ABLATIONS

Examining the Utility of Self-disclosure Types for Modeling Annotators of Social Norms (2026.findings-eacl)

Challenge:	Current benchmarks do not evaluate numeracy of pretraining language models on measurements.
Approach:	They propose a new task where a model learns to reconstruct a number with its associated unit given masked text.
Outcome:	The proposed model significantly underperforms pre-trained model with baselines and ablations.

Copied to clipboard

Kieran Henderson, Kian Omoomi, Vasudha Varadarajan, Allison Lahnala, Charles Welch

Answer-based Adversarial Training for Generating Clarification Questions (N19-1)

Challenge:	Recent work has explored the use of personal information in the form of persona sentences to improve modeling of individual characteristics and prediction of annotator labels for subjective tasks.
Approach:	They categorize self-disclosures and use them to build annotator models for predicting judgments of social norms by analyzing comments from original post.
Outcome:	The proposed model improves the model and its ability to predict annotator labels.

Copied to clipboard

Sudha Rao, Hal Daumé III

Counterfactual Explanations for Natural Language Interfaces (2022.acl-short)

Challenge:	a goal of natural language processing is to develop techniques that enable machines to process naturally occurring language.
Approach:	They propose a model where hypothetical answers are latent variables that can guide the model into generating more useful clarification questions.
Outcome:	The proposed model outperforms retrieval-based models and ablations that exclude utility model and adversarial training on two datasets.

Copied to clipboard

George Tolkachev, Stephen Mell, Stephan Zdancewic, Osbert Bastani

Explainability & Interpretability in NLP

Challenge:	Semantic parsing is a promising technique for enabling natural language interfaces, but human language can encode concepts that do not exist in the underlying system or are encoded using different language.
Approach:	They propose a novel approach for generating explanations of a natural language interface based on semantic parsing by providing a user with an utterance and a demonstration of their desired goal.
Outcome:	The proposed approach significantly improves user performance and generates explanations that more closely match the user’s intent compared to two ablations.

Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement Learning (2026.acl-short)

Copied to clipboard

Zhikun Xu, Xiaodong Yu, Ben Zhou, Jiang Liu, Jialian Wu, Ze Wang, Ximeng Sun, Hao Chen, Zicheng Liu

Spurious Correlations in Cross-Topic Argument Mining (2021.starsem-1)

Challenge:	Recent large language models (LLMs) perform strongly on mathematical benchmarks but often import conclusions without validating assumptions.
Approach:	They propose a model that encodes a lemma specification and trains with reinforcement learning and section-aware loss masking to assign penalty to the section responsible for errors.
Outcome:	The proposed model performs well on benchmarks but often misapplyes lemmas . the model is able to encode the specification and train with reinforcement learning .

Copied to clipboard

Terne Sasha Thorn Jakobsen, Maria Barrett, Anders Søgaard

EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction (2022.naacl-main)

Challenge:	Recent work in cross-topic argument mining attempts to learn models that generalise across topics rather than relying on within-topic spurious correlations.
Approach:	They propose to use linear approximations of decision boundaries and manual feature grouping to learn models that generalise across topics rather than relying on within-topic spurious correlations.
Outcome:	The proposed model generalise across topics rather than relying on spurious correlations.

Copied to clipboard

Benfeng Xu, Quan Wang, Yajuan Lyu, Yabing Shi, Yong Zhu, Jie Gao, Zhendong Mao

Where Are You? Localization from Embodied Dialog (2020.emnlp-main)

Challenge:	Existing studies only explore entity representations, but propose a novel triple perspective for relation extraction.
Approach:	They propose to explicitly introduce relation representation and jointly represent it with entities to identify valid triples.
Outcome:	The proposed method is based on ablations and document-level relation extraction and joint entity and relation extraction.

Copied to clipboard

Meera Hahn, Jacob Krantz, Dhruv Batra, Devi Parikh, James Rehg, Stefan Lee, Peter Anderson

Compositional Zero-Shot Domain Transfer with Text-to-Text Models (2023.tacl-1)

Challenge:	Observer and Locator perform a cooperative localization task in a 3D environment.
Approach:	They propose a dataset of 6k dialogs in which two humans complete a cooperative localization task.
Outcome:	The proposed model achieves 32.7% success at identifying the Observer’s location within 3m in unseen buildings, vs. 70.4% for human Locators.

Copied to clipboard

Fangyu Liu, Qianchu Liu, Shruthi Bannur, Fernando Pérez-García, Naoto Usuyama, Sheng Zhang, Tristan Naumann, Aditya Nori, Hoifung Poon, Javier Alvarez-Valle, Ozan Oktay, Stephanie L. Hyland

OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering (2022.naacl-main)

Challenge:	Existing approaches to zero-shot domain transfer are limited by domain gap and lack of in-domain labels.
Approach:	They propose a compositional transfer learning framework (DoT51) that learns domain knowledge and task knowledge in a multi-task manner without access to in-domain labels.
Outcome:	The proposed framework outperforms the current state-of-the-art in zero-shot domain transfer by over 7 absolute points in accuracy on RadNLI.

Copied to clipboard

Zhengbao Jiang, Yi Mao, Pengcheng He, Graham Neubig, Weizhu Chen

Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training (2022.findings-naacl)

Challenge:	a table-based question answering system requires complex reasoning and alignment between questions and tables.
Approach:	They propose a table-based QA model that consumes both natural and synthetic data . they combine retrieval with masking to pair natural sentences with QA .
Outcome:	The proposed model outperforms existing models in few-shot and full settings and on WikiTableQuestions.

Copied to clipboard

Yifan Gao, Qingyu Yin, Zheng Li, Rui Meng, Tong Zhao, Bing Yin, Irwin King, Michael Lyu

Hierarchical Reason-of-Contact Detection in Retail Banking Customer Interactions via LLM-Driven Taxonomy Induction (2026.acl-industry)

Challenge:	Existing studies on keyphrase generation on non-English languages haven’t been vastly investigated.
Approach:	They propose a retrieval-augmented method for multilingual keyphrase generation that leverages keyphrase annotations in English datasets to facilitate generating keyphrases in low-resource languages.
Outcome:	The proposed model outperforms baselines on non-English keyphrase generation datasets and the proposed model is scalable.

Copied to clipboard

Yoages Kumar Mantri, Yagneswaran Sriraja, John Hartley, Greig A Cowan, Raad Khraishi, Abhinav Gupta

Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning (2024.findings-emnlp)

Challenge:	Existing approaches to define customer intents or contact reasons are fragmented and manual . existing systems fail to capture the linguistic diversity of thousands of daily callers .
Approach:	They propose a framework that develops a hierarchical Reason-of-Contact taxonomy . it covers hundreds of business processes and can be deployed in real time .
Outcome:	The proposed framework achieves 10% improvement in F1 score over baseline approaches on a reference dataset.

Copied to clipboard

Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Kumar Dubey, Alexandre Rame, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Leonard Hussenot, Olivier Bachem, Edouard Leurent

The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification (2023.eacl-main)

Challenge:	Existing approaches for multi-objective Reinforcement Learning (RL) are difficult due to plurality of preferences and applications.
Approach:	They propose a framework for finetuning language models on multiple objectives using conditional language policy.
Outcome:	The proposed framework outperforms and Pareto-dominates existing approaches for multi-objective Reinforcement Learning (RL) it does not require training or maintaining multiple models to achieve different trade-offs between the objectives.

Copied to clipboard

Mohsen Mesgar, Thy Thy Tran, Goran Glavaš, Iryna Gurevych

Improving Generative Visual Dialog by Answering Diverse Questions (D19-1)

Challenge:	Recent methods for task-oriented dialog (ToD) intent classification use pretrained language models . but lack of informative ablations prevents identification of factors that drive performance .
Approach:	They propose a framework to evaluate components of Few-Shot Intent Classification . they propose to combine cross-encoder architecture and episodic meta-learning .
Outcome:	The proposed framework evaluates cross-encoder architecture and episodic meta-learning . it also shows that splitting episodes into support and query sets outperforms non-episodic counterparts.

Copied to clipboard

Vishvak Murahari, Prithvijit Chattopadhyay, Dhruv Batra, Devi Parikh, Abhishek Das

Visually Grounded Continual Learning of Compositional Phrases (2020.emnlp-main)

Challenge:	Prior work on training generative Visual Dialog models with reinforcement learning has shown that this improvement saturates and starts degrading after a few rounds of interaction, and does not lead to a better Visual Dialog model.
Approach:	They propose a Q-Bot-A-Bot image-guessing game that allows Q-BOT to ask diverse questions, thus reducing repetitions and enabling A-BOTT to explore a larger state space during RL.
Outcome:	The proposed approach improves Q-Bot-A-Bot image-guessing performance but degrades after a few rounds of interaction and does not lead to a better Visual Dialog model.

Copied to clipboard

Xisen Jin, Junyi Du, Arka Sadhu, Ram Nevatia, Xiang Ren

SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning (2026.findings-eacl)

Challenge:	Modern NLP systems rely on offline training and are inefficient for new tasks.
Approach:	They propose a visually grounded ContinuaL learning task which simulates the continual acquisition of compositional phrases from streaming visual scenes.
Outcome:	The proposed system improves on existing systems, but it's infeasible to store all possible compositions.

Copied to clipboard

Kaiwen Zhou, Ahmed Elgohary, A S M Iftekhar, Amin Saied

WangchanThaiInstruct: An instruction-following Dataset for Culture-Aware, Multitask, and Multi-domain Evaluation in Thai (2025.emnlp-main)

Challenge:	Existing red-teaming frameworks do not cover all the risks associated with arbitrary black-box LLMs.
Approach:	They propose a generic red-teaming framework for arbitrary black-box LLM agents that iteratively constructs and refines model-based adversarial attacks based on the execution trajectories of former attempts.
Outcome:	The proposed model improves attack success rate by 100%, surpassing the 671B Deepseek-R1 model.

Copied to clipboard

Peerat Limkonchotiwat, Pume Tuchinda, Lalita Lowphansirikul, Surapon Nonesung, Panuthep Tasawong, Alham Fikri Aji, Can Udomcharoenchaikit, Sarana Nutanong

Machine Translation

Challenge:	Existing benchmarks for large language models rely on translations, missing cultural and domain specificity.
Approach:	They present a human-authored dataset for evaluation and instruction tuning in Thai . findings highlight need for culturally and professionally grounded instruction data .
Outcome:	a human-authored dataset for evaluation and instruction tuning in Thai outperforms translation-based models . findings highlight need for culturally and professionally grounded instruction data .

Large Language Models Can Solve Real-World Planning Rigorously with Formal Verification Tools (2025.naacl-long)

Copied to clipboard

Yilun Hao, Yongchao Chen, Yang Zhang, Chuchu Fan

Continual and Multi-Task Architecture Search (P19-1)

Challenge:	Large Language Models (LLMs) struggle to generate correct plans for multi-constraint planning problems . a recent study showed that large language models have significant potential in solving planning problems.
Approach:	They propose an LLM-based planning framework that formalizes and solves multi-constraint planning problems as constrained satisfiability problems.
Outcome:	The proposed framework achieves a success rate of 93.9% and is effective with diverse paraphrased prompts.

Copied to clipboard

Ramakanth Pasunuru, Mohit Bansal

Show Your Work with Confidence: Confidence Bands for Tuning Curves (2024.naacl-long)

Challenge:	Recent studies have shown that architecture search can improve performance on language modeling and image classification tasks with reasonable training speed.
Approach:	They propose a continual architecture search approach that continually evolves the model parameters during sequential training of several tasks without losing performance on previously learned tasks.
Outcome:	The proposed approach improves language modeling and image classification with reasonable training speed and a weight-sharing strategy.

Copied to clipboard

Nicholas Lourie, Kyunghyun Cho, He He

Challenge:	a rush to scale up has left us with large, costly language models and little understanding of how different designs compare.
Approach:	They propose a method to construct valid confidence bands for tuning curves . they validated their method with ablations and analyze the effect of sample size .
Outcome:	The proposed method shows that bootstrap confidence bands do not approximate their target confidence.

KoBLEX: Open Legal Question Answering with Multi-hop Reasoning (2025.emnlp-main)

Copied to clipboard

Jihyung Lee, Daehui Kim, Seonjeong Hwang, Hyounghun Kim, Gary Lee

Question Answering

Challenge:	Large Language Models (LLMs) have demonstrated remarkable performances in general domains and are now extending into the expert domain of law.
Approach:	They propose a Korean Benchmark for Legal EXplainable QA (KoBLEX) that evaluates provision-grounded, multi-hop legal reasoning.
Outcome:	The proposed method outperforms baselines and shows a high correlation with human judgments.

FBS: Modeling Native Parallel Reading inside a Transformer (2026.findings-acl)

Copied to clipboard

Tongxi Wang

Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication (2020.coling-main)

Challenge:	Existing acceleration methods largely patch the autoregressive pipeline and miss core human-reading ingredients.
Approach:	They propose a trainable loop that injects a causal loop into Transformers via a 'parafoveal' approach.
Outcome:	The proposed model improves quality-efficiency trade-off without increasing parameters . ablations show the three modules are complementary .

Copied to clipboard

Ruize Wang, Zhongyu Wei, Ying Cheng, Piji Li, Haijun Shan, Ji Zhang, Qi Zhang, Xuanjing Huang

On-the-fly Definition Augmentation of LLMs for Biomedical NER (2024.naacl-long)

Challenge:	Existing methods for visual storytelling construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content.
Approach:	They propose a topic description task to detect the global semantic context of an image stream and a story is then constructed with the guidance of the topic description.
Outcome:	The proposed framework can generate stories with higher quality compared to state-of-the-art methods on a VIST dataset.

Copied to clipboard

Monica Munnangi, Sergey Feldman, Byron Wallace, Silvio Amir, Tom Hope, Aakanksha Naik

Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Models (2024.findings-emnlp)

Challenge:	Despite their general capabilities, LLMs struggle on biomedicalNER tasks due to specialized terminology and lack of training data.
Approach:	They propose a new knowledge augmentation approach which incorporates definitions of relevant concepts on-the-fly.
Outcome:	The proposed approach improves performance on biomedicalNER tasks by 15% (on average) The proposed method outperforms fine-tuned language models in few-shot settings.

Copied to clipboard

Songtao Jiang, Tuo Zheng, Yan Zhang, Yeying Jin, Li Yuan, Zuozhu Liu

Decomposition-Enhanced Training for Post-Hoc Attributions in Language Models (2026.eacl-long)

Challenge:	Recent advances in multimodal large language models have seen remarkable progress for medical decision-making, however, they are designated for specific classification or generative tasks and require model training or finetuning on large-scale datasets with sizeable parameters and tremendous computing.
Approach:	They propose a framework that tackles discriminative and generative multimodal medical tasks using multimodal alignment, instruction tuning and routing.
Outcome:	The proposed model can achieve superior performance to or on par with state-of-the-art baselines while only requiring 30%-50% of activated model parameters.

Copied to clipboard

Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami, Ryan A. Rossi, Varun Manjunatha, Roshan Santhosh, Ruiyi Zhang, Soheil Feizi, Nedim Lipka

The Power of Scale for Parameter-Efficient Prompt Tuning (2021.emnlp-main)

Challenge:	Existing methods for extractive QA struggle in multi-hop, abstractive, and semi-extractive settings.
Approach:	They propose a method that prompts models to produce answer decompositions as intermediate reasoning steps.
Outcome:	The proposed method outperforms existing methods and matches or exceeds state-of-the-art frontier models.

Copied to clipboard

Brian Lester, Rami Al-Rfou, Noah Constant

ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation (2021.findings-acl)

Challenge:	Unlike discrete text prompts used by GPT-3, soft prompts are learned through backpropagation and can be tuned to incorporate signals from any number of labeled examples.
Approach:	They propose a mechanism for learning "soft prompts" to condition frozen language models to perform specific downstream tasks.
Outcome:	The proposed method outperforms fewshot learning using GPT-3 and matches the quality of model tuning as models exceed billions of parameters.

Copied to clipboard

Kaushal Kumar Maurya, Maunendra Sankar Desarkar, Yoshinobu Kano, Kumari Deepshikha

FENAS: Flexible and Expressive Neural Architecture Search (2020.findings-emnlp)

Challenge:	Recent advances in NLP focus on large annotated training data.
Approach:	They propose an unsupervised framework that does not use parallel or pseudo-parallel/back-translated data.
Outcome:	The proposed framework does not use parallel or pseudo-parallel/back-translated data.

Copied to clipboard

Ramakanth Pasunuru, Mohit Bansal

Limits of Theory of Mind Modelling in Dialogue-Based Collaborative Plan Acquisition (2024.acl-long)

Challenge:	Recent approaches to architecture search have shown good improvements in terms of performance with reasonable training speed.
Approach:	They propose an algorithm with more activation functions, input edges, and atomic operations to search for architectures that are optimal for given task.
Outcome:	The proposed algorithm reproduces well-known LSTM and GRU architectures and initializes with them for finding architectures more efficiently.

Copied to clipboard

Matteo Bortoletto, Constantin Ruhdorfer, Adnen Abdessaied, Lei Shi, Andreas Bulling

Dialogue Systems & Conversational Agents

Challenge:	Recent work on dialogue-based collaborative plan acquisition (CPA) suggests Theory of Mind (ToM) modelling can improve missing knowledge prediction in settings with asymmetric skill-sets and knowledge.
Approach:	They propose to use task-specific constraints to represent plans as graphs and exploit task-related constraints to improve missing knowledge prediction in CPA.
Outcome:	The proposed model improves missing knowledge prediction in contexts with asymmetric skill-sets and knowledge, but the improvements diminish . the proposed model is compared with baseline models and found to be more effective than existing models.

Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning (2021.emnlp-main)

Copied to clipboard

Weijiang Yu, Yingpeng Wen, Fudan Zheng, Nong Xiao

Randomized Smoothing with Masked Inference for Adversarially Robust Text Classifications (2023.acl-long)

Challenge:	Existing algorithms for math word problems only capture word-level relationship and ignore to build hierarchical reasoning like the human being.
Approach:	They propose a Reasoning with Pre-trained Knowledge and Hierarchical Structure network that uses outside knowledge to build hierarchical reasoning like the human being.
Outcome:	The proposed method outperforms state-of-the-art methods on two large-scale datasets and boosts performance.

Copied to clipboard

Han Cheol Moon, Shafiq Joty, Ruochen Zhao, Megh Thakkar, Chi Xu

TAN-NTM: Topic Attention Networks for Neural Topic Modeling (2021.acl-long)

Challenge:	Large-scale pre-trained language models are brittle against specifically crafted adversarial examples, leading to increasing interest in probing the adversariality of NLP systems.
Approach:	They propose a two-stage framework that combines randomized smoothing and masked inference to improve the adversarial robustness of NLP systems.
Outcome:	The proposed framework improves adversarial robustness by 2 to 3 times over existing state-of-the-art methods on benchmark datasets.

Copied to clipboard

Madhur Panwar, Shashank Shailabh, Milan Aggarwal, Balaji Krishnamurthy

Glider: Global and Local Instruction-Driven Expert Router (2025.emnlp-main)

Challenge:	Topic models have been widely used to learn text representations and gain insight into document corpora.
Approach:	They propose a framework which processes document as a sequence of tokens through a LSTM whose contextual outputs are attended in a topic-aware manner.
Outcome:	The proposed model improves on two downstream tasks: document classification and topic guided keyphrase generation.

Copied to clipboard

Pingzhi Li, Prateek Yadav, Jaehong Yoon, Jie Peng, Yi-Lin Sung, Mohit Bansal, Tianlong Chen

Natural Language Video Localization with Learnable Moment Proposals (2021.emnlp-main)

Challenge:	Existing methods for routing-based expert models favor generalization over performance on held-in tasks.
Approach:	They propose a global and local instruction driven expert router that leverages recent LLMs' semantic reasoning capabilities to generate task-specific instructions from the input query.
Outcome:	The proposed method improves held-in performance while maintaining strong generalization on held-out tasks.

Copied to clipboard

Shaoning Xiao, Long Chen, Jian Shao, Yueting Zhuang, Jun Xiao

Teaching Small Language Models Reasoning through Counterfactual Distillation (2024.emnlp-main)

Challenge:	Existing methods for video moment localization have poor performance due to predefined rules.
Approach:	They propose a model with a fixed set of learnable moment proposals with 'border-aware loss' they propose to localize the video moment corresponding to the query by locating the start and end timestamps in an untrimmed video.
Outcome:	The proposed model outperforms state-of-the-art models on two challenging benchmarks.

Copied to clipboard

Tao Feng, Yicheng Li, Li Chenglin, Hao Chen, Fei Yu, Yin Zhang

Investigating Mysteries of CoT-Augmented Distillation (2024.emnlp-main)

Challenge:	Large language models (LLMs) have demonstrated remarkable performance in a wide range of downstream tasks.
Approach:	They propose a counterfactual distillation framework that leverages LLMs to generate high-quality counterfacts and utilizes multi-view CoT to enhance the diversity of reasoning samples.
Outcome:	The proposed framework enhances reasoning capabilities of large language models and is more robust to OOD data.

Copied to clipboard

Somin Wadhwa, Silvio Amir, Byron Wallace

M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)

Challenge:	Recent studies show that eliciting chain of thought rationales from a large "teacher" model in addition to target labels yields (often substantial) improvements in model distillation.
Approach:	They ask: Why and how does this additional training signal help in model distillation?
Outcome:	The proposed method improves model performance on question answering tasks by eliciting CoT rationales from a student model in addition to target labels.

Copied to clipboard

Zhaopeng Feng, Jiayuan Su, Jiamei Zheng, Jiahan Ren, Yan Zhang, Jian Wu, Hongwei Wang, Zuozhu Liu

Machine Translation

Challenge:	Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments.
Approach:	They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment.
Outcome:	The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini.

Learning from Natural Language Explanations for Generalizable Entity Matching (2024.emnlp-main)

Copied to clipboard

Somin Wadhwa, Adit Krishnan, Runhui Wang, Byron Wallace, Luyang Kong

AutoSeM: Automatic Task Selection and Mixing in Multi-Task Learning (N19-1)

Challenge:	Entity matching is the task of linking records from different sources that refer to the same real-world entity.
Approach:	They propose to "distill" LLM reasoning into smaller entity matching models via natural language explanations.
Outcome:	The proposed model distillation approach achieves strong performance on out-of-domain generalization tests (10.85% F-1).

Copied to clipboard

Han Guo, Ramakanth Pasunuru, Mohit Bansal

An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text (2023.findings-acl)

Challenge:	Multi-task learning is an inductive transfer mechanism that leverages information from related tasks to improve the primary model's generalization performance.
Approach:	They propose a multitask learning pipeline that finds relevant auxiliary tasks and learns their mixing ratio.
Outcome:	The proposed model can find relevant auxiliary tasks and learn their mixing ratio . the proposed model achieves significant performance boosts on several primary tasks .

Copied to clipboard

Yova Kementchedjhieva, Ilias Chalkidis

Noisy Channel Language Model Prompting for Few-Shot Text Classification (2022.acl-long)

Challenge:	Standard methods for multi-label text classification rely on encoder-only pre-trained models . encoder decoder models have proven more effective in other classification tasks .
Approach:	They compare four methods for multi-label classification based on encoder-only models . they use a pre-trained model for multilabel text classification .
Outcome:	The proposed methods outperform encoder-only methods on complex datasets and labeling schemes.

Copied to clipboard

Sewon Min, Mike Lewis, Hannaneh Hajishirzi, Luke Zettlemoyer

Event-Keyed Summarization (2024.findings-emnlp)

Challenge:	Prior work has suggested methods for finding better prompt or scoring of the output from the model.
Approach:	They propose a noisy channel approach for language model prompting in few-shot text classification by in-context demonstration or prompt tuning.
Outcome:	The proposed model outperforms direct models in both demonstration and prompt tuning.

Copied to clipboard

William Gantt, Alexander Martin, Pavlo Kuchmiichuk, Aaron White

S2ynRE: Two-stage Self-training with Synthetic data for Low-resource Relation Extraction (2023.acl-long)

Challenge:	a novel task combines document-level event extraction with event-keyed summarization . a recent study has shown that traditional summarizing produces inferior summaries of target events .
Approach:	They propose a task that marries traditional summarization and document-level event extraction with the goal of generating a contextualized summary for a specific event, given a document and an extracted event structure.
Outcome:	The proposed task combines document-level event extraction with event-keyed summarization . the authors show that the proposed task is robust and humane .

Copied to clipboard

Benfeng Xu, Quan Wang, Yajuan Lyu, Dai Dai, Yongdong Zhang, Zhendong Mao

ReSee: Responding through Seeing Fine-grained Visual Knowledge in Open-domain Dialogue (2023.emnlp-main)

Challenge:	Existing methods for relation extraction suffer from the inadequacy of large-scale annotated data.
Approach:	They propose a framework for two-stage self-training with synthetic data for relation extraction .
Outcome:	The proposed framework is based on two-stage self-training with synthetic data . it is able to synthesize large quantities of training data and iteratively and alternately learn from synthetic and golden data together.

Copied to clipboard

Haoqin Tu, Yitong Li, Fei Mi, Zhongliang Yang

Simple and Effective Curriculum Pointer-Generator Networks for Reading Comprehension over Long Narratives (P19-1)

Challenge:	Existing multimodal dialogue systems are limited by the scale and quality of available datasets or the coarse concept of visual knowledge.
Approach:	They propose to explicitly split visual knowledge into finer granularity and turn-level . they propose a framework to add visual representation into vanilla dialogue models .
Outcome:	The proposed framework outperforms state-of-the-art methods on automatic and human evaluations.

Copied to clipboard

Yi Tay, Shuohang Wang, Anh Tuan Luu, Jie Fu, Minh C. Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, Aston Zhang

Machine Reading Comprehension

Challenge:	Using a pointer-generator framework for reading/sampling over large documents, we propose a framework for learning over long narratives where documents easily span over thousands of tokens.
Approach:	They propose a curriculum learning (CL) based pointer-generator framework for reading/sampling over large documents, enabling diverse training of the neural model based on the notion of alternating contextual difficulty.
Outcome:	The proposed framework improves on the NarrativeQA reading comprehension benchmark and reaches state-of-the-art performance.

Efficient and Accurate Contextual Re-Ranking for Knowledge Graph Question Answering (2024.lrec-main)

Copied to clipboard

Kexuan Sun, Nicolaas Paul Jedema, Karishma Sharma, Ruben Janssen, Jay Pujara, Pedro Szekely, Alessandro Moschitti

Question Answering

Challenge:	Existing approaches to QA over textual data are based on a "retrieve-then-generate" pipeline.
Approach:	They propose a "triple-level" labeling strategy that infers fine-grained labels and trains a re-ranker to improve relevance of retrieved triples.
Outcome:	The proposed pipeline improves on prior KGQA systems by 5.56% Exact Match.

SCDE: Sentence Cloze Dataset with High Quality Distractors From Examinations (2020.acl-main)

Copied to clipboard

Xiang Kong, Varun Gangal, Eduard Hovy

Challenge:	Experimental results show that there is a significant performance gap between advanced models (72%) and humans (87%) Cloze datasets are convenient either to be generated automatically or by annotators.
Approach:	They propose to use a dataset to evaluate the performance of computational models through sentence prediction.
Outcome:	The proposed model fills up multiple blanks in a passage from a shared candidate set with distractors designed by English teachers.

Provably Safe Offline-to-Online RL: Decoupling Learning from Data-Driven Safety Enforcement (2026.acl-long)

Copied to clipboard

Kaitong Cai, Jusheng Zhang, Keze Wang

Reasoning Gets Harder for LLMs Inside A Dialogue (2026.acl-long)

Challenge:	Hybrid offline–online reinforcement learning (O2O RL) promises both sample efficiency and robust exploration, but suffers from instability due to distribution shift between offline and online data.
Approach:	They propose a framework that decouples policy optimization from safety enforcement . they propose dynamic curricula that gradually extend temporal horizons and anneal offline–online data mixing .
Outcome:	The proposed framework preserves the exploratory value of online interactions without collapsing to conservative policies.

Copied to clipboard

Ivan Kartáč, Mateusz Lango, Ondrej Dusek

Dialogue Systems & Conversational Agents

Challenge:	Large Language Models (LLMs) achieve strong performance on many reasoning benchmarks, yet these evaluations typically focus on isolated tasks that differ from real-world usage in task-oriented dialogue (TOD).
Approach:	They propose to use a dynamic benchmark to examine how framing reasoning tasks within task-oriented dialogue (TOD) affect LLM performance.
Outcome:	The proposed model performs well on isolated tasks and in task-oriented dialogues, but performance is inconsistent between them.

Model-tuning Via Prompts Makes NLP Models Adversarially Robust (2023.emnlp-main)

Copied to clipboard

Mrigank Raman, Pratyush Maini, J Kolter, Zachary Lipton, Danish Pruthi

Data, Data Everywhere: A Guide for Pretraining Dataset Construction (2024.emnlp-main)

Challenge:	Pre-trained models are typically adapted to downstream tasks by appending a randomly initialized multilayer perceptron to their topmost representation layer and fine-tuning the entire model on a downstream task.
Approach:	They propose to append a multilayer perceptron to a CLS token and fine-tune the entire model on a downstream task.
Outcome:	The proposed model-tuning via prompts outperforms adversarial training-based state-of-art defenses by 3.5% and improves against adversarials by 8% over standard methods.

Copied to clipboard

Jupinder Parmar, Shrimai Prabhumoye, Joseph Jennings, Bo Liu, Aastha Jhunjhunwala, Zhilin Wang, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro

PowerTransformer: Unsupervised Controllable Revision for Biased Language Correction (2020.emnlp-main)

Challenge:	Recent language models have impressive capabilities on a number of evaluation areas.
Approach:	They conduct systematic analysis of pretraining set construction to identify which methods yield the greatest gains in model accuracy.
Outcome:	The proposed method can be used to refine and improve a pretraining set.

Copied to clipboard

Xinyao Ma, Maarten Sap, Hannah Rashkin, Yejin Choi

Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models (2025.emnlp-main)

Challenge:	Unconscious biases continue to be prevalent in modern text and media, calling for algorithms that can assist writers with bias correction.
Approach:	They propose a new revision task that debiases text through the lens of connotation frames to correct implicit biases in character portrayals.
Outcome:	The proposed approach outperforms existing methods and ablations in the literature.

Copied to clipboard

Lijia Lv, Yuanshu Zhao, Guan Wang, Xuehai Tang, Wen Jie, Jizhong Han, Songlin Hu

Combo of Thinking and Observing for Outside-Knowledge VQA (2023.acl-long)

Challenge:	Large language models (LLMs) are widely deployed as zero-shot evaluators for answer grading, content moderation, and document ranking.
Approach:	They propose a system that trains LLMs with adapters to denoise embeddings and refocus attention.
Outcome:	The proposed model lifts adversarial accuracy from 5% to 95% a 90 percentage-point gain while reducing clean-data accuracy by just 8 percentage points.

Copied to clipboard

Qingyi Si, Yuchen Mo, Zheng Lin, Huishan Ji, Weiping Wang

Weakly-Supervised Temporal Article Grounding (2022.emnlp-main)

Challenge:	Existing approaches to visual question answering use external knowledge to acquire and use knowledge beyond images.
Approach:	They propose to constrain the cross-modality space into the same space of natural-language space . they propose a multimodal encoder, textual encoder and answer decoder to introduce more types of knowledge .
Outcome:	The proposed framework outperforms the state-of-the-art by 6.17% accuracy on a cross-modal space and natural-language space.

Copied to clipboard

Long Chen, Yulei Niu, Brian Chen, Xudong Lin, Guangxing Han, Christopher Thomas, Hammad Ayyubi, Heng Ji, Shih-Fu Chang

Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-the-fly (2025.findings-emnlp)

Challenge:	Existing VG models make unrealistic assumptions about how to ground video segments . a recent study has shown that video grounding can be useful for downstream applications .
Approach:	They propose a new task: Weakly-Supervised temporal Article Grounding (WSAG) given an article and a relevant video, WSAG aims to localize all "groundable" sentences to the video.
Outcome:	The proposed method is simple but effective, and it can be used in real-world applications.

Copied to clipboard

Lance Ying, Ryan Truong, Katherine M. Collins, Cedegao E. Zhang, Megan Wei, Tyler BrookeWilson, Tan Zhi-Xuan, Lionel Wong, Joshua B. Tenenbaum

Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress? (2024.emnlp-main)

Challenge:	Language is a powerful source of information in social settings, especially in novel situations where language can provide both abstract information about the environment dynamics and concrete specifics about an agent that cannot be easily visually observed.
Approach:	They propose a language-informed rational agent synthesis framework that integrates linguistic and visual inputs to draw context-specific social inferences.
Outcome:	The proposed framework outperforms ablations and state-of-the-art models on a range of social reasoning tasks derived from cognitive science experiments.

Copied to clipboard

Daniel Jeong, Saurabh Garg, Zachary Lipton, Michael Oberst

Agentic Rubrics as Contextual Verifiers for SWE Agents (2026.acl-long)

Challenge:	Several studies claim that domain-adaptive pretraining improves performance on downstream medical tasks.
Approach:	They compare medical LLMs and VLMs against their corresponding base models . they find that medical Lms outperform their base models in 12.1% of cases .
Outcome:	The proposed models outperform their base models on medical questions and tasks in 12.1% of cases and reach a tie in 49.8% of cases.

Copied to clipboard

Mohit Raghavendra, Anisha Gunjal, Bing Liu, Yunzhong He

Challenge:	Large Language Models (LLMs) have rapidly advanced on coding tasks, enabling increasingly capable software engineering agents for real-time code editing and bug fixing.
Approach:	They propose to use a rubric checklist to create a context-grounded rubric for SWE agents.
Outcome:	The proposed rubrics achieve a score of 54.2% on Qwen3-Coder-30B-A3B and 40.6% on Qween3-332B .

Atomic Self-Consistency for Better Long Form Generations (2024.emnlp-main)

Copied to clipboard

Raghuveer Thirukovalluru, Yukun Huang, Bhuwan Dhingra

Challenge:	Recent work has aimed to improve LLM generations by filtering out hallucinations, thereby improving the accuracy of the information in responses.
Approach:	They propose a technique that improves the recall of relevant information in an LLM.
Outcome:	The proposed technique improves the recall of relevant information in an LLM.

Temporal Contrastive Decoding: A Training-Free Method for Large Audio-Language Models (2026.findings-acl)

Copied to clipboard

Yanda Li, Yuhan Liu, Zirui Song, Yunchao Wei, Martin Takáč, Salem Lahlou

Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale Tuning (2025.acl-long)

Challenge:	Large audio-language models (LALMs) can exhibit a temporal smoothing bias . unified decoders can produce less specific audio-grounded outputs .
Approach:	They propose a temporally blurred slow-path view that is re-encoded by a token-level logit update.
Outcome:	Experiments on MMAU and AIR-Bench show consistent improvements on strong unified LALMs.

Copied to clipboard

Sohan Patnaik, Milan Aggarwal, Sumit Bhatia, Balaji Krishnamurthy

ProtoCycle: Reflective Tool-Augmented Planning for Text-Guided Protein Design (2026.findings-acl)

Challenge:	Prior studies have demonstrated that LLMs generate step-by-step rationales, but limited data is available to improve their performance in commercial settings due to copyright and legal issues.
Approach:	They propose a trainable framework that tunes a (small) LLM to generate outputs from a pool of diverse rationales that selectively improves the downstream task.
Outcome:	The proposed framework outperforms several trainable and prompting baselines on maths problem solving, natural language inference, and commonsense reasoning.

Copied to clipboard

Yutang Ge, Guojiang Zhao, Sihang Li, Zheng Cheng, Zifeng Zhao, Hanchen Xia, Guolin Ke, Linfeng Zhang, Zhifeng Gao, Yu Guang Wang

Challenge:	Recent deep generative models have already shown encouraging * Equal contribution.
Approach:	They propose to use generic instruction-tuned LLMs as direct text-to-sequence generators to achieve this goal.
Outcome:	Recent studies show that reflection improves sequence quality and alignment while maintaining competitive foldability.

Large Language Models Are Reasoning Teachers (2023.acl-long)

Copied to clipboard

Namgyu Ho, Laura Schmid, Se-Young Yun

ACING: Actor-Critic for Instruction Learning in Black-Box LLMs (2025.emnlp-main)

Challenge:	Recent studies have shown that chain-of-thought (CoT) prompting can elicit language models to solve complex reasoning tasks step-by-step.
Approach:	They propose a method that uses large model samples as reasoning teachers to fine-tune smaller models.
Outcome:	The proposed method outperforms prompt-based methods and the teacher model in many tasks and extends it by leveraging the teacher's ability to generate multiple rationales for each original sample.

Copied to clipboard

Salma Kharrat, Fares Fourati, Marco Canini

LatentRefusal: Latent-Signal Refusal for Unanswerable Text-to-SQL Queries (2026.findings-acl)

Challenge:	Large Language Models (LLMs) have impressive capabilities across tasks like classification, summarization, and reasoning.
Approach:	They propose an actor-critic reinforcement learning framework that formulates instruction optimization as a stateless, continuous-action problem.
Outcome:	The proposed framework outperforms human-written prompts in 76% of instruction-induction tasks with gains of 33 points and 10-point improvement over baseline.

Copied to clipboard

Xuancheng Ren, Shijing Hu, Zhihui Lu, Jiangqi Huang, Qiang Duan

Programming Languages in NLP

Challenge:	Existing refusal strategies for unanswerable and underspecified user queries are brittle due to model hallucinations or add complexity and overhead.
Approach:	They propose a latent-signal refusal mechanism that predicts query answerability from hidden activations of an LLM.
Outcome:	The proposed scheme reduces schema noise and sparse, localized question–schema mismatch cues that indicate unanswerability.

s1: Simple test-time scaling (2025.emnlp-main)

Copied to clipboard

Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candes, Tatsunori Hashimoto

Video-Text Prompting for Weakly Supervised Spatio-Temporal Video Grounding (2024.emnlp-main)

Challenge:	OpenAI’s o1 model showed this capability but did not publicly share its methodology, leading to many replication efforts.
Approach:	They curate a small dataset s1K with 1,000 reasoning questions based on three criteria we validate through ablations: difficulty, diversity, and quality.
Outcome:	The proposed model exceeds o1-preview on competition math questions by up to 27% (MATH and AIME24).

Copied to clipboard

Heng Zhao, Zhao Yinjie, Bihan Wen, Yew-Soon Ong, Joey Zhou

MASSIVE-Agents: A Benchmark for Multilingual Function-Calling in 52 Languages (2025.findings-emnlp)

Challenge:	Existing methods extract each candidate tube feature independently by cropping objects from video frame feature, discarding all contextual information such as position change and inter-entity relationship.
Approach:	They propose to use video-text prompts to construct candidate feature instead of cropping tube region from feature map . they also propose negative contrastive samples whose candidate object is erased instead of being highlighted .
Outcome:	The proposed methods surpass existing weakly-supervised methods by a great margin . they draw visual markers over objects tubes as video prompts .

Copied to clipboard

Mayank Kulkarni, Vittorio Mazzia, Judith Gaspers, Chris Hench, Jack FitzGerald

A Unified Feature Mixture Framework for Joint Speech and Singing Deepfake Detection (2026.findings-acl)

Challenge:	Using the original dataset, we cleaned up the MASSIVE dataset and reformatted it for evaluation within the Berkeley Function-Calling Leaderboard framework.
Approach:	They present a new benchmark for assessing multilingual function calling across 52 languages . they clean the original MASSIVE dataset and reformat it for evaluation .
Outcome:	The new benchmark covers 55 functions and 286 arguments in 52 languages.

Copied to clipboard

Aastha Sharma, Guangjing Wang

Speech & Audio in NLP

Challenge:	Existing methods for deepfake detection fail under speech-to-singing domain shift . a speech-retentive multi-domain fine-tuning strategy enables adaptation to singing .
Approach:	They propose a unified deepfake detector based on a multi-branch mixture-of-experts architecture that integrates three complementary feature views.
Outcome:	The proposed detector achieves 1.82% EER on CtrSVDD, compared to 37–62% for existing detectors . it can generalize to unseen generators and preserve strong speech performance .

From Knowing to Teaching: Scaffolding Pedagogical Decisions for LLM Agent (2026.acl-long)

Copied to clipboard

Yucheng Wang, Shen Yang, Jifan Yu, Haoxuan Li, Joy Jia Yin Lim, Daniel Zhang-Li, Huiqin Liu, Lei Hou, Juanzi Li, Bin Xu

Why Are We Moral? An LLM-based Agent Simulation Approach to the Study of Moral Evolution (2026.acl-long)

Challenge:	Large language models produce content lacking pedagogical depth when asked to generate lessons .
Approach:	They propose a framework that allows teachers to select content according to pedagogical intent and sequence topics so foundations precede applications.
Outcome:	The framework achieves 67.8% win rate in human evaluation and 79.6% in LLM-based evaluation against eight baselines.

Copied to clipboard

Zhou Ziheng, Huacong Tang, Mingjie Bi, Wanying He, Fang Sun, Yizhou Sun, Ying Nian Wu, Demetri Terzopoulos, Yipeng Kang, Fangwei Zhong

Linguistics & Cognitive NLP

Challenge:	Existing models of moral evolution must abstract away cognitive processes . et al. (2017): evolution of morality presents a puzzle: natural selection favors selfish .
Approach:	They propose an LLM-based agent simulation framework that manipulates cognitive factors to understand moral evolution.
Outcome:	The proposed model exploits cognitive realism to explore moral evolution in a hunter-gatherer society.

DeepSpecs: Expert-Level Question Answering in 5G (2026.findings-acl)

Copied to clipboard

Aman Ganapathy Manvattira, Yifei Xu, Ziyue Dang, Songwu Lu

Translation with Thought: Difficulty-Adaptive Reasoning via Reinforcement Learning for Multi-Domain Machine Translation (2026.acl-long)

Challenge:	3GPP standards define the technical design and implementation of 5G systems . expert-level questions require navigating thousands of pages of cross-referenced standards .
Approach:	They propose a standard-native retrieval-augmented generation system that can answer 5G questions . they use SpecDB, ChangeDB, TDocDB and a metadata-rich retrieval system to do this .
Outcome:	The proposed solution outperforms base models and state-of-the-art RAG systems in QA datasets . expert-level queries require navigating thousands of pages of cross-referenced standards .

Copied to clipboard

Yongshi Ye, Biao Fu, Chongxuan Huang, Yidong Chen, Xiaodong Shi

Machine Translation

Challenge:	Multi-domain machine translation (MDMT) is a unique challenge due to varying levels of linguistic complexity across domains.
Approach:	They propose a resource-rational framework that learns to modulate inference between intuitive and deliberate reasoning.
Outcome:	Evaluated on 15 benchmarks spanning in-domain and out-of-domain settings, as well as 3 seen and 59 unseen languages, with ablations across three backbone models, TwT-7B and Twt-14B outperform much larger SOTA reasoning models in translation quality, while reducing token usage by 32–60%.

MTA: Multi-Granular Trajectory Alignment for Large Language Model Distillation (2026.acl-long)

Copied to clipboard

Pham Khanh Chi, Quoc Phong Dao, Thuat Nguyen, Linh Ngo Van, Trung Le, Thanh Hong Nguyen

PRInTS: Reward Modeling for Long-Horizon Information Seeking (2026.acl-long)

Challenge:	Existing methods for reducing the computational cost of large language models (LLMs) focus on minimizing the divergence between the output probability distributions of the teacher and the student, which limits knowledge transfer.
Approach:	They propose a framework that aligns teacher and student representations along their layer-wise transformation trajectory.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on teacher–student layers.

Copied to clipboard

Jaewoo Lee, Archiki Prasad, Justin Chen, Zaid Khan, Elias Stengel-Eskin, Mohit Bansal

Audit Me If You Can: Query-Efficient Active Fairness Auditing of Black-Box LLMs (2026.findings-acl)

Challenge:	Existing PRMs cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs.
Approach:	They propose a generative PRM trained with dual capabilities that compresses the growing context while preserving essential information for step evaluation.
Outcome:	PRInTS improves on FRAMES, GAIA, and WebWalkerQA models while preserving essential information for step evaluation.

Copied to clipboard

David Hartmann, Lena Pohlmann, Lelia Hanslik, Noah Gießing, Bettina Berendt, Pieter Delobelle

The Role of Mixed-Language Documents for Multilingual Large Language Model Pretraining (2026.acl-long)

Challenge:	Large Language Models exhibit systematic biases across demographic groups.
Approach:	They propose to use auditing as uncertainty estimation over a fairness metric . they propose to introduce the Bounded Active Fairness Auditor for query-efficient auditing .
Outcome:	The proposed auditing tool reduces query access costs and improves performance over time.

Copied to clipboard

Jiandong Shao, Raphael Tang, Crystina Zhang, Karin Sevegnani, Pontus Stenetorp, Jianfei Yang, Yao Lu

Multilinguality

Challenge:	Existing research suggests that multilingual large language models can achieve impressive cross-lingual understanding despite largely monolingual pretraining.
Approach:	They compare a monolingual-only corpus with a standard web corpus that removes all multilingual documents and then retrain the models from scratch under controlled conditions.
Outcome:	The results show that removing bilingual data causes translation performance to drop 56% in BLEU, whereas code-switching contributes minimally.

Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement (2026.findings-acl)

Copied to clipboard

Daeun Lee, Jaehong Yoon, Jaemin Cho, Mohit Bansal

Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation (2026.findings-acl)

Challenge:	Recent text-to-video models struggle to faith-fully follow text prompts, authors say . authors propose a new refinement framework that detects fine-grained misalignments .
Approach:	They propose a video refinement framework that detects fine-grained misalignments . they propose preserving regions that should be preserved rather than regenerated .
Outcome:	The proposed framework detects fine-grained misalignments and performs targeted corrections . it preserves correctly generated entities, segments regions across frames, and regenerates problematic regions .

Copied to clipboard

Srujan P Mule, Aniketh Garikaparthi, Manasi Patwardhan

LLMs are Brittle to Simple Code Transformations: Introducing CETBench – A Benchmark for Code-Equivalence Checking (2026.findings-acl)

Challenge:	Language models are accelerating scientific research by automating hypothesis generation and implementation.
Approach:	They ask whether LMs can forecast the empirical success of research ideas before experiments . they frame evaluation as a reasoning task via Reinforcement Learning with Verifiable Rewards .
Outcome:	The proposed model outperforms off-the-shelf models in 77.1% of the evaluations . the model outpersforms GPT-5 in the evaluation of 11,488 idea pairs .

Copied to clipboard

Neeva Oza, Ishaan Govil, Parul Gupta, Dinesh Khandelwal, Dinesh Garg, Parag Singla

Programming Languages in NLP

Challenge:	a new benchmarking tool for code equivalence checks the performance of LLMs.
Approach:	They propose a code-equivalence with transformations benchmark built from a repository of programs that may solve the same or different tasks.
Outcome:	The proposed approach boosts performance on the transformed pairs of programs.

Combining Distantly Supervised Models with In Context Learning for Monolingual and Cross-Lingual Relation Extraction (2026.acl-long)

Copied to clipboard

Vipul Kumar Rathore, Malik Hammad Faisal, Parag Singla, null Mausam

MUTANT: A Recipe for Multilingual Tokenizer Design (2026.acl-long)

Challenge:	Existing Distantly Supervised Relation Extraction models rely on task-specific training, but their integration with in-context learning (ICL) using large language models (LLMs) remains underexplored.
Approach:	They propose a framework for distantly supervised relation extraction that uses a trained DSRE model to identify the top-k candidate relations for a given test sentence and a dynamic exemplar retrieval strategy that extracts reliable, sentence-level exemplars from training data.
Outcome:	The proposed framework achieves 20 F1 points gains in English and 17 F1 point gains on Indic languages over previous models and naive prompting baselines.

Copied to clipboard

Souvik Rana, Ashish Kulkarni, Arul Menezes, Chandra Khatri, Shubham Agarwal

Syntactic Text Processing

Challenge:	Subword tokenization schemes such as Byte Pair Encoding (BPE) are widely adopted, but their effectiveness in multilingual settings remains understudied.
Approach:	They propose a multilingual tokenizer that produces linguistically coherent tokens for multilingual LLMs.
Outcome:	The proposed tokenizer improves fertility score by 39.5% over LLaMA4 and 18% over Sutra.

From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning (2026.findings-acl)

Copied to clipboard

Beining Wu, Fuyou Mao, Jiong Lin, Cheng Yang, Jiaxuan Lu, Yifu Guo, Siyu Zhang, Yifan Wu, Ying Huang, Fu Li

Challenge:	Generative engines (GEs) are replacing ranked links with citation-grounded answers . current methods are unable to accumulate or transfer effective strategies across tasks and engines .
Approach:	They propose a multi-agent framework where planning, editing, and fidelity-aware evaluation serve as the execution layer.
Outcome:	The proposed framework outperforms heuristic baselines in visibility and citation fidelity on three mainstream engines.

Fin-STAR: Structure-as-Semantics to Resolve Implicitness in Financial Retrieval (2026.findings-acl)

Copied to clipboard

Yu Zou, Yan Chen, Lida He, Qi Zhou, Xiaorui Zhou, Aixi Zhong, Yi Wang, Wei Li, Qingyu Wang, Jiatao Li, Wei Gong, Jialei Zeng, Jingmei Zhao, Ke Jiang, Qing Li

Adaptive Instruction Composition for Automated LLM Red-Teaming (2026.acl-long)

Challenge:	Existing Retrieval-Augmented Generation systems treat structure as a physical navigational skeleton rather than intrinsic semantic knowledge.
Approach:	They propose a framework that redefining hierarchy as intrinsic semantics and uses snippets to enrich hierarchical lineage.
Outcome:	The proposed framework outperforms state-of-the-art hierarchical and graph-based benchmarks on FinTierQA Gold.

Copied to clipboard

Jesse Zymet, Andy Luo, Swapnil Shinde, Sahil Wadhwa, Emily Chen