Situational Understanding for ChatGPT (2023.emnlp-main)

Challenge:	Sign language models could make language technologies more accessible to deaf and hard-of-hearing signers, but the supply of accurately labeled data struggles to meet the demand associated with training large, end-to-end architectures.
Approach:	They construct an American Sign Language Knowledge Graph from 11 sources of linguistic knowledge and use it to train neuro-symbolic models on ASL video input tasks.
Outcome:	The proposed model achieves 91% accuracies for isolated sign recognition, 14% for predicting the semantic features of unseen signs, and 36% for classifying the topic of Youtube-ASL videos.

Copied to clipboard

Chenghao Yang, Allyson Ettinger

Dialogue Systems & Conversational Agents

Challenge:	Existing studies have identified certain SU limitations in non-chatbot Large Language models, but the extent and causes of these limitations are not well understood.
Approach:	They propose a synthetic environment for SU testing in chat-oriented models . they test models' ability to track and enumerate environment states .
Outcome:	The proposed environment allows for controlled and systematic testing of SU in chat-oriented models, and to better understand underlying causes for performance patterns.

Towards Language Agnostic Universal Representations (P19-1)

Copied to clipboard

Armen Aghajanyan, Xia Song, Saurabh Tiwary

Albanian Part-of-Speech Tagging: Gold Standard and Evaluation (L18-1)

Challenge:	Current representations in machine learning are language dependent . however, fluent bilingual speakers rarely face trouble translating a task learned in one language to another .
Approach:	They propose a method to decouple the language from the problem by learning language agnostic representations.
Outcome:	The proposed model achieves similar accuracies in a single language and in another language.

Copied to clipboard

Besim Kabashi, Thomas Proisl

Compositional Generalization for Primitive Substitutions (D19-1)

Challenge:	a corpus of more than 31,000 tokens is used for part-of-speech tagging in Albanian . a large number of multi-word units are difficult to tally, especially when they have articles or particles as their first part.
Approach:	They propose a gold standard corpus for Albanian part-of-speech tagging and perform evaluation experiments with different statistical taggers.
Outcome:	The proposed corpus can accurately represent the syntagmatic aspects of Albanian . the results show that the standard is accurate on both the full and coarse tagsets .

Copied to clipboard

Yuanpeng Li, Liang Zhao, Jianyu Wang, Joel Hestness

Universal Semantic Tagging for English and Mandarin Chinese (2021.naacl-main)

Challenge:	Existing approaches to encoding compositional generalization are lacking . et al., 2017) argue that neural networks lack compositional ability .
Approach:	They propose a method to encode compositionality in neural networks using two representations . they reduce the entropy in each representation to improve generalization .
Outcome:	The proposed approach improves performance on five NLP tasks including instruction learning and machine translation.

Copied to clipboard

Wenxi Li, Yiyang Hou, Yajie Ye, Li Liang, Weiwei Sun

MMQA: A Multi-domain Multi-lingual Question-Answering Framework for English and Hindi (L18-1)

Challenge:	Existing approaches to generating semantic annotations for different languages are attracting more and more interest.
Approach:	They propose to extend Universal Semantic Tagging to Mandarin Chinese and evaluate its performance.
Outcome:	The proposed scheme is only tested in four Indo–European languages . accuracies are 92.7% and 94.6% for Chinese and English respectively .

Copied to clipboard

Deepak Gupta, Surabhi Kumari, Asif Ekbal, Pushpak Bhattacharyya

Question Answering

Challenge:	Existing work on multi-domain, multi-lingual question answering is limited to the same language.
Approach:	They curate 500 articles in six different domains from the web and create question-answer pairs . they develop a deep learning based model for classifying an input question into coarse and finer categories .
Outcome:	The proposed model accuracies 90.12% and 80.30% for coarse and finer classes . the proposed model is the first attempt to create multi-domain, multi-lingual question answering evaluation involving English and Hindi.

ISAAQ - Mastering Textbook Questions with Pre-trained Transformers and Bottom-Up and Top-Down Attention (2020.emnlp-main)

Copied to clipboard

Jose Manuel Gomez-Perez, Raúl Ortega

Compositional Semantic Parsing across Graphbanks (P19-1)

Challenge:	Textbook Question Answering is a complex task that requires reasoning with multimodal information from text and diagrams.
Approach:	They propose to use transformer language models and bottom-up and top-down attention to tackle the language and visual understanding challenges of text and diagrams.
Outcome:	The proposed system achieves unprecedented accuracies on all TQA question types . the system also obtains state-of-the-art results in other demanding datasets .

Copied to clipboard

Matthias Lindemann, Jonas Groschwitz, Alexander Koller

The student becomes the master: Outperforming GPT3 on Scientific Factual Error Correction (2023.findings-emnlp)

Challenge:	Existing semantic parsers that map sentences to graph-based meaning representations are hand-designed for specific graphbanks.
Approach:	They propose a compositional neural semantic parser which achieves competitive accuracies across graphbanks.
Outcome:	The proposed system achieves competitive accuracies across a variety of graphbanks.

Copied to clipboard

Dhananjay Ashok, Atharva Kulkarni, Hai Pham, Barnabas Poczos

Refinement Matters: Textual Description Needs to be Refined for Zero-shot Learning (2022.findings-emnlp)

Challenge:	Existing methods for Factual Claim Correction rely on a verification model to guide the correction process.
Approach:	They propose a claim correction system that does not require a verifier but outperforms existing methods by a considerable margin.
Outcome:	The proposed system outperforms existing methods by a considerable margin on the SciFact dataset, 77% on SciFACT-Open and 72.75% on the CovidFact data set.

Copied to clipboard

Chandan Gautam, Sethupathy Parameswaran, Vinay Verma, Suresh Sundaram, Savitha Ramasamy

Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models (2025.naacl-long)

Challenge:	Zero-Shot Learning (ZSL) is a new form of learning that uses textual description and attribute to transfer knowledge from seen to unseen classes.
Approach:	They propose a non-generative gating-based attribute refinement network for ZSL that uses a circle loss-guided attribute embedder to refine the attributes.
Outcome:	The proposed approach outperforms generative methods and most generative ones in all three scenarios.

Copied to clipboard

Lovish Madaan, David Esiobu, Pontus Stenetorp, Barbara Plank, Dieuwke Hupkes

Hierarchical Modeling for User Personality Prediction: The Role of Message-Level Attention (2020.acl-main)

Challenge:	In the recent past, a popular way of evaluating natural language understanding was to consider a model’s ability to perform natural language inference (NLI) tasks.
Approach:	They focus on five different NLI benchmarks across six models of different scales and examine how their accuracies develop during training.
Outcome:	The softmax distributions of models align with human label distributions in cases where statements are ambiguous or vague.

Copied to clipboard

Veronica Lynn, Niranjan Balasubramanian, H. Andrew Schwartz

Challenge:	Language processing is increasingly finding use as a supplement for questionnaires to assess psychological attributes of consenting individuals, but most approaches neglect to consider whether all documents of an individual are equally informative.
Approach:	They propose a model that uses message-level attention to learn the relative weight of users’ social media posts for assessing their five factor personality traits.
Outcome:	The proposed model outperforms models with word-level attention and yields state-of-the-art accuracies for all five personality traits.

A Surprisingly Robust Trick for the Winograd Schema Challenge (P19-1)

Copied to clipboard

Vid Kocijan, Ana-Maria Cretu, Oana-Maria Camburu, Yordan Yordanov, Thomas Lukasiewicz

Event Representation Learning Enhanced with External Commonsense Knowledge (D19-1)

Challenge:	The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning.
Approach:	They propose to fine-tune language models on the Winograd Schema Challenge dataset WSC273 and its inference counterpart WNLI to achieve accuracies of 72.5% and 74.7%, respectively.
Outcome:	The proposed language models achieve 72.5% and 74.7% accuracy on the WSC273 and WNLI datasets, respectively.

Copied to clipboard

Xiao Ding, Kuo Liao, Ting Liu, Zhongyang Li, Junwen Duan

Representation Learning

Challenge:	Existing methods to learn event representations from text lack commonsense knowledge about the intents and emotions of event participants.
Approach:	They propose to leverage external commonsense knowledge about the intent and sentiment of the event to learn distributed representations for structured events from text.
Outcome:	The proposed model improves on hard similarity tasks and yields more precise inferences on subsequent events under given contexts.

Revisiting the Importance of Encoding Logic Rules in Sentiment Classification (D18-1)

Copied to clipboard

Kalpesh Krishna, Preethi Jyothi, Mohit Iyyer

GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation (2024.findings-acl)

Challenge:	Neural models that explicitly encode word order, syntax and semantic features are unequipped to deal with complex syntactic structures that affect sentiment, such as contrastive conjunctions.
Approach:	They propose to use contextualized ELMo embeddings instead of logic rules to compare models on syntactically complex sentences.
Outcome:	The proposed models outperform baseline models even on sentences with ambiguous sentiment labels.

Copied to clipboard

Yi Zong, Xipeng Qiu

Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations (D19-1)

Challenge:	Existing datasets focus on primary perception abilities and commonsense knowledge, or have low level of text comprehension difficulty, which are insufficient to reflect comprehensive capabilities of large vision-language models.
Approach:	They propose a multimodal benchmark based on the Chinese College Entrance Examination (GAOKAO) which sets human-level requirements for the model’s abilities, including perception, understanding, knowledge and reasoning.
Outcome:	The proposed model derives from native Chinese context and sets human-level requirements for its abilities, including perception, understanding, knowledge and reasoning.

Copied to clipboard

Christian Hadiwinoto, Hwee Tou Ng, Wee Chung Gan

Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference (2020.acl-main)

Challenge:	Contextualized word representations are effective in downstream tasks such as question answering, named entity recognition, and sentiment analysis.
Approach:	They propose to integrate pre-trained contextualized word representations into a neural network that captures the whole sentence and the word representation in the sentence.
Outcome:	The proposed approach outperforms the state-of-the-art approach that makes use of non-contextualized word embeddings on multiple benchmark WSD datasets.

Copied to clipboard

Nikita Kitaev, Dan Klein

FASTMATCH: Accelerating the Inference of BERT-based Text Matching (2020.coling-main)

Challenge:	Using custom architectures, constituency parsers are limited and require specialized hardware.
Approach:	They propose an algorithm that assigns labels to each word in a sentence in parallel and then performs a reconciliation phase to extract a tree in (empirically) linear time.
Outcome:	The proposed model achieves 95.4 F1 on the WSJ test set while also achieving substantial speedups compared to current state-of-the-art parsers with comparable accuracies.

Copied to clipboard

Shuai Pang, Jianqiang Ma, Zeyu Yan, Yang Zhang, Jianping Shen

Investigating Transformer-Guided Chaining for Interpretable Natural Logic Reasoning (2023.findings-acl)

Challenge:	Recent pre-trained language models have shown state-of-the-art accuracies in text matching.
Approach:	They propose a BERT-based text matching model where representations and interactions are decoupled . they propose generating final matching scores using a lightweight attention network .
Outcome:	Experiments show that the proposed model can achieve up to 100X speed-up to BERT and RoBERTa while keeping more up to 98.7% of the performance.

Copied to clipboard

Kanagasabai Rajaraman, Saravanan Rajamanickam, Wei Shi

A Comparative Analysis of the Effectiveness of Rare Tokens on Creative Expression using ramBERT (2023.findings-acl)

Challenge:	Natural logic reasoning has received increasing attention lately, with several datasets and neural models proposed, though with limited success.
Approach:	They propose to iteratively perform 1-step neural inferences and chain together the results to generate a multi-step reasoning trace.
Outcome:	The proposed method has high accuracies on a multi-hop First-Order Logic (FOL) reasoning benchmark.

Copied to clipboard

Youbin Lee, Deokgi Kim, Byung-Won On, Ingyu Lee

FlattenQuant: Breaking through the Inference Compute-bound for Large Language Models with Per-tensor Quantization (2024.lrec-main)

Challenge:	a pre-trained model labels an essay as creative or non-creative. a preliminary study examines the correlation between creative essays and expressiveness.
Approach:	They propose to use rare tokens to investigate correlation between creative essays and expressiveness . they propose to apply this technique to a model that automatically labels essays as creative or non-creative .
Outcome:	The proposed model improves the existing model by 14%.

Copied to clipboard

Yi Zhang, Fei Yang, Shuang Peng, Fangyu Wang, Aimin Pan

Dependency Graph Parsing as Sequence Labeling (2024.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated state-of-the-art accuracies across tasks, but their latency and GPU memory consumption limit their performance.
Approach:	They propose a method which flattens the tensor to achieve low bit per-tensori quantization with minimal accuracy loss.
Outcome:	The proposed method achieves low bit per-tensor quantization with minimal accuracy loss.

Copied to clipboard

Ana Ezquerro, David Vilares, Carlos Gómez-Rodríguez

Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge (2023.acl-long)

Challenge:	Various linearizations have been proposed to cast syntactic dependency parsing as sequence labeling, but they cannot handle reentrancy or cycles.
Approach:	They propose unbounded linearizations that can be used to cast dependency parsing as sequence labeling.
Outcome:	The proposed linearizations can cast syntactic dependency parsing as a sequence labeling task.

Copied to clipboard

Vasudha Varadarajan, Swanie Juhng, Syeda Mahwish, Xiaoran Liu, Jonah Luby, Christian Luhmann, H. Andrew Schwartz

An Iteratively Parallel Generation Method with the Pre-Filling Strategy for Document-level Event Extraction (2023.emnlp-main)

Challenge:	Active learning has been proposed to alleviate data acquisition challenges for rare-class tasks when the class label is very infrequent (e.g., 5% of samples).
Approach:	They propose to use transformers to train models on closely related tasks and evaluate acquisition strategies, including a proposed probability-of-rare-class approach to dissonance detection.
Outcome:	The proposed method improves model accuracy while iterative transfer-learning does not improve cold-start performance.

Copied to clipboard

Guanhua Huang, Runxin Xu, Ying Zeng, Jiaze Chen, Zhouwang Yang, Weinan E

MLEC-QA: A Chinese Multi-Choice Biomedical Question Answering Dataset (2021.emnlp-main)

Challenge:	Existing methods to generate event roles require a given generation order . parallel methods suffer from inadequate training and manifest zero accuracies on some event roles.
Approach:	They propose an iteratively parallel generation method with the Pre-Filling strategy to generate event roles in parallel to avoid order selection.
Outcome:	The proposed method outperforms other entity-enhanced models and achieves state-of-the-art performance on two public datasets.

Copied to clipboard

Jing Li, Shangping Zhong, Kaizhi Chen

Natural Language Interfaces

Challenge:	Question Answering (QA) is a branch of QA that enables effective perceiving, accessing, and understanding complex biomedical knowledge by innovative applications.
Approach:	They present MLEC-QA, the largest-scale Chinese multi-choice biomedical QA dataset . they implement eight representative control methods and open-domain QA methods as baselines .
Outcome:	The proposed dataset is the largest-scale Chinese multi-choice biomedical QA dataset . it covers the following biomedically-relevant sub-fields: Clinic, Stomatology, Public Health, Traditional Chinese Medicine, and Traditional Chinese medicine Combined with Western Medicine.

CoGen: Learning from Feedback with Coupled Comprehension and Generation (2024.emnlp-main)

Copied to clipboard

Mustafa Omer Gul, Yoav Artzi

Challenge:	Existing studies on coupling comprehension and generation in computational systems show that the ability to finish incomplete partner utterances in dialogue is closely related to comprehension and vice versa.
Approach:	They propose techniques to tightly integrate comprehension and generation capabilities with focus on continually learning from interaction with users.
Outcome:	The proposed models improve performance by 26% and 17% over time, while the non-coupled system is more human-like.

A Crosslingual Investigation of Conceptualization in 1335 Languages (2023.acl-long)

Copied to clipboard

Yihong Liu, Haotian Ye, Leonie Weissweiler, Philipp Wicke, Renhao Pei, Robert Zangenfeind, Hinrich Schütze

Multilinguality

Challenge:	Conceptualizer is a method that creates a bipartite directed alignment graph between source language concepts and sets of target language strings.
Approach:	They propose a method that creates a bipartite directed alignment graph between source language concepts and sets of target language strings.
Outcome:	The proposed method has good alignment accuracy across all languages and on 32 Swadesh concepts.

ESGenius: Benchmarking LLMs on Environmental, Social, and Governance (ESG) and Sustainability Knowledge (2025.emnlp-main)

Copied to clipboard

Chaoyue He, Xin Zhou, Yi Wu, Xinjia Yu, Yan Zhang, Lei Zhang, Di Wang, Shengfei Lyu, Hong Xu, Wang Xiaoqiao, Wei Liu, Chunyan Miao

Extracting Headless MWEs from Dependency Parse Trees: Parsing, Tagging, and Joint Modeling Approaches (2020.acl-main)

Challenge:	ESGenius is a comprehensive benchmark for evaluating Large Language Models on ESG and sustainability knowledge.
Approach:	They introduce ESGenius, a benchmark for evaluating and enhancing ESG proficiency . they use a rigorous two-stage evaluation protocol and a repository of foundational frameworks .
Outcome:	ESGenius is a benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in ESG and sustainability-focused question answering.

Copied to clipboard

Tianze Shi, Lillian Lee

Predicting Fine-Tuning Performance with Probing (2022.emnlp-main)

Challenge:	Headless multi-word expressions are frequent in natural language but lack internal syntactic dominance relations.
Approach:	They propose an efficient joint decoding algorithm that combines scores from both strategies.
Outcome:	The proposed algorithm combines scores from parsing and tagging for predicting flat MWEs . the proposed algorithm is more accurate than parse and more efficient for non-BERT features .

Copied to clipboard

Zining Zhu, Soroosh Shahtalebi, Frank Rudzicz

Peter Zeng, Pegah Alipoormolabashi, Jihu Mun, Gourab Dey, Nikita Soni, Niranjan Balasubramanian, Owen Rambow, H. Schwartz

Challenge:	Large-scale neural models have recently demonstrated impressive performance in language understanding tasks, typically evaluated by their fine-tuned performance.
Approach:	They propose to use probing to extract a proxy signal widely used in model development to predict fine-tuning performance.
Outcome:	The proposed method predicts fine-tuning performance with errors 40% - 80% smaller than baselines.

Copied to clipboard

Unsupervised Binary Code Translation with Application to Code Clone Detection and Vulnerability Discovery (2023.findings-emnlp)

Challenge:	Neural methods achieve high accuracy, but their representations lack direct interpretability.
Approach:	They propose a method that supplements systems using interpretable features with a neural network to improve their performance while maintaining interpretability.
Outcome:	The proposed method improves the performance of state-of-the-art models while maintaining interpretability.

Copied to clipboard

Iftakhar Ahmad, Lannan Luo

Text Generation

Challenge:	a recent study shows that binary code analysis is a key problem in software security research.
Approach:	They propose to apply Neural Machine Translation to binary code analysis . they translate a binary in a low-resource ISA and train a model on the high-resourced ISA .
Outcome:	The proposed model can be used to analyze binary code across ISAs using a high-resource ISA.

MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Language (2025.findings-emnlp)

Copied to clipboard

Seyoung Song, Seogyeong Jeong, Eunsu Kim, Jiho Jin, Dongkwan Kim, Jay Shin, Alice Oh

Dialogue Systems & Conversational Agents

Challenge:	Evaluating text generation capabilities of large language models (LLMs) is challenging, especially for low-resource languages where methods for direct assessment are scarce.
Approach:	They propose a framework that transforms existing benchmarks into conversational tasks and measures LLMs’ accuracies on those tasks.
Outcome:	The proposed framework correlates strongly with established benchmarks while enabling standardized comparisons across languages and models.

Toward Machine Interpreting: Lessons from Human Interpreting Studies (2025.emnlp-main)

Copied to clipboard

Matthias Sperber, Maureen de Seyssel, Jiajun Bao, Matthias Paulik

Multilinguality

Challenge:	Current speech translation systems are static and do not adapt to real-world situations in ways human interpreters do.
Approach:	They propose to model human interpreting using a new language model to improve usability . they argue that there is great potential to adopt many human interpreted principles .
Outcome:	The proposed models can be used to improve human interpreting and improve translation performance.

Multiple LLM Agents Debate for Equitable Cultural Alignment (2025.acl-long)

Copied to clipboard

Dayeon Ki, Rachel Rudinger, Tianyi Zhou, Marine Carpuat

Challenge:	Recent efforts focus on single-LLM, single-turn generation approaches, but it can be challenging for any single model to support all cultures equally well.
Approach:	They propose to exploit the complementary strengths of multiple LLMs to promote cultural adaptability.
Outcome:	The proposed model improves accuracy and cultural group parity over single-LLM models.

RoCoFT: Efficient Finetuning of Large Language Models with Row-Column Updates (2025.acl-long)

Copied to clipboard

Md Kowsher, Tara Esmaeilbeig, Chun-Nam Yu, Chen Chen, Mojtaba Soltanalian, Niloofar Yousefi

EquiBench: Benchmarking Large Language Models’ Reasoning about Program Semantics via Equivalence Checking (2025.emnlp-main)

Challenge:	Existing methods for fine-tuning large language models use full finetunation, but this is impractical as language models continue to scale up.
Approach:	They propose a parameter-efficient fine-tuning method for large language models based on updating only a few rows and columns of the weight matrices in transformers.
Outcome:	The proposed method gives comparable or better accuracies than state-of-the-art methods while being more memory and computation-efficient.

Copied to clipboard

Anjiang Wei, Jiannan Cao, Ran Li, Hongyu Chen, Yuhui Zhang, Ziheng Wang, Yuan Liu, Thiago S. F. X. Teixeira, Diyi Yang, Ke Wang, Alex Aiken