AUTOMATIC GENERATION

Assistive Recipe Editing through Critiquing (2023.eacl-main)

Challenge:	Recent studies have demonstrated that LLMs are highly sensitive to small, meaning-preserving variations in task formulation.
Approach:	They propose a framework that enables the automatic generation of various prompts.
Outcome:	The proposed framework provides meaningful variations to support strong evaluation practices.

Copied to clipboard

Diego Antognini, Shuyang Li, Boi Faltings, Julian McAuley

Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts (2026.tacl-1)

Challenge:	Existing methods for generating recipes that satisfy dietary restrictions are inconsistent or incoherent and paired datasets are not available at scale.
Approach:	They propose to build a hierarchical denoising auto-encoder that edits recipes given ingredient-level critiques by interacting with the predicted ingredients.
Outcome:	The proposed model can more effectively edit recipes compared to strong language models and iteratively rewrites recipes to satisfy user feedback.

Copied to clipboard

Hanhua Hong, Chenghao Xiao, Yang Wang, Yiqi Liu, Wenge Rong, Chenghua Lin

LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory (2022.acl-short)

Challenge:	Evaluating natural language generation systems is challenging due to the diversity of valid outputs.
Approach:	They propose an inversion learning method that learns effective reverse mappings from model outputs back to their input instructions.
Outcome:	The proposed method requires only a single evaluation sample and eliminates manual prompt engineering.

Copied to clipboard

Eunhwan Park, Donghyeon Jeon, Seonhoon Kim, Inho Kang, Seung-Hoon Na

Semantic Text Processing

Challenge:	LM-BFF (CITATION) achieves significant few-shot performance by using auto-generated prompts and adding demonstrations similar to an input example.
Approach:	They propose to use auto-generated prompts and add demonstrations to LM-BFF to improve few-shot fine-tuning of language models with multiple soft demonstrations.
Outcome:	The proposed method improves few-shot fine-tuning on eight NLP tasks.

EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models (2025.emnlp-demos)

Copied to clipboard

Ziwen Xu, Shuxun Wang, Kewei Xu, Haoming Xu, Mengru Wang, Xinle Deng, Yunzhi Yao, Guozhou Zheng, Huajun Chen, Ningyu Zhang

Generating Vehicular Icon Descriptions and Indications Using Large Vision-Language Models (2024.emnlp-industry)

Challenge:	Large Language Models (LLMs) have demonstrated extraordinary capabilities, however, they may still generate unreliable or unsafe outputs.
Approach:	They propose a framework that allows plug-and-play adjustability for controlling Large Language Model (LLM) behaviors.
Outcome:	The framework is designed to enable plug-and-play adjustability for controlling Large Language Model (LLM) behaviors.

Copied to clipboard

James Fletcher, Nicholas Dehnen, Seyed Nima Tayarani Bathaie, Aijun An, Heidar Davoudi, Ron DiCarlantonio, Gary Farmaner

Towards Continuous Dialogue Corpus Creation: writing to corpus and generating from it (L18-1)

Challenge:	Existing image description systems are trained mainly on natural images, whereas icon images are drawings.
Approach:	They propose to use a dataset to generate both visual and functional icon descriptions based on the icon image and its context information in the car manual.
Outcome:	The proposed model performs well on the dashboard icon description task while the third model perform poorly.

Copied to clipboard

Andrei Malchanau, Volha Petukhova, Harry Bunt

Self-Contained Utterance Description Corpus for Japanese Dialog (2022.lrec-1)

Challenge:	Existing methods to create dialogue corpora annotated with interoperable semantic information are based on ISO standard data models and tools.
Approach:	They propose to use a corpus as a shared repository for analysis and modelling of interactive dialogue behaviour and for implementation, integration and evaluation of dialogue system components.
Outcome:	The proposed method is applied to the design of two multimodal interactive applications - the Virtual Negotiation Coach and the Virtual Debate Coach.

Copied to clipboard

Yuta Hayashibe

SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Models (2025.emnlp-main)

Challenge:	Existing task frameworks for dialog-act classification and slot filling can only interpret utterances using pre-defined types and slots.
Approach:	They propose a task to describe the intent of an utterance in a dialog with multiple simple natural sentences without the context.
Outcome:	The proposed task can describe the intent of an utterance in a dialog with multiple simple natural sentences without the context.

Copied to clipboard

Tong Bao, Mir Tafseer Nayeem, Davood Rafiei, Chengzhi Zhang

Be a Multitude to Itself: A Prompt Evolution Framework for Red Teaming (2024.findings-emnlp)

Challenge:	Automated survey generation is a key task in scientific document processing due to lack of standardized evaluation datasets.
Approach:	They propose a survey-based framework that integrates quality indicators into literature retrieval to assess higher-quality sources.
Outcome:	The proposed framework enhances the standard Retrieval-Augmented Generation pipeline and enables human-guided writing.

Copied to clipboard

Rui Li, Peiyi Wang, Jingyuan Ma, Di Zhang, Lei Sha, Zhifang Sui

The StatCan Dialogue Dataset: Retrieving Data Tables through Conversations with Genuine Intents (2023.eacl-main)

Challenge:	Large Language Models (LLMs) have gained increasing attention for their capacity to generate harmful content.
Approach:	They propose a scalable evolution framework to evolve red teaming prompts across breadth and depth dimensions, facilitating automatic generation of numerous high-quality and diverse red team prompts.
Outcome:	The proposed framework surpasses existing red teaming methods on attack success rate and diversity.

Copied to clipboard

Xing Han Lu, Siva Reddy, Harm de Vries

Cross-modal Contrastive Attention Model for Medical Report Generation (2022.coling-1)

Challenge:	StatCan Dialogue Dataset consists of 19,379 conversation turns between agents and online users . researchers propose two tasks to help knowledge workers find relevant tables for live chat users based on real-world intents .
Approach:	They propose two tasks based on 19,379 conversation turns between agents and online users . they investigate the difficulty of each task by establishing strong baselines .
Outcome:	The proposed task is based on a dataset of 19,379 conversation turns . the researchers show that the models struggle to generalize to future conversations .

Copied to clipboard

Xiao Song, Xiaodan Zhang, Junzhong Ji, Ying Liu, Pengxu Wei

On the Automatic Generation and Simplification of Children’s Stories (2023.emnlp-main)

Challenge:	Existing methods for medical report generation are unable to capture useful information from historical cases.
Approach:	They propose a model that captures both visual and semantic information from similar cases.
Outcome:	The proposed model outperforms the state-of-the-art models on almost all metrics on IU X-Ray and MIMIC-CXR benchmarks.

Copied to clipboard

Maria Valentini, Jennifer Weber, Jesus Salcido, Téa Wright, Eliana Colunga, Katharina von der Wense

Text Generation

Challenge:	Recent advances in large language models (LLMs) have made it possible to generate children's educational texts with appropriate lexical and readability levels.
Approach:	They first examine the ability of several popular LLMs to generate stories with properly adjusted lexical and readability levels.
Outcome:	The proposed models can generalize to the domain of children's stories and create an efficient pipeline for their automatic generation.

One Comment from One Perspective: An Effective Strategy for Enhancing Automatic Music Comment (2020.coling-main)

Copied to clipboard

Tengfei Huo, Zhiqiang Liu, Jinchao Zhang, Jie Zhou

ChainLM: Empowering Large Language Models with Improved Chain-of-Thought Prompting (2024.lrec-main)

Challenge:	Existing methods for automatic comment generation generate common and meaningless comments for music.
Approach:	They propose a multi-perspective strategy to enhance automatic music comment generation by combining different perspectives on a music comment dataset.
Outcome:	The proposed model outperforms state-of-the-art models on two music comment datasets and outperformed existing models by a substantial margin.

Copied to clipboard

Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation (2022.findings-emnlp)

Challenge:	Existing CoT synthesis approaches focus on simpler reasoning tasks and result in inconsistent CoT prompts.
Approach:	They propose a framework for automatic generation of superior CoT prompts based on three major evolution strategies . they propose 'step-level debating' method where multiple debaters discuss each reasoning step to arrive at the correct answer.
Outcome:	The proposed framework can generate superior CoT prompts from a CoT dataset.

Copied to clipboard

Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Fei Mi, Yasheng Wang, Lifeng Shang, Minlie Huang

arXiv2Table: Toward Realistic Benchmarking and Evaluation for LLM-Based Literature-Review Table Generation (2026.acl-long)

Challenge:	Existing methods to detect toxic generation of pretrained language models rely on templates, data extraction, crowdsourcing workers or automatic generation.
Approach:	They propose a method to construct adversarial contexts conditioned on a given response . they augment existing dataset BAD+ and construct a new dataset B AD+ .
Outcome:	The proposed method can detect toxic or biased content in large pretrained language models.

Copied to clipboard

Weiqi Wang, Jiefu Ou, Yangqiu Song, Benjamin Van Durme, Daniel Khashabi

Generation of a Spanish Artificial Collocation Error Corpus (L18-1)

Challenge:	Literature review tables are essential for summarizing and comparing collections of scientific papers.
Approach:	They propose to generate a database of literature review tables from a pool of papers and to model retrieval noise via semantically related but out-of-scope distractor papers verified by human annotators.
Outcome:	The proposed method improves over strong baselines while the absolute scores remain modest, underscoring the task’s difficulty.

Copied to clipboard

Sara Rodríguez-Fernández, Roberto Carlini, Leo Wanner

Syntactic Text Processing

Challenge:	collocations are combinations of two elements where one (the base) is freely chosen, despite the limitations of the other (collocate) current tools for collocation error detection and correction focus on collocation validation and identification of miscollocations .
Approach:	They propose an algorithm for automatic generation of an artificial collocation error corpus of american English learners of Spanish that includes 17 different types of collocation errors.
Outcome:	The proposed algorithm can detect and classify collocation errors in learners' writings . collocation error detection and correction has not received the attention it deserves .

PAP2PAT: Benchmarking Outline-Guided Long-Text Patent Generation with Patent-Paper Pairs (2025.findings-acl)

Copied to clipboard

Valentin Knappich, Anna Hätty, Simon Razniewski, Annemarie Friedrich

Challenge:	In patents, the description constitutes more than 90% of the document on average, yet its automatic generation remains understudied.
Approach:	They propose a method to generate patent documents using a research paper as an invention specification.
Outcome:	The proposed model can generate 1.8k patent-paper pairs describing the same inventions, but it's difficult to provide the level of detail required.

Multi-Figurative Language Generation (2022.coling-1)

Copied to clipboard

Huiyuan Lai, Malvina Nissim

Generation of Patient After-Visit Summaries to Support Physicians (2022.coling-1)

Challenge:	Figurative language generation is the task of reformulating a given text in the desired figure of speech while still being faithful to the original context.
Approach:	They propose a scheme for multi-figurative language pre-training on top of BART and a mechanism for injecting the target figurative information into the encoder to generate text with the target figure from another figurativ form without parallel figura-figura pairs.
Outcome:	The proposed model outperforms all baselines and qualitatively examines the relationship between the different figures of speech.

Copied to clipboard

Pengshan Cai, Fei Liu, Adarsha Bajracharya, Joe Sills, Alok Kapoor, Weisong Liu, Dan Berlowitz, David Levy, Richeek Pradhan, Hong Yu

Challenge:	After-visit summary is a summary note given to patients after their clinical visit.
Approach:	They propose to automate the generation of after-visit summaries and introduce a feedback mechanism that alerts physicians when an automatic summary fails to capture important details of the clinical notes.
Outcome:	The proposed system improves on a large clinical dataset that contains electronic health record (EHR) notes and their associated summaries.

Evaluating Implicit Biases in LLM Reasoning through Logic Grid Puzzles (2026.findings-acl)

Copied to clipboard

Fatima Jahara, Mark Dredze, Sharon Levy

A Symbolic Adversarial Learning Framework for Evolving Fake News Generation and Detection (2025.emnlp-main)

Challenge:	Existing methods to eliminate implicit biases in LLMs do not eradicate underlying behavioral bias.
Approach:	They propose a framework that uses logic grid puzzles to probe the influence of social stereotypes on logical reasoning and decision making in LLMs.
Outcome:	The proposed framework systematically probes the influence of social stereotypes on logical reasoning and decision making in LLMs.

Copied to clipboard

Chong Tian, Qirong Ho, Xiuying Chen

Interpretable Multimodal Misinformation Detection with Logic Reasoning (2023.findings-acl)

Challenge:	Rapid LLM advancements heighten fake news risks by enabling the automatic generation of increasingly sophisticated misinformation.
Approach:	They propose a framework that implements an adversarial training paradigm by an agent symbolic learning optimization process rather than numerical updates.
Outcome:	The proposed framework generates sophisticated fake news that degrades state-of-the-art detection performance by 53.4% in Chinese and 34.2% in English on average.

Copied to clipboard

Hui Liu, Wenya Wang, Haoliang Li

Improve LLM-as-a-Judge Ability as a General Ability (2025.emnlp-main)

Challenge:	Existing methods for misinformation detection lack interpretability due to the black-box nature of the neural network.
Approach:	They propose a logic-based neural model which integrates interpretable logic clauses to express the reasoning process of the target task.
Outcome:	The proposed model can be generalizable across multiple misinformation sources and is based on three public datasets.

Copied to clipboard

Jiachen Yu, Shaoning Sun, Xiaohui Hu, Jiaxu Yan, Kaidong Yu, Xuelong Li

Challenge:	Recent studies focus on generative judges, but only on their judge ability.
Approach:	They propose a method that leverages the generative and reasoning capabilities of large language models to evaluate LLM responses across diverse scenarios, providing accurate preference signals.
Outcome:	The proposed model performs on RewardBench with only 2% to 40% of the data required by other training frameworks.

Evaluating the Knowledge Dependency of Questions (2022.emnlp-main)

Copied to clipboard

Hyeongdon Moon, Yoonseok Yang, Hangyeol Yu, Seunghyun Lee, Myeongho Jeong, Juneyoung Park, Jamin Shin, Minsam Kim, Seungtaek Choi

Challenge:	Existing evaluation metrics for MCQ generation focus on the n-gram based similarity of the generated MCq to the gold sample and disregard their educational value.
Approach:	They propose to use a human survey to measure the MCQ’s answerability given knowledge of the target fact.
Outcome:	The proposed methods measure the MCQ’s answerability given knowledge of the target fact.

Annotating a Fable in Italian Sign Language (LIS) (2020.lrec-1)

Copied to clipboard

Serena Trolvi, Rodolfo Delmonte

Challenge:	fables are short or medium-length stories with a moral and they generally have specific characteristics in SLs that are usually not to be found in spoken languages like Italian.
Approach:	They present work for automatic generation of a written text in Italian starting from glosses of fable in Italian Sign Language (LIS).
Outcome:	The proposed method was used to generate a written text in Italian starting from glosses of a fable in Italian Sign Language (LIS).

Robustifying Sentiment Classification by Maximally Exploiting Few Counterfactuals (2022.emnlp-main)

Copied to clipboard

Maarten De Raedt, Fréderic Godin, Chris Develder, Thomas Demeester

Robustness in NLP

Challenge:	a recent study found that finetuned language models rely on spurious patterns in training data . this limitation limits their performance on out-of-distribution (OOD) test data.
Approach:	They propose a method that only requires annotation of a small fraction of training data . they add 1% manual counterfactuals to training data and generate extra counterfacts in vector space .
Outcome:	The proposed approach improves sentiment classification using IMDb data and other sets for OOD tests.

A Multi-level Annotated Corpus of Scientific Papers for Scientific Document Summarization and Cross-document Relation Discovery (2020.lrec-1)

Copied to clipboard

Ahmed AbuRa’ed, Horacio Saggion, Luis Chiruzzo

Information Extraction & Text Mining

Challenge:	Recent studies have proposed to take advantage of the scientific paper's citation network to approach literature summarization.
Approach:	They propose to annotate related work sections, cite papers and sentences using machine readable data and an additional layer of papers citing the references.
Outcome:	The proposed corpus expands the existing data-set of related work sections and cites the papers cited in the related work section.

GTA: Generating Long-horizon Tasks for Web Agents at Scale (2026.acl-long)

Copied to clipboard

Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey, Yilun Zhou, Muhao Chen, Jonathan May, Chien-Sheng Wu

Green & Sustainable NLP

Challenge:	Existing benchmarks provide only coarse start–goal annotations without intermediate trajectories . Existing frameworks provide no supervision over the agent's latent decision process .
Approach:	They propose a framework that integrates crawling, retrieval-based seeding, in-context generation and automated quality control to produce realistic tasks paired with executable trajectories.
Outcome:	The proposed framework decouples crawling from generation for greater efficiency and ensures dense supervision through deterministic replays and systematic validation.

ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents (2026.acl-long)

Copied to clipboard

Tianjian Liu, Fanqi Wan, Jiajian Guo, Xiaojun Quan