GENERATOR

Adversarial Text Generation via Sequence Contrast Discrimination (2020.findings-emnlp)

Challenge:	Retrieval Augment Generation (RAG) has been developed for use in open-domain question answering (ODQA) but it is not optimized for use with other specialized domains such as healthcare and news.
Approach:	They propose an extension to RAG that can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training.
Outcome:	The proposed extension can adapt to a domain-specific knowledge base by updating all components of the external knowledge base during training.

Copied to clipboard

Ke Wang, Xiaojun Wan

Is Agentic RAG worth it? An experimental comparison of RAG approaches (2026.acl-industry)

Challenge:	Existing approaches to generate human-like texts are auto-regressive, but they suffer from exposure bias due to the dependence on the previous sampled output during the inferring phase.
Approach:	They propose a sequence contrast loss driven text generation framework which learns the difference between real texts and generated texts and uses that difference.
Outcome:	The proposed framework improves training stability and quality of generated texts and avoids the time-consuming sampling process.

Copied to clipboard

Pietro Ferrazzi, Milica Cvjetićanin, Alessio Piraccini, Davide Giannuzzi

Extractive Summarization with Text Generator (2024.naacl-long)

Challenge:	Retrieval-Augmented Generation (RAG) systems have several limitations, including noisy or suboptimal retrieval, misuse of retrieval for out-of-scope queries, weak query–document matching, and variability or cost associated with the generator.
Approach:	They propose to use a "Enhanced" RAG to address weaknesses in the workflow . they propose to orchestrate the entire process, deciding which actions to perform, when to perform them, and whether to iterate .
Outcome:	The proposed models address shortcomings in the RAG workflow, and provide practical insights into the trade-offs between them.

Copied to clipboard

Thang Le, Anh Tuan Luu

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

Challenge:	Existing extractive systems lack gold training signals, thereby hindering learning of extractive models.
Approach:	They propose to use text generators to train extractive summarizers by approximating outputs of abstractive summaries.
Outcome:	The proposed method can be used to train extractive summarizers without training . it is shown that the approximated summaries correlate positively with the auxiliary summary outputs.

Copied to clipboard

Sudha Rao, Hal Daumé III

Improving Mongolian-Chinese Neural Machine Translation with Morphological Noise (P19-2)

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

Yatu Ji, Hongxu Hou, Chen Junjie, Nier Wu

Discourse-Aware Neural Rewards for Coherent Text Generation (N18-1)

Challenge:	Existing models for Mongolian-Chinese translation are based on recurrent, convolutional neural networks or completely eliminate recurrence connections.
Approach:	They propose a adversarial training model to alleviate the UNK problem in Mongolian-Chinese machine translation by adding a screener to the model to emphasize the added Mongolian morphological noise.
Outcome:	The proposed model reduces training time and improves accuracy in Mongolian-Chinese translation tasks.

Copied to clipboard

Antoine Bosselut, Asli Celikyilmaz, Xiaodong He, Jianfeng Gao, Po-Sen Huang, Yejin Choi

Comprehensive Comparison of RAG Methods Across Multi-Domain Conversational QA (2026.eacl-srw)

Challenge:	Existing approaches to train text generation models using cross-entropy loss do not always correlate well with achieving high scores on commonly used evaluation measures.
Approach:	They propose to use discourse-aware rewards to model cross-sentence ordering to approximate desired discourse structure to train a model of long, coherent text.
Outcome:	The proposed model produces more coherent and less repetitive text than models trained with cross-entropy or with commonly used scores as rewards.

Copied to clipboard

Klejda Alushi, Jan Strich, Chris Biemann, Martin Semmann

Cooperative Self-training of Machine Reading Comprehension (2022.naacl-main)

Challenge:	Existing studies evaluate RAG methods in isolation and focus on single-turn settings.
Approach:	They compare retrieval-augmented generation methods for multi-turn conversational QA with those that use dialogue history and coreference to ground large language models.
Outcome:	The proposed methods outperform vanilla RAG and advanced methods fail to yield gains and can even degrade performance below the No-RAG baseline.

Copied to clipboard

Hongyin Luo, Shang-Wen Li, Mingye Gao, Seunghak Yu, James Glass

Reinforced Counterfactual Data Augmentation for Dual Sentiment Classification (2021.emnlp-main)

Challenge:	Pretrained language models provide high-quality contextualized word embeddings, but training question answering models requires large amounts of annotated data for specific domains.
Approach:	They propose a framework for automatically generating more non-trivial question-answer pairs to improve model performance.
Outcome:	The proposed framework outperforms state-of-the-art (SOTA) pretrained language models and transfer learning approaches on standard question-answering benchmarks.

Copied to clipboard

Hao Chen, Rui Xia, Jianfei Yu

Forged-GAN-BERT: Authorship Attribution for LLM-Generated Forged Novels (2024.eacl-srw)

Challenge:	Existing approaches to improve generalization ability by augmenting training data with synonymous examples or adding random noises to word embeddings cannot address spurious association problem.
Approach:	They propose an end-to-end reinforcement learning framework which jointly performs counterfactual data generation and dual sentiment classification.
Outcome:	The proposed framework outperforms strong data augmentation baselines on several benchmark sentiment classification datasets.

Copied to clipboard

Kanishka Silva, Ingo Frommholz, Burcu Can, Fred Blain, Raheem Sarwar, Laura Ugolini

Unsupervised KB-to-Text Generation with Auxiliary Triple Extraction using Dual Learning (2020.aacl-main)

Challenge:	generative Large Language Models (LLMs) are capable of producing human-like texts, but they pose challenges related to the authenticity of the text documents.
Approach:	They propose a modified GANBERT-based model to improve the classification of forged novels via the Forged Novels Generator and the generator in GAN.
Outcome:	The proposed model improves classification of forged novels in two data-augmentation aspects.

Copied to clipboard

Zihao Fu, Bei Shi, Lidong Bing, Wai Lam

Data-to-text Generation with Macro Planning (2021.tacl-1)

Challenge:	Existing methods to generate text from KB triples are limited and expensive . a novel approach is proposed to train the generation model in unsupervised way .
Approach:	They propose a method which trains the generation model in a completely unsupervised way with unaligned raw text data and KB triples.
Outcome:	The proposed method outperforms existing methods and is cost-effective.

Copied to clipboard

Ratish Puduppully, Mirella Lapata

Neural Topic Modeling with Bidirectional Adversarial Training (2020.acl-main)

Challenge:	Recent approaches to data-to-text generation adopt the encoder-decoder architecture . however, these models perform poorly at selecting appropriate content and ordering it coherently .
Approach:	They propose a neural model with a macro planning stage followed by a generation stage . they use data from databases of records, simulations of physical systems, accounting spreadsheets .
Outcome:	The proposed model outperforms baselines on two data-to-text benchmarks . it uses the encoderdecoder architecture and is compared with existing models .

Copied to clipboard

Rui Wang, Xuemeng Hu, Deyu Zhou, Yulan He, Yuxuan Xiong, Chenchen Ye, Haiyang Xu

Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion (2024.eacl-long)

Challenge:	Recent studies have shown that neural topic models for automatic topic extraction avoid complicated mathematical derivations for model inference.
Approach:	They propose a bidirectional adversarial topic model which uses a generator and an encoder to infer topic distribution.
Outcome:	The proposed model outperforms baselines and competitive models in three benchmark corpora.

Copied to clipboard

Aly Kassem, Sherif Saad

Discourse Understanding and Factual Consistency in Abstractive Summarization (2021.eacl-main)

Challenge:	Adversarial attacks against Language models (LMs) are a significant concern.
Approach:	They propose an approach to automatically learn a policy to generate challenging examples that improve the model’s performance.
Outcome:	The proposed approach outperforms baselines and exhibits generalizability across classifiers and datasets.

Copied to clipboard

Saadia Gabriel, Antoine Bosselut, Jeff Da, Ari Holtzman, Jan Buys, Kyle Lo, Asli Celikyilmaz, Yejin Choi

Summarization

Challenge:	Existing abstractive summarization models often hallucinate information or generate factually incorrect summaries.
Approach:	They propose a general framework for abstractive summarization with factual consistency and distinct modeling of the narrative flow in an output summary.
Outcome:	The proposed framework generates abstracts with factual consistency and coherence significantly better than baselines.

Text Generation from Discourse Representation Structures (2021.naacl-main)

Copied to clipboard

Jiangming Liu, Shay B. Cohen, Mirella Lapata

Personalized Abstractive Summarization by Tri-agent Generation Pipeline (2024.findings-eacl)

Challenge:	Existing models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs) .
Approach:	They propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs).
Outcome:	The proposed model achieves competitive performance on the GMB benchmark against several strong baselines.

Copied to clipboard

Wen Xiao, Yujia Xie, Giuseppe Carenini, Pengcheng He

DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction (P18-1)

Challenge:	Existing research shows that large language models do not consistently satisfy users' preferences or expectations.
Approach:	They propose a tri-agent generation pipeline that includes a generator, an instructor, and an editor to enhance output personalization.
Outcome:	The proposed pipeline generates outputs that better meet user expectations on two abstractive summarization datasets.

Copied to clipboard

Pengda Qin, Weiran Xu, William Yang Wang

Defense Against Knowledge Poisoning Attack on GraphRAG (2026.acl-short)

Challenge:	Distant supervision can effectively label data for relation extraction, but suffers from the noise labeling problem.
Approach:	They propose a sentence-level true-positive generator to learn a true-negative generator from a fuzzy sentence bag.
Outcome:	The proposed method significantly improves the performance of distant supervision relation extraction compared to state-of-the-art systems.

Copied to clipboard

Havva Alizadeh Noughabi, Fattane Zarrinkalam, Ali Dehghantanha

ReFSQL: A Retrieval-Augmentation Framework for Text-to-SQL Generation (2023.findings-emnlp)

Challenge:	Existing GraphRAGs expose a new attack surface: corpus-level knowledge poisoning can corrupt query-specific subgraphs and steer the generator toward incorrect answers.
Approach:	They propose a defense layer between retriever and generator that decomposes multi-hop questions into ordered subqueries and monitors hop-wise execution for poisoning-induced inconsistencies.
Outcome:	The proposed defense layer decomposes multi-hop questions into ordered subqueries and monitors hop-wise execution for poisoning-induced inconsistencies.

Copied to clipboard

Kun Zhang, Xiexiong Lin, Yuanzhuo Wang, Xin Zhang, Fei Sun, Cen Jianhe, Hexiang Tan, Xuhui Jiang, Huawei Shen

Programming Languages in NLP

Challenge:	Existing methods that align natural language with SQL Language underestimate inherent structural characteristics of SQL and lead to structure errors.
Approach:	They propose a retrieval-argument framework that aligns natural language with SQL Language and trains one encoder-decoder-based model to fit all questions.
Outcome:	The proposed framework improves accuracy and robustness of text-to-SQL generation on five datasets.

OoMMix: Out-of-manifold Regularization in Contextual Embedding Space for Text Classification (2021.acl-long)

Copied to clipboard

Seonghyeon Lee, Dongha Lee, Hwanjo Yu

Representation Learning

Challenge:	Recent studies on neural networks with pre-trained weights focus on low-dimensional subspace where the embedding vectors computed from input words are located.
Approach:	They propose an approach to find and regularize the remainder of the space, referred to as out-of-manifold, which cannot be accessed through the words.
Outcome:	The proposed approach is able to fine-tune the out-of-manifold embedding space on text classification benchmarks.

AutoChecklist: Composable Pipelines for Checklist Generation and Scoring with LLM-as-a-Judge (2026.acl-demo)

Copied to clipboard

Karen Zhou, Chenhao Tan

Challenge:	AutoChecklist is an open-source library that unifies checklist-based evaluation into composable pipelines.
Approach:	They propose an open-source library that unifies checklist-based evaluation into composable pipelines.
Outcome:	The open-source library unifies checklist-based evaluation into composable pipelines.

GEMINI: Controlling The Sentence-Level Summary Style in Abstractive Text Summarization (2023.emnlp-main)

Copied to clipboard

Guangsheng Bao, Zebin Ou, Yue Zhang

Interlocking-free Selective Rationalization Through Genetic-based Learning (2025.acl-long)

Challenge:	Existing models that mimic human summarization techniques are difficult to imitate.
Approach:	They propose an adaptive model that integrates a rewriter and a generator to mimic the sentence rewriting and abstracting techniques.
Outcome:	The proposed model outperforms baselines on WikiHow and on other datasets.

Copied to clipboard

Federico Ruggeri, Gaetano Signorelli

Challenge:	Existing approaches to selective rationalization suffer from interlocking, a phenomenon known as interlock.
Approach:	They propose a genetically-based disjoint training architecture for selective rationalization that avoids interlocking by performing genetic global search.
Outcome:	The proposed model outperforms state-of-the-art models on a synthetic and real-world benchmark.

Know What You Don’t Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories (P19-1)

Copied to clipboard

Sina Zarrieß, David Schlangen

Little Giants: Synthesizing High-Quality Embedding Data at Scale (2025.naacl-long)

Challenge:	a lot of recent and traditional research on pragmatically informative object descriptions has focused on the task of correctly labelling objects of novel categories.
Approach:	They extend a neural generator to become a pragmatic speaker reasoning about uncertain object categories.
Outcome:	The proposed model improves the accuracy of the listener's communication with unfamiliar objects.

Copied to clipboard

Haonan Chen, Liang Wang, Nan Yang, Yutao Zhu, Ziliang Zhao, Furu Wei, Zhicheng Dou

Computational Morphology and Lexicography Modeling of Modern Standard Arabic Nominals (2024.findings-eacl)

Challenge:	Synthetic data generation is an increasingly popular way of training models without the need for large, manually labeled datasets.
Approach:	They propose a framework that aligns open-source small models to efficiently generate large-scale embedding data.
Outcome:	The proposed framework outperforms state-of-the-art embedding models by using only 1/10 of the GPT API calls.

Copied to clipboard

Christian Khairallah, Reham Marzouk, Salam Khalifa, Mayar Nassar, Nizar Habash

Out-of-domain Detection based on Generative Adversarial Network (D18-1)

Challenge:	Modern Standard Arabic (MSA) nominals present many morphological and lexical modeling challenges that have not been consistently addressed before.
Approach:	They propose to use a morphological framework to model Arabic nominals using a proposed morphology framework.
Outcome:	The proposed model improves accuracy and consistency compared to a commonly used morphological analyzer and generator.

Copied to clipboard

Seonghan Ryu, Sangjun Koo, Hwanjo Yu, Gary Geunbae Lee

Adaptive Weighted Proxy Tuning: Efficient Gray-Box Steering for Image Captioning. (2026.acl-industry)

Challenge:	Existing methods for out-of-domain (OOD) detection require huge effort to collect OOD sentences.
Approach:	They propose to use only in-domain (IND) sentences to build a generative adversarial network (GAN) of which the discriminator generates low scores for OOD sentences.
Outcome:	The proposed method is most accurate compared to existing methods on multi-domain dialog systems.

Copied to clipboard

Nafew Azim, Fuad Rahman, Nabeel Mohammed

Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training (C18-1)

Challenge:	Proxy tuning is a decoding-time approach that fails to account for instance-specific variations in model certainty and domain shift.
Approach:	They propose a gray-box steering framework that dynamically modulates the logit contributions of a large base model, a fine-tuned expert, and an untune .
Outcome:	Adaptive Weighted Proxy Tuning achieves performance parity with fine-tuned models while remaining parameter-free.

Copied to clipboard

Zhongyang Li, Xiao Ding, Ting Liu

Think While You Write: Hypothesis Verification Promotes Faithful Knowledge-to-Text Generation (2024.findings-naacl)

Challenge:	Story generation is a challenging problem in artificial intelligence (AI) . previous work focused on learning statistical models of event sequences from large-scale text corpora .
Approach:	They propose to use adversarial training to generate reasonable story endings . their model includes a generator that defines the policy of generating a story ending .
Outcome:	The proposed model achieves better performance on the task of Story Cloze Test with an accuracy of 62.6% compared with state-of-the-art baseline methods.

Copied to clipboard

Yifu Qiu, Varun Embar, Shay Cohen, Benjamin Han

A New Approach to Overgenerating and Scoring Abstractive Summaries (2021.naacl-main)

Challenge:	Knowledge-to-text generators often struggle to faithfully generate descriptions for input facts . we propose a decoding-only method to reduce hallucinations .
Approach:	They propose a decoding-only method to generate accurate descriptions for input facts . they use a Natural Language Inference model as the model and replace it with a task-specific HVM .
Outcome:	The proposed method improves faithfulness with minimal impact on quality and in/out-of-distribution evaluations.

Copied to clipboard

Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu

DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization (2022.acl-long)

Challenge:	Abstractive summarization is a learning objective to produce system outputs that resemble reference summaries on a word-to-word basis.
Approach:	They propose a two-staged strategy to generate multiple variants of the target summary and score and select admissible ones according to users’ needs.
Outcome:	The proposed approach can achieve state-of-the-art on benchmark summarization datasets.

Copied to clipboard

Ziming Mao, Chen Henry Wu, Ansong Ni, Yusen Zhang, Rui Zhang, Tao Yu, Budhaditya Deb, Chenguang Zhu, Ahmed Awadallah, Dragomir Radev

APOLLO: An Optimized Training Approach for Long-form Numerical Reasoning (2024.lrec-main)

Challenge:	Existing models struggle with summarizing long text due to high memory complexity of the full self-attention.
Approach:	They propose a dynamic latent extraction approach for abstractive long-input summarization that treats extracted text snippets as latent variables and allows dynamic attention weights during decoding.
Outcome:	The proposed method outperforms existing methods on GovReport, QMSum, and arXiv while yielding strong results on arX.

Copied to clipboard

Jiashuo Sun, Hang Zhang, Chen Lin, Xiangdong Su, Yeyun Gong, Jian Guo

Programming Languages in NLP

Challenge:	Existing methods to generate reasoning programs that ignore the differences between facts treated all facts equally, leading to wrong punishment of programs that differed from the ground truth.
Approach:	They propose an optimized training framework for long-form numerical reasoning that incorporates a number-aware negative sampling strategy and consistency-based reinforcement learning to increase execution accuracy.
Outcome:	The proposed method improves the performance of long-form numerical reasoning on the FinQA and ConvFinQA leaderboards.

Improving Neural Machine Translation with Conditional Sequence Generative Adversarial Nets (N18-1)

Copied to clipboard

Zhen Yang, Wei Chen, Feng Wang, Bo Xu

Graph Neural Networks with Generated Parameters for Relation Extraction (P19-1)

Challenge:	Experimental results show that the proposed model consistently outperforms the traditional RNNSearch and the newly emerged state-of-the-art Transformer on English-German and Chinese-English translation tasks.
Approach:	They propose an approach for applying GANs to NMT by building a conditional sequence generative adversarial net with two adversarials.
Outcome:	The proposed model outperforms the existing RNNSearch and Transformer on English-German and Chinese-English translation tasks.

Copied to clipboard

Hao Zhu, Yankai Lin, Zhiyuan Liu, Jie Fu, Tat-Seng Chua, Maosong Sun

NAST: A Non-Autoregressive Generator with Word Alignment for Unsupervised Text Style Transfer (2021.findings-acl)

Challenge:	Existing graph neural networks can only process multi-hop relational reasoning on pre-defined graphs and cannot be directly applied in natural language relational reasoning.
Approach:	They propose a graph neural network with generated parameters using natural language sentences as inputs.
Outcome:	The proposed model can process relational reasoning on graphs and in natural language processing tasks.

Copied to clipboard

Fei Huang, Zikai Chen, Chen Henry Wu, Qihan Guo, Xiaoyan Zhu, Minlie Huang

LLM Agents Implement an NLG System from Scratch: Building Interpretable Rule-Based RDF-to-Text Generators (2025.emnlp-industry)

Challenge:	Autoregressive text style transfer models often ignore part of the source sentence and generate some irrelevant words with strong styles.
Approach:	They propose a non-autoregressive generator for unsupervised text style transfer which explicitly models word alignments to suppress irrelevant words.
Outcome:	The proposed generator significantly improves performance and provides explainable word alignments.

Copied to clipboard

Mateusz Lango, Ondrej Dusek

Explainability & Interpretability in NLP

Challenge:	Existing neural approaches to generate RDF-to-text are limited in their implementation.
Approach:	They propose a framework where the model is “trained” through collaborative interactions among multiple LLM agents rather than traditional backpropagation.
Outcome:	The proposed framework reduces hallucinations and fluency penalties on the WebNLG and OpenDialKG datasets.

FAID: Fine-grained AI-generated Text Detection using Multi-task Auxiliary and Multi-level Contrastive Learning (2026.eacl-long)

Copied to clipboard

Minh Ngoc Ta, Dong Cao Van, Duc-Anh Hoang, Minh Le-Anh, Truong Nguyen, My Anh Tran Nguyen, Yuxia Wang, Preslav Nakov, Dinh Viet Sang

Generative Bridging Network for Neural Sequence Prediction (N18-1)

Challenge:	Existing binary detection frameworks for human-written, LLM-generated and human-LLM collaborative texts are challenging . a recent study focused on binary detection, i.e., human vs. LLM, or on fine-grained detection limited to English.
Approach:	They propose a fine-grained detection framework to classify text into three categories . they use multilingual datasets and a multi-domain, multi-generator dataset .
Outcome:	The proposed framework outperforms baselines on unseen domains and new LLMs.

Copied to clipboard

Wenhu Chen, Guanlin Li, Shuo Ren, Shujie Liu, Zhirui Zhang, Mu Li, Ming Zhou

Evidentiality-guided Generation for Knowledge-Intensive NLP Tasks (2022.naacl-main)

Challenge:	Existing approaches to improve the likelihood of sequence prediction models are based on MLE and teacher forcing.
Approach:	They propose a Generative Bridging Network (GBN) that extends the point-wise ground truth to a bridge distribution conditioned on it and optimizes their KL-divergence.
Outcome:	The proposed bridge module can improve on two recognized sequence prediction tasks and minimize learning burden.

Copied to clipboard

Akari Asai, Matt Gardner, Hannaneh Hajishirzi

Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net (2022.findings-naacl)

Challenge:	Existing methods to augment retrieval-augmented generation models with retrievers often rely on spurious cues or generate hallucinations during inference.
Approach:	They propose a method to incorporate evidentiality of passages into training a retrieval-augmented generation model.
Outcome:	The proposed method outperforms its direct counterpart on all knowledge-intensive tasks.

Copied to clipboard

Xin Sheng, Linli Xu, Yinlong Xu, Deqiang Jiang, Bo Ren

Eliciting Implicit Acoustic Styles from Open-domain Instructions to Facilitate Fine-grained Controllable Generation of Speech (2025.emnlp-main)

Challenge:	Existing methods focus on attention mechanism, but they are not suitable for abstractive text summarization.
Approach:	They propose a siamese generative adversarial net for abstractive text summarization which preserves the main semantics of the source text and the target summary.
Outcome:	The proposed model can preserve the main semantics of the source text and target summary.

Copied to clipboard

Jianxing Yu, Gou Zihao, Chen Li, Zhisheng Wang, Peiji Yang, Wenqing Chen, Jian Yin

“Barking up the Right Tree”, a GAN-Based Pun Generation Model through Semantic Pruning (2024.lrec-main)

Challenge:	Current work relies on pre-defined rules or templates to control the style of speech.
Approach:	They propose to use open-domain instructions to generate speech with the acoustic style that meets users’ needs based on their instructions.
Outcome:	The proposed model can be used to generate speech with the acoustic style that meets users’ needs based on open-domain instructions.

Copied to clipboard

JingJie Zeng, Liang Yang, Jiahao Kang, Yufeng Diao, Zhihao Yang, Hongfei Lin

Divide and Conquer: Legal Concept-guided Criminal Court View Generation (2024.findings-emnlp)

Challenge:	Existing methods for generating humorous puns are limited and require a broad spectrum of commonsense and worldly skills.
Approach:	They propose a GAN-based approach that employs semantic pruning and contrastive learning to generate humorous puns using a model that captures the semantic nuances of puns.
Outcome:	The proposed model produces semantically coherent and humorous puns while ensuring both correctness and humor.

Copied to clipboard

Qi Xu, Xiao Wei, Hang Yu, Qian Liu, Hao Fei

Retrieval-guided Dialogue Response Generation via a Matching-to-Generation Framework (D19-1)

Challenge:	Existing methods for creating rationales for criminal cases do not pay enough attention to the important legal concepts.
Approach:	They propose a legal concept-guided court view generation framework that generates rationales based on predicted legal concepts . they first divide the court view into sub-views, then employ a solver and verifier to generate and select rationale.
Outcome:	The proposed model generates coherent and coherent court views on a real-world criminal case dataset.

Copied to clipboard

Deng Cai, Yan Wang, Wei Bi, Zhaopeng Tu, Xiaojiang Liu, Shuming Shi

BotChat: Evaluating LLMs’ Capabilities of Having Multi-Turn Dialogues (2024.findings-naacl)

Challenge:	generative models for end-to-end sequence generation have been shown promising for this task . however, how to precisely extract a skeleton and how to effectively train a retrieval-guided response generator is still challenging.
Approach:	They propose a framework where skeleton extraction is made by an interpretable matching model and a retrieval-guided response generator is followed by a separate generator.
Outcome:	The proposed framework outperforms baseline models in a variety of experiments.

Copied to clipboard

Haodong Duan, Jueqi Wei, Chonghua Wang, Hongwei Liu, Yixiao Fang, Songyang Zhang, Dahua Lin, Kai Chen

Cycle-Consistent Adversarial Autoencoders for Unsupervised Text Style Transfer (2020.coling-main)

Challenge:	Modern Large Language Models (LLMs) facilitate high-quality, multi-turn dialogues with humans, but human-based evaluation of such a capability requires substantial manual effort.
Approach:	They propose to evaluate LLMs' ability to emulate human-like, multi-turn conversations using an LLM-centric approach.
Outcome:	The proposed model emulates human-like, multi-turn conversations using an LLM-centric approach.

Copied to clipboard

Yufang Huang, Wentao Zhu, Deyi Xiong, Yiye Zhang, Changjian Hu, Feiyu Xu

On Controlling Fallback Responses for Grounded Dialogue Generation (2022.findings-acl)

Challenge:	Existing methods for unsupervised text style transfer lack parallel data and difficulties in content preservation.
Approach:	They propose a neural approach to unsupervised text style transfer using non-parallel data.
Outcome:	The proposed approach can be trained end-to-end on two widely-used public datasets.

Copied to clipboard

Hongyuan Lu, Wai Lam, Hong Cheng, Helen Meng

Biomedical Entity Linking as Multiple Choice Question Answering (2024.lrec-main)

Challenge:	Existing knowledge grounded dialogue frameworks assume that the user intention is always answerable.
Approach:	They propose a framework that automatically generates a control token with the generator to bias the succeeding response towards informativeness for answerable contexts and fallback for unanswerable context.
Outcome:	The proposed framework incorporates fallback responses to respond to unanswerable contexts in an informative manner while retaining informativeness for answerable context.

Copied to clipboard

Zhenxi Lin, Ziheng Zhang, Xian Wu, Yefeng Zheng

DivGAN: Towards Diverse Paraphrase Generation via Diversified Generative Adversarial Network (2020.findings-emnlp)

Challenge:	Existing methods for biomedical entity linking are discriminative and disambiguative . Existing models for bioMEDical entity linking use a BERT-based encoder to encode mentions and entities into the same embedding space and dissociate mentions by nearest neighbors.
Approach:	They propose a model that treats biomedical entity linking as Multiple Choice Question Answering.
Outcome:	The proposed model outperforms state-of-the-art models on several datasets.

Copied to clipboard

Yue Cao, Xiaojun Wan

Training ELECTRA Augmented with Multi-word Selection (2021.findings-acl)

Challenge:	Paraphrases refer to texts that convey the same meaning with different expression forms.
Approach:	They propose to incorporate a diversity loss term into a deep generative model to generate diverse paraphrases.
Outcome:	The proposed model can generate more diverse paraphrases compared with baselines.

Copied to clipboard

Jiaming Shen, Jialu Liu, Tianqi Liu, Cong Yu, Jiawei Han

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential (2024.findings-acl)

Challenge:	Existing pre-training methods for NLP tasks require massive computation resources.
Approach:	They propose a method that trains a discriminator to detect replaced tokens and select original tokens from candidate sets.
Outcome:	The proposed method improves ELECTRA based on multi-task learning on GLUE and SQUAD datasets.

Copied to clipboard

Wei Tang, Yixin Cao, Jiahao Ying, Bo Wang, Yuyue Zhao, Yong Liao, Peng Zhou

Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation (2025.findings-acl)

Challenge:	Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models.
Approach:	They propose a "generate-then-read" pipeline to replace retrieval stage with generation from the LLM itself.
Outcome:	The proposed framework outperforms single models in the base and chat versions and addresses safety and helpfulness post-adaptation challenges.

Copied to clipboard

Pengyue Jia, Derong Xu, Xiaopeng Li, Zhaocheng Du, Xiangyang Li, Yichao Wang, Yuhao Wang, Qidong Liu, Maolin Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

NewsDialogues: Towards Proactive News Grounded Conversation (2023.findings-acl)

Challenge:	Existing approaches to rerank and align documents based on reasoning capabilities of large language models (LLMs) . prior work shows that LLMs have exceptional reasoning and text generation capabilities .
Approach:	They propose a rationale extraction method that leverages reasoning capabilities of large language models to extract the rationales necessary for answering a query.
Outcome:	The proposed method is compared with baseline methods on two tasks across three datasets.

Copied to clipboard

Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, Yujiu Yang

Enhancing Arguments Recognition for Financial Mathematical Reasoning over Hybrid Data (2024.findings-emnlp)

Challenge:	Hot news is one of the most popular topics in daily conversations.
Approach:	They propose a task where a dialogue system can lead the conversation based on key topics of the news.
Outcome:	The proposed method can lead conversations based on key topics of the news . it can also be used in information-seeking and chit-chat scenarios .

Copied to clipboard

Jinsu Lim, Yechan Hwang, Young-Jun Lee, Ho-Jin Choi

Camel Morph MSA: A Large-Scale Open-Source Morphological Analyzer for Modern Standard Arabic (2024.lrec-main)

Challenge:	Existing methods for question answering on textual data are difficult to train and pose a misrecognition problem.
Approach:	They propose an approach to train a reasoning program generator to improve argument recognition by aggregating arguments and loss argument set.
Outcome:	The proposed method improves the probabilities of proper arguments in a reasoning program generation so that arguments comprising the ground truth have higher weights.

Copied to clipboard

Christian Khairallah, Salam Khalifa, Reham Marzouk, Mayar Nassar, Nizar Habash

Solving Math Word Problems via Cooperative Reasoning induced Language Models (2023.acl-long)

Challenge:	Camel Morph MSA is the largest open-source Modern Standard Arabic morphological analyzer and generator.
Approach:	They present Camel Morph MSA, the largest open-source Arabic morphological analyzer and generator.
Outcome:	The analysis can produce 1.45B analyses and 535M unique diacritizations, almost an order of magnitude larger than SAMA on a 10B word corpus.

Copied to clipboard

Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, Yujiu Yang

Bridging Attribution and Open-Set Detection using Graph-Augmented Instance Learning in Synthetic Speech (2026.eacl-long)

Challenge:	Large-scale pre-trained language models (PLMs) can be used to solve math word problems, but they lack fast adaptivity as humans.
Approach:	They propose a cooperative reasoning-induced PLM for solving the math word problem . they use system 1 as the generator and system 2 as the verifier to generate reasoning paths .
Outcome:	The proposed model improves on several mathematical reasoning datasets and achieves 9.6% improvement over baselines.

Copied to clipboard

Mohd Mujtaba Akhtar, null Girish, Farhan Sheth, Muskaan Singh

VIMI: Grounding Video Generation through Multi-modal Instruction (2024.emnlp-main)

Challenge:	Synthetic speech detection is a critical part of safeguarding digital communication, enabling systems to identify and mitigate the risks posed by highly realistic, machine-generated voices.
Approach:	They propose a framework that combines SFMs with graph-based modeling and open-set generalization to capture meaningful relationships between utterances and recognize speech that doesn’t belong to any known generator.
Outcome:	The proposed framework improves performance across both tasks, with Mamba-based embeddings delivering particularly strong results.

Copied to clipboard

Yuwei Fang, Willi Menapace, Aliaksandr Siarohin, Tsai-Shien Chen, Kuan-Chieh Wang, Ivan Skorokhodov, Graham Neubig, Sergey Tulyakov

F2RL: Factuality and Faithfulness Reinforcement Learning Framework for Claim-Guided Evidence-Supported Counterspeech Generation (2024.emnlp-main)

Challenge:	Existing text-to-video diffusion models rely on text-only encoders for their pretraining, restricting their versatility and application in multimodal integration.
Approach:	They propose a multimodal conditional video generation framework for pretraining on augmented text prompts and then utilize a two-stage training strategy to enable diverse video generation tasks within a model.
Outcome:	The proposed model can synthesize consistent and temporally coherent videos with large motion while retaining the semantic control.

Copied to clipboard

Haiyang Wang, Yuchen Pan, Xin Song, Xuechen Zhao, Minghao Hu, Bin Zhou

Compete to Complete: Co-opetition Adversarial Learning for Retrieval-Augmented Generation (2026.acl-long)

Challenge:	Existing methods for generating evidence-supported counterspeech lack clear guidance with a core claim for organizing evidence.
Approach:	They propose a Factuality and Faithfulness Reinforcement Learning framework for generating claim-guided and evidence-supported counterspeech (F2RL) they generate counter-claims based on hate speech and design a self-evaluation mechanism to select the most appropriate one.
Outcome:	The proposed framework achieves excellent performance on three benchmark datasets with strong factuality and faithfulness.

Copied to clipboard

Xin Liu, Yu-An Liu, Ruqing Zhang, Yixing Fan, Lixin Su, Jiafeng Guo, Xueqi Cheng

Adversarial Category Alignment Network for Cross-domain Sentiment Classification (N19-1)

Challenge:	Existing approaches to reduce hallucination in large language models lack a robust mechanism for generating a generative model.
Approach:	They propose a framework that formulates retriever–generator training in RAG as a minimax game.
Outcome:	The proposed framework improves retrieval-augmented generation performance on seven benchmark datasets.

Copied to clipboard

Xiaoye Qu, Zhikang Zou, Yu Cheng, Yang Yang, Pan Zhou

Sentiment Analysis

Challenge:	Existing methods for cross-domain sentiment classification focus on aligning marginal distribution without taking category-specific decision boundaries into consideration.
Approach:	They propose an adversarial category alignment network to enhance category consistency . experimental results show the proposed method can achieve state-of-the-art performance .
Outcome:	The proposed method achieves state-of-the-art performance and produces more discriminative features on benchmark datasets.

RoSE: Round-robin Synthetic Data Evaluation for Selecting LLM Generators without Human Test Sets (2026.eacl-long)

Copied to clipboard

Jan Cegin, Branislav Pecher, Ivan Srba, Jakub Simko

Hello Again! LLM-powered Personalized Agent for Long-term Dialogue (2025.naacl-long)

Challenge:	Current large language models (LLMs) are powerful generators of synthetic data, which are used for training smaller, more efficient models.
Approach:	They propose a proxy metric for selecting the best LLM generator without human annotations and a metric that measures the performance of a model.
Outcome:	The proposed proxy metric outperforms intrinsic heuristics and comes within 0.76 percentage points of the optimal generator baseline.

Copied to clipboard

Hao Li, Chenghao Yang, An Zhang, Yang Deng, Xiang Wang, Tat-Seng Chua

Adversarial Grammatical Error Correction (2020.findings-emnlp)

Challenge:	Existing dialogue systems focus on brief single-session interactions, neglecting real-world needs for long-term companionship and personalized interactions.
Approach:	They propose a model-agnostic framework for long-term dialogue agents . they use event summary and persona management to enable reasoning .
Outcome:	The proposed framework incorporates three independently tunable modules dedicated to event perception, persona extraction, and response generation.

Copied to clipboard

Vipul Raheja, Dimitris Alikaniotis

Multilinguality

Challenge:	Experimental results show that adversarial-GEC can achieve competitive GEC quality compared to NMT-based baselines.
Approach:	They propose an adversarial approach to Grammatical Error Correction using a transformer-based model and a sentence-pair classification model.
Outcome:	The proposed approach achieves competitive GEC quality compared to baselines.

Automated Generation of Accurate & Fluent Medical X-ray Reports (2021.emnlp-main)

Copied to clipboard

Hoang Nguyen, Dong Nie, Taivanbat Badamdorj, Yujie Liu, Yingying Zhu, Jason Truong, Li Cheng

Grammatical Error Correction as GAN-like Sequence Labeling (2021.findings-acl)

Challenge:	Existing medical report generation efforts focus on producing human-readable reports, yet the generated text may not be well aligned to the clinical facts.
Approach:	They propose to automate the generation of medical reports from chest X-ray image inputs . medical reports are the primary medium, which physicians communicate findings from scans - authors say .
Outcome:	The proposed method achieves fluency and clinical accuracy on common metrics.

Copied to clipboard

Kevin Parnow, Zuchao Li, Hai Zhao

A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph (2020.findings-emnlp)

Challenge:	Traditional GEC models learn from sentences with fixed error rates . sequence labeling approaches suffer from a couple of key problems .
Approach:	They propose a GAN-like sequence labeling model with a grammatical error detector and a generator to correct grammamatical errors.
Outcome:	The proposed model improves the state-of-the-art in GEC and improves on benchmarks.

Copied to clipboard

Lin Qiao, Jianhao Yan, Fandong Meng, Zhendong Yang, Jie Zhou

Effective Data Augmentation for Sentence Classification Using One VAE per Class (2022.coling-1)

Challenge:	Topic-to-essay generation is a promising task for natural language generation.
Approach:	They propose a Sentiment Controllable topic-to- essay generator with a Topic Knowledge Graph enhanced decoder to generate essays with only several given topic words.
Outcome:	The proposed model outperforms the state-of-the-art model on automatic and human evaluation.

Copied to clipboard

Frédéric Piedboeuf, Philippe Langlais

On the Zero-Shot Generalization of Machine-Generated Text Detectors (2023.findings-emnlp)

Challenge:	Variational auto-encoders and its conditional variant the Conditional-VAE (CVAE) are often used to generate new textual data, but they require more complex manipulations to ensure that the generated examples are useful.
Approach:	They propose a simple way to use Variational Auto-Encoders (VAE) for data augmentation by training one VAE per class.
Outcome:	The proposed method outperforms generative models on binary classification tasks and several dataset sizes on four different tasks.

Copied to clipboard

Xiao Pu, Jingyu Zhang, Xiaochuang Han, Yulia Tsvetkov, Tianxing He

Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus (N19-1)

Challenge:	rampant proliferation of large language models generates text indistinguishable from human-written language.
Approach:	They train neural detectors on outputs of a new generator and test their performance on held-out generators.
Outcome:	The proposed detectors can be built on training data from medium-sized models.

Copied to clipboard

Hongyu Gong, Suma Bhat, Lingfei Wu, JinJun Xiong, Wen-mei Hwu

PRCA: Fitting Black-Box Large Language Models for Retrieval Question Answering via Pluggable Reward-Driven Contextual Adapter (2023.emnlp-main)

Challenge:	Existing methods for text style transfer have demonstrated considerable success, but a parallel corpus may not always be available for a transfer task.
Approach:	They propose a text style transfer model that uses an attention-based encoder-decoder to transfer a sentence from the source style to the target style.
Outcome:	The proposed model outperforms state-of-the-art methods on two different style transfer tasks.

Copied to clipboard

Haoyan Yang, Zhitao Li, Yong Zhang, Jianzong Wang, Ning Cheng, Ming Li, Jing Xiao

FinTextQA: A Dataset for Long-form Financial Question Answering (2024.acl-long)

Challenge:	Large Language Models (LLMs) are too large to be fine-tuned with budget constraints and some are only accessible via APIs.
Approach:	They propose a pluggable Reward-Driven Contextual Adapter that integrates large language models as generators and trains them to refine the retrieved information.
Outcome:	The proposed method improves ReQA performance on three datasets by up to 20% compared to existing methods.

Copied to clipboard

Jian Chen, Peilin Zhou, Yining Hua, Loh Xin, Kehui Chen, Ziyuan Li, Bing Zhu, Junwei Liang

Pun-GAN: Generative Adversarial Network for Pun Generation (D19-1)

Challenge:	Existing financial question answering datasets lack scope diversity and question complexity.
Approach:	They propose to use a dataset for long-form question answering in finance to evaluate QA systems.
Outcome:	The proposed dataset includes 1,262 high-quality, source-attributed QA pairs extracted and selected from finance textbooks and government agency websites.

Copied to clipboard

Fuli Luo, Shunyao Li, Pengcheng Yang, Lei Li, Baobao Chang, Zhifang Sui, Xu Sun

Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model (2022.emnlp-main)

Challenge:	Existing methods for generating pun sentences with word senses lack large-scale corpus for supervised learning . a pun is a clever and amusing use of a word with two meanings (word senses)
Approach:	They propose an adversarial generative network for pun generation with a generator and a discriminator to distinguish between generated pun sentences and real sentences with specific word senses.
Outcome:	The proposed network generates sentences that are more ambiguous and diverse in both automatic and human evaluation.

Copied to clipboard

Hojun Cho, Dohee Kim, Seungwoo Ryu, ChaeHun Park, Hyungjong Noh, Jeong-in Hwang, Minseok Choi, Edward Choi, Jaegul Choo

Connecting the Dots: A Knowledgeable Path Generator for Commonsense Question Answering (2020.findings-emnlp)

Challenge:	Existing methods to train text style transfer models with adversarial loss degrade fluency compared to other metrics.
Approach:	They propose a method which leverages a pretrained language model to improve fluency by restructuring the discriminator and the model itself.
Outcome:	The proposed model achieves state-of-the-art on three public benchmarks and achieved state-outperformance on the overall metrics.

Copied to clipboard

Peifeng Wang, Nanyun Peng, Filip Ilievski, Pedro Szekely, Xiang Ren

Data Augmentation with Atomic Templates for Spoken Language Understanding (D19-1)

Challenge:	Existing QA systems do not have commonsense knowledge or cannot reason with it.
Approach:	They propose to augment a general commonsense QA framework with a knowledgeable path generator by extrapolating existing paths from a KG with 'state-of-the-art' language model.
Outcome:	The generated paths are interpretable, novel, and relevant to the task.

Copied to clipboard

Zijian Zhao, Su Zhu, Kai Yu

How to Write Summaries with Patterns? Learning towards Abstractive Summarization through Prototype Editing (D19-1)

Challenge:	Existing methods to enlarge SLU data require large amounts of labelled data.
Approach:	They propose a data augmentation method with atomic templates for Spoken Language Understanding which generates atomic exemplars from atomic template.
Outcome:	The proposed method improves on a DSTC 2&3 dataset which is a domain adaptation setting of SLU.

Copied to clipboard

Shen Gao, Xiuying Chen, Piji Li, Zhangming Chan, Dongyan Zhao, Rui Yan

Beyond Embeddings: The Promise of Visual Table in Visual Reasoning (2024.emnlp-main)

Challenge:	Extensive experiments on a large-scale real-world text summarization dataset show that PESG achieves the state-of-the-art performance in terms of both automatic metrics and human evaluations.
Approach:	They propose a model that learns summary patterns and prototype facts from a prototype document . they use a fact checker to estimate mutual information between the input document and generated summary .
Outcome:	Experiments on a large-scale real-world text summarization dataset show that PESG achieves state-of-the-art performance.

Copied to clipboard

Yiwu Zhong, Zi-Yuan Hu, Michael Lyu, Liwei Wang

Learning to Sample Replacements for ELECTRA Pre-Training (2021.findings-acl)

Challenge:	Visual representation learning has been a cornerstone in computer vision for decades.
Approach:	They propose a visual representation tailored for visual reasoning that provides instance-level world knowledge and detailed attributes that are essential for visual reason.
Outcome:	The proposed visual tables outperform existing models on 11 visual reasoning benchmarks.

Copied to clipboard

Yaru Hao, Li Dong, Hangbo Bao, Ke Xu, Furu Wei

Prompt Optimization via Adversarial In-Context Learning (2024.acl-long)

Challenge:	Experimental results show that ELECTRA pretrains a discriminator to detect replaced tokens . despite compelling performance, there is no direct feedback loop from discriminator and generator to generator, making replacements biased to correct tokens.
Approach:	They propose to augment sampling with a hardness prediction mechanism to encourage the discriminator to learn what it has not acquired.
Outcome:	The proposed method improves ELECTRA pre-training on various downstream tasks.

Copied to clipboard

Do Long, Yiran Zhao, Hannah Brown, Yuxi Xie, James Zhao, Nancy Chen, Kenji Kawaguchi, Michael Shieh, Junxian He

GraDA: Graph Generative Data Augmentation for Commonsense Reasoning (2022.coling-1)

Challenge:	Existing methods to optimize prompts for in-context learning are based on adversarial learning and are computationally efficient and extensible to other LLMs and tasks.
Approach:	They propose a method to optimize prompts for in-context learning by a generator and a discriminator.
Outcome:	The proposed method improves state-of-the-art prompt optimization techniques on 13 generation and classification tasks including summarization, arithmetic reasoning, machine translation, data-to-text generation, and the MMLU and big-bench hard benchmarks.

Copied to clipboard

Adyasha Maharana, Mohit Bansal

Improving Model Factuality with Fine-grained Critique-based Evaluator (2025.acl-long)

Challenge:	Recent advances in commonsense reasoning have been fueled by the availability of large-scale human annotated datasets.
Approach:	They propose a graph-generative data augmentation framework to synthesize factual data samples from knowledge graphs for commonsense reasoning.
Outcome:	The proposed framework improves SocialIQA, CODAH, HellaSwag and CommonsenseQA . it also performs well for generative tasks like ProtoQA proving its robustness to adversaries .

Copied to clipboard

Yiqing Xie, Wenxuan Zhou, Pradyot Prakash, Di Jin, Yuning Mao, Quintin Fettes, Arya Talebzadeh, Sinong Wang, Han Fang, Carolyn Rose, Daniel Fried, Hejia Zhang

Dual-Feedback Knowledge Retrieval for Task-Oriented Dialogue Systems (2023.emnlp-main)

Challenge:	Factuality evaluation aims to detect factual errors produced by language models and guide the development of more factual models.
Approach:	They propose a framework that leverages FenCE to improve the factuality of LM generators by constructing training data.
Outcome:	The proposed framework improves the factuality of LM generators by enhancing their training data.

Copied to clipboard

Tianyuan Shi, Liangzhi Li, Zijian Lin, Tao Yang, Xiaojun Quan, Qifan Wang

PEER: Pre-training ELECTRA Extended by Ranking (2023.findings-acl)

Challenge:	Current approaches to task-oriented dialogue systems integrate knowledge retrieval and response generation, which poses scalability challenges when dealing with extensive knowledge bases.
Approach:	They propose a retriever-generator architecture that harnesses a retrieval and a generator to generate system responses by using feedback from the generator as pseudo-labels.
Outcome:	The proposed architecture shows superior performance on three benchmark datasets.

Copied to clipboard

Ru He, Wei Wang, Songfang Huang, Fei Huang

SCRIPT: Self-Critic PreTraining of Transformers (2021.naacl-main)

Challenge:	Existing models for pre-training require expensive pre-trainer computation cost . ELECTRA model can perform replaced token detection (RTD) task with reduced pre- training cost compared to current models .
Approach:	They propose to extend a discriminator-based replaced token detection task into a ranker-based task . they propose to use a binary classifier to perform a more precise task with negligible additional computation cost.
Outcome:	The proposed model outperforms state-of-the-art models with ELECTRA in GLUE tasks given the same cost.

Copied to clipboard

Erik Nijkamp, Bo Pang, Ying Nian Wu, Caiming Xiong

Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control (D19-1)

Challenge:	Existing methods for representation learning of text are masked language modeling (MLM) a language model is trained to learn universal contextual embeddings, which are fine-tuned on a down-stream task.
Approach:	They propose a self-critic pretraining transformer for representation learning of text . they demonstrate improved sample-efficiency and improved performance over strong baselines .
Outcome:	The proposed model improves sample-efficiency and performance over strong baselines.

Copied to clipboard

Mo Yu, Shiyu Chang, Yang Zhang, Tommi Jaakkola

MDocRAG-RL: Empowering Multi-Modal Document RAG via Complex Visual Reasoning with Reinforcement Learning (2026.findings-acl)

Challenge:	Selective rationalization is a common mechanism to ensure that predictive models reveal how they use any available features.
Approach:	They propose a co-operative method which uses introspection to explicitly predict and incorporate the outcome into the selection process.
Outcome:	The proposed model maintains high predictive accuracy and leads to comprehensive rationales.

Copied to clipboard

Zhongyu Wang

Paraphrase Generation with Deep Reinforcement Learning (D18-1)

Challenge:	Existing RAG systems produce suboptimal embeddings and naively insert images into context without adequate visual perception, limiting reasoning capabilities.
Approach:	They propose a novel RAG framework for complex visual reasoning that integrates multimodal large language models with external knowledge to enhance retrieval efficiency.
Outcome:	The proposed framework achieves state-of-the-art performance on multiple benchmarks.

Copied to clipboard

Zichao Li, Xin Jiang, Lifeng Shang, Hang Li

Diversity-Promoting GAN: A Cross-Entropy Based Generative Adversarial Network for Diversified Text Generation (D18-1)

Challenge:	Paraphrase generation is an important but challenging task in natural language processing . traditional symbolic approaches to paraphrase generation include rule-based methods, thesaurus-based approaches and statistical machine translation (SMT)
Approach:	They propose a deep reinforcement learning approach to automatic paraphrase generation . they propose supervised learning and reinforcement learning for evaluators .
Outcome:	The proposed framework outperforms state-of-the-art methods in paraphrase generation on two datasets.

Copied to clipboard

Jingjing Xu, Xuancheng Ren, Junyang Lin, Xu Sun

ARAML: A Stable Adversarial Training Framework for Text Generation (D19-1)

Challenge:	Existing text generation methods tend to produce repeated and ”boring” expressions.
Approach:	They propose a model that assigns low reward for repeatedly generated text and high reward for ”novel” and fluent text, and a novel language-model based discriminator which can distinguish novel text from repeated text without the saturation problem.
Outcome:	The proposed model generates more diverse and informative text than existing baselines on review generation and dialogue generation tasks.

Copied to clipboard

Pei Ke, Fei Huang, Minlie Huang, Xiaoyan Zhu

End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems (2020.emnlp-main)

Challenge:	Existing generative adversarial networks suffer from the instability of reinforcement learning training algorithms such as policy gradient, leading to unstable performance.
Approach:	They propose a framework where the discriminator assigns rewards to samples acquired from a stationary distribution near the data rather than the generator’s distribution.
Outcome:	The proposed framework outperforms state-of-the-art text GANs with a more stable training process.

Copied to clipboard

Siamak Shakeri, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang

A Two-Agent Game for Zero-shot Relation Triplet Extraction (2024.findings-acl)

Challenge:	Existing approaches for synthetic QA data generation have limited or no success in improving the downstream Reading Comprehension task.
Approach:	They propose an end-to-end approach for synthetic QA data generation using a transformer-based encoder-decoder network that is trained end- to-end to generate both answers and questions.
Outcome:	The proposed model outperforms current state-of-the-art methods in the domain adaptation of QA models.

Copied to clipboard

Ting Xu, Haiqin Yang, Fei Zhao, Zhen Wu, Xinyu Dai

Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks (D18-1)

Challenge:	Existing methods for relation triplet extraction rely on labeled data and are limited in their applicability.
Approach:	They propose a two-agent game approach to deliberate and debate unseen relations by two agents, a generator and an extractor.
Outcome:	The proposed method outperforms baseline methods by 6%-16% in F1 scores.

Copied to clipboard

Yaushian Wang, Hung-Yi Lee

SGG: Learning to Select, Guide, and Generate for Keyphrase Generation (2021.naacl-main)

Challenge:	a popular approach to learning data representations involves the use of an auto-encoder that compresses data into a latent-space representation without supervision.
Approach:	They propose to train an auto-encoder that encodes input text into human-readable sentences . they use comprehensible natural language as a latent representation of the input source text .
Outcome:	The proposed auto-encoder can encode input text into human-readable sentences without document-summary pairs.

Copied to clipboard

Jing Zhao, Junwei Bao, Yifan Wang, Youzheng Wu, Xiaodong He, Bowen Zhou

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization (2025.naacl-long)

Challenge:	Existing keyphrase generation approaches synchronously generate present and absent keyphrases without explicitly distinguishing these two categories.
Approach:	They propose to deal with present and absent keyphrases separately with different mechanisms by using a hierarchical neural network with a pointing-based selector and a selection-guided generator.
Outcome:	The proposed model outperforms baselines on four keyphrase generation tasks and shows extensibility in natural language generation tasks.

Copied to clipboard

Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, Ming Gao

R2D2: Robust Data-to-Text with Replacement Detection (2022.emnlp-main)

Challenge:	Existing approaches to optimize RAG generators fail to align with RAG requirements thoroughly.
Approach:	They propose a method for optimizing the RAG generator from multiple preference perspectives to align with RAG requirements comprehensively.
Outcome:	The proposed method improves the performance of RAG generators by incorporating retrieved documents into the prompt.

Copied to clipboard

Linyong Nan, Lorenzo Jaime Flores, Yilun Zhao, Yixin Liu, Luke Benson, Weijin Zou, Dragomir Radev

Joint Generator-Ranker Learning for Natural Language Generation (2023.findings-acl)

Challenge:	Existing methods to mitigate unfaithful text generation are inadequate . data-to-text generation requires a structured input format .
Approach:	They propose a training framework that addresses unfaithful Data-to-Text generation by training a system as a generator and faithfulness discriminator with additional replacement detection and unlikelihood learning tasks.
Outcome:	The proposed training framework improves FeTaQA, LogicNLG, and ToTTo fidelity on D2T systems.

Copied to clipboard

Weizhou Shen, Yeyun Gong, Yelong Shen, Song Wang, Xiaojun Quan, Nan Duan, Weizhu Chen

Reasoning with Ontology Graph: Toward Type-Constrained Knowledge Graph Question Answering (2026.acl-long)

Challenge:	Existing methods for text generation train the generator and ranker individually . existing methods neglect the mutual feedback that could enhance the quality of outputs .
Approach:	They propose a joint training algorithm that integrates the generator and ranker in a single framework.
Outcome:	The proposed algorithm surpasses existing methods on four public datasets across three common generation scenarios.

Copied to clipboard

Yongxue Shan, Jie Peng, Zixuan Dong, Fei Hu, Xiaodong Wang

Knowledge Representation

Challenge:	Existing knowledge graph question answering methods rely on LLM-induced type systems with inconsistent granularity or perform multi-hop reasoning without explicit target-type constraints.
Approach:	They propose a type-constrained knowledge graph question answering framework that reasons over a relation-centric ontology graph.
Outcome:	The proposed framework achieves state-of-the-art and produces ontology-grounded reasoning chains with substantial Hit@1 gains.

FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts (2025.findings-emnlp)

Copied to clipboard

Ziyi Zhang, Zhen Sun, Zongmin Zhang, Jihui Guo, Xinlei He

DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation (2021.acl-long)

Challenge:	Recent research shows that multimodal large language models are vulnerable to jailbreak attacks .
Approach:	They propose a jailbreak attack method based on auto-generated flowcharts . the flowchartings are then combined with a benign textual prompt to execute the attack .
Outcome:	The proposed method achieves an attack success rate of up to 96% via images and 78% via videos across multiple MLLMs.

Copied to clipboard

Xinyu Hua, Ashwin Sreevatsa, Lu Wang

From RAG to Riches: Retrieval Interlaced with Sequence Generation (2024.emnlp-main)

Challenge:	Existing neural generation models fall short of coherence, thus requiring efficient content planning.
Approach:	They propose a generation framework that conducts dynamic planning of content while generating the output based on a novel design of mixed language models.
Outcome:	The proposed model outperforms competing models on argument generation and writing articles using New York Times’ Opinion section.

Copied to clipboard

Palak Jain, Livio Baldini Soares, Tom Kwiatkowski

Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System (2023.emnlp-main)

Challenge:	RICHES interleaves retrieval with sequence generation tasks . traditional approaches chain LLM generation with separate retrieval model .
Approach:	They propose a novel approach that interleaves retrieval with sequence generation tasks . they propose attributed evidence, multi-hop retrievals and interleave thoughts to plan on what to retrieve next .
Outcome:	The proposed approach can work with any Instruction-tuned model, without additional training.

Copied to clipboard

Weizhou Shen, Yingqi Gao, Canbin Huang, Fanqi Wan, Xiaojun Quan, Wei Bi

A Free/Open-Source Morphological Analyser and Generator for Sakha (2022.lrec-1)

Challenge:	generative models struggle to distinguish subtle differences among retrieved knowledge records, resulting in suboptimal quality of generated responses.
Approach:	They propose to use maximum marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision.
Outcome:	The proposed approach improves on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models.

Copied to clipboard

Sardana Ivanova, Jonathan Washington, Francis Tyers

LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification (D19-1)

Challenge:	a morphological transducer for Sakha is being developed for use in downstream tasks . the marginalised language is subject to increasing economic and cultural peril due to climate change .
Approach:	They describe the development of a morphological analyser and generator for Sakha . the transducer has coverage of solidly above 90%, and high precision . it is already being used in downstream tasks such as linguistic maintenance .
Outcome:	The proposed morphological analyser has coverage of 90% and high precision . it is already being used in computer assisted language learning applications .

Copied to clipboard

Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu Sun

CoCGAN: Contrastive Learning for Adversarial Category Text Generation (2022.coling-1)

Challenge:	Existing text classification models are fragile and sensitive to simple perturbations.
Approach:	They propose a generator-classifier adversarial training approach to improve classification models . they use a large-scale lexical knowledge base to generate attacking examples .
Outcome:	The proposed approach outperforms strong baselines and reduces test errors on neural networks.

Copied to clipboard

Xin Sheng, Linli Xu, Yinlong Xu, Changcun Bao, Huang Chen, Bo Ren

IBADR: an Iterative Bias-Aware Dataset Refinement Framework for Debiasing NLU models (2023.emnlp-main)

Challenge:	Experimental results on synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generators.
Approach:	They propose to incorporate contrastive learning into adversarial category text generation by using a discriminator to optimize a contrastive learn objective to capture more flexible data-to-class relations and data- to-data relations among training samples.
Outcome:	The proposed model improves on synthetic and real category text generation datasets.

Copied to clipboard

Xiaoyue Wang, Xin Liu, Lijie Wang, Yaoxiang Wang, Jinsong Su, Hua Wu

Best Student Forcing: A Simple Training Mechanism in Adversarial Language Generation (2020.lrec-1)

Challenge:	Using manual data analysis, dataset refinement approaches are often unable to cover all the potential biased features.
Approach:	They propose an iterative bias-aware dataset refinement framework which debiases NLU models without predefining biased features.
Outcome:	The proposed framework outperforms existing methods and is compatible with model-centric methods.

Copied to clipboard

Jonathan Sauder, Ting Hu, Xiaoyin Che, Goncalo Mordido, Haojin Yang, Christoph Meinel

When Generative Adversarial Networks Meet Sequence Labeling Challenges (2024.emnlp-main)

Challenge:	Language models trained with Maximum Likelihood Estimation (MLE) have been considered as a mainstream solution in Natural Language Generation (NLG) however, they are reportedly suffering from training instability and mode collapse, and therefore outperform conventional MLE models.
Approach:	They propose a method to improve Generative Adversarial Nets (GANs) using best student forcing and discriminators to increase training stability and sample diversity.
Outcome:	The proposed techniques outperform MLE models and outperformed existing approaches in terms of sample diversity and training stability.

Copied to clipboard

Yu Tong, Ge Chen, Guokai Zheng, Rui Li, Jiang Dazhi

Towards Comprehensive Description Generation from Factual Attribute-value Tables (P19-1)

Challenge:	Existing approaches for sequence labeling use a feature extractor and sequence tagger . a recent study shows that SLGAN is versatile and highly effective .
Approach:	They propose a framework that harnesses the capabilities of Generative Adversarial Networks to address sequence labeling challenges.
Outcome:	The proposed framework exhibits strong adaptability to various sequence labeling tasks.

Copied to clipboard

Tianyu Liu, Fuli Luo, Pengcheng Yang, Wei Wu, Baobao Chang, Zhifang Sui

Uni-Parser: Unified Semantic Parser for Question Answering on Knowledge Base and Database (2022.emnlp-main)

Challenge:	Existing models for comprehensive descriptions for factual attribute-value tables might suffer from missing key attributes and groundless information problems.
Approach:	They propose a force attention method to encourage the generator to pay more attention to uncovered attributes to avoid potential key attributes missing.
Outcome:	The proposed model outperforms the state-of-the-art baselines on automatic and human evaluation.

Copied to clipboard

Ye Liu, Semih Yavuz, Rui Meng, Dragomir Radev, Caiming Xiong, Yingbo Zhou

Question Answering

Challenge:	Existing approaches on semantic parsing suffer from exponential growth of logical form candidates and can hardly generalize to unseen data.
Approach:	They propose a unified semantic parser for question answering on KB and DB . they define the primitive as the essential element in their framework .
Outcome:	The proposed framework can predict logical forms by altering and composing top-ranked primitives with different operations.

Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games (2025.findings-emnlp)

Copied to clipboard

Niv Eckhaus, Uri Berger, Gabriel Stanovsky

Challenge:	LLMs are used in synchronous communication, where a human user and a model communicate in alternating turns.
Approach:	They develop an adaptive asynchronous LLM agent consisting of two modules that decide what to say and a scheduler that decides when to say it.
Outcome:	The proposed agent performs on par with human players in online Mafia games and in its ability to blend in with the other human players.

What are the Generator Preferences for End-to-end Task-Oriented Dialog System? (2024.emnlp-main)

Copied to clipboard

Wanshi Xu, Xianwei Zhuang, Zhanpeng Chen, Zhihong Zhu, Xuxin Cheng, Yuexian Zou

Learning Rhyming Constraints using Structured Adversaries (D19-1)

Challenge:	Existing methods to improve the accuracy of entity retrieval are not effective.
Approach:	They propose a framework that improves the performance of task-oriented dialogue systems by obtaining fine-grained matching information between contexts and entities and extracting the entity attribute shift matrix as preference signals.
Outcome:	The proposed framework outperforms existing methods and improves the quality of the dialogue.

Copied to clipboard

Harsh Jhamtani, Sanket Vaibhav Mehta, Jaime Carbonell, Taylor Berg-Kirkpatrick

One2Set + Large Language Model: Best Partners for Keyphrase Generation (2024.emnlp-main)

Challenge:	Existing approaches to text generation fail to capture higher-level structure in text, for example, rhyming patterns.
Approach:	They propose a method that uses a structured discriminator to learn rhyming constraints from poetry . the discriminator compares two English poetry datasets based on a learned similarity matrix .
Outcome:	The proposed method can learn rhyming patterns in English poetry without explicit phonetic information.

Copied to clipboard

Liangying Shao, Liang Zhang, Minlong Peng, Guoqi Ma, Hao Yue, Mingming Sun, Jinsong Su

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts (2025.acl-long)

Challenge:	Existing selection methods make redundant selections, causing poor recall and accuracy.
Approach:	They propose a framework to generate keyphrases from a one2set-based model and an LLM as selector.
Outcome:	The proposed framework surpasses state-of-the-art models in absent keyphrase prediction.

Copied to clipboard

Mingyan Wu, Zhenghao Liu, Yukun Yan, Xinze Li, Shi Yu, Zheni Zeng, Yu Gu, Ge Yu

Meta-Reinforced Multi-Domain State Generator for Dialogue Systems (2020.acl-main)

Challenge:	Retrieval-Augmented Generation (RAG) models enable Large Language Models to access external knowledge.
Approach:	They propose a knowledge refinement method that incorporates reranking signals to generate CoT-based summarization based on query and retrieval documents.
Outcome:	RankCoT generates CoT-based summarization based on query and all retrieval documents . Rank CoT incorporates a self-reflection mechanism that refines the outputs .

Copied to clipboard

Yi Huang, Junlan Feng, Min Hu, Xiaoting Wu, Xiaoyu Du, Shuo Ma

A Preliminary Exploration of GANs for Keyphrase Generation (2020.emnlp-main)

Challenge:	Existing methods to train a multi-domain dialogue state tracker are lacking in accuracy.
Approach:	They propose a Meta-Reinforced Multi-Domain State Generator to train a DST meta-learning model with a few domains as source domains and a new domain as target domain.
Outcome:	The proposed system outperforms the traditional training approach with extremely little training data in target domain.

Copied to clipboard

Avinash Swaminathan, Haimin Zhang, Debanjan Mahata, Rakesh Gosangi, Rajiv Ratn Shah, Amanda Stent

Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning (P19-1)

Challenge:	Existing studies on extractive keyphrases have shown promising results, but the results suggest that there is room for improvement.
Approach:	They propose a new keyphrase generation approach using Generative Adversarial Networks (GANs) their model produces a sequence of keyphrases and a discriminator distinguishes between human-curated and machine-generated keyphrase.
Outcome:	The proposed model outperforms the state-of-the-art generative models on benchmark datasets and is comparable to the best performing extractive models.

Copied to clipboard

Zhihao Fan, Zhongyu Wei, Siyuan Wang, Xuanjing Huang

Where Am I From? Identifying Origin of LLM-generated Content (2024.emnlp-main)

Challenge:	Existing research on image captioning generates frequent n-grams with irrelevant words.
Approach:	They propose to construct an image-grounded vocabulary incorporating visual information and relations among words into the decoding process directly.
Outcome:	The proposed framework is compared with state-of-the-art models on MS COCO and Flickr30k and shows that it is more efficient than existing models.

Copied to clipboard

Liying Li, Yihan Bai, Minhao Cheng

Challenge:	Generative models have produced high-quality content, but they pose security risks . a new framework for deep learning systems enables the tracing of AI-generated content back to its source .
Approach:	They propose a digital forensics framework that embeds a secret watermark into the generated output and a "depth watermark" this watermark strengthens the link between content and generator, enabling accurate tracing while maintaining the quality of the generated content.
Outcome:	The proposed framework ensures accurate tracing while maintaining quality of generated content.

Unsupervised Selective Rationalization with Noise Injection (2023.acl-long)

Copied to clipboard

Adam Storek, Melanie Subbiah, Kathleen McKeown

MGR: Multi-generator Based Rationalization (2023.acl-long)

Challenge:	Unsupervised selective rationalization produces rationales alongside predictions, but does not ensure that the rationale contains a plausible explanation for the prediction.
Approach:	They propose a technique that injects noise between a rationale generator and a predictor to limit generation of implausible rationales.
Outcome:	The proposed method achieves significant improvements in plausibility and task accuracy over the state-of-the-art models while maintaining or improving model faithfulness.

Copied to clipboard

Wei Liu, Haozhao Wang, Jun Wang, Ruixuan Li, Xinyang Li, YuanKai Zhang, Yang Qiu

Challenge:	Existing approaches to explain NLP models have two key challenges: spurious correlation and degeneration.
Approach:	They propose a rationalization framework using a generator and a predictor to construct a self-explaining NLP model with spurious correlation and degeneration as key challenges.
Outcome:	The proposed method improves the F1 score by 20.9% compared to state-of-the-art methods.

Neural Topic Modeling with Cycle-Consistent Adversarial Training (2020.emnlp-main)

Copied to clipboard

Xuemeng Hu, Rui Wang, Deyu Zhou, Yuxuan Xiong

Debias NLU Datasets via Training-free Perturbations (2023.findings-emnlp)

Challenge:	Recent advances on deep generative models have attracted significant interest in neural topic modeling.
Approach:	They propose an adversarial-neural topic model which uses Dirichlet prior to capture the semantic patterns in latent topics.
Outcome:	The proposed models outperform competing models on unsupervised/supervised topic modeling and text classification.

Copied to clipboard

Qi Guo, Yuanhang Tang, Yawen Ouyang, Zhen Wu, Xinyu Dai

When is Tree Search Useful for LLM Planning? It Depends on the Discriminator (2024.acl-long)

Challenge:	Existing approaches to debiase NLU models capture biased features that are independent of the task but spuriously correlated to labels.
Approach:	They propose a framework that conducts training-free perturbations on samples containing biased features to Debias NLU Datasets.
Outcome:	The proposed framework shows competitive performance with previous state-of-the-art debiasing strategies.

Copied to clipboard

Ziru Chen, Michael White, Ray Mooney, Ali Payani, Yu Su, Huan Sun

Knowing When Not to Answer: Lightweight KB-Aligned OOD Detection for Safe RAG (2026.acl-long)

Challenge:	Existing methods to build language agents that can plan efficiently and accurately have not met the needs of advanced planning methods to achieve such improvements.
Approach:	They propose to use iterative correction and tree search to solve multi-step problems in a language agent framework with three components: a generator, a discriminator, and a planning method.
Outcome:	The proposed methods improve performance on two tasks, text-to-SQL parsing and mathematical reasoning, while using discriminators with 90% accuracy.

Copied to clipboard

Ilias Triantafyllopoulos, Renyi Qu, Salvatore Giorgi, Brenda Curtis, Lyle Ungar, João Sedoc

Target-to-Source Augmentation for Aspect Sentiment Triplet Extraction (2023.emnlp-main)

Challenge:	Retrieval-Augmented Generation (RAG) systems are increasingly deployed in high-stakes domains where safety depends on how a system answers . out-of-domain (OOD) queries can impair performance and safety .
Approach:	They propose to use lightweight, KB-aligned OOD detection as an always-on gate for RAG systems.
Outcome:	The proposed method scores queries in a compact subspace selected either by explained-variance retention (EVR) or by a separability-driven -test ranking.

Copied to clipboard

Yice Zhang, Yifan Yang, Meng Li, Bin Liang, Shiwei Chen, Ruifeng Xu

Sentiment Analysis

Challenge:	Aspect Sentiment Triplet Extraction (ASTE) is an important task in sentiment analysis, but data scarcity limits performance of existing methods.
Approach:	They propose a target-to-source augmentation approach to alleviate the issue of data scarcity in Aspect Sentiment Triplet Extraction (ASTE) they use fluency and alignment discriminators to provide feedback and use this feedback to optimize the generator.
Outcome:	The proposed approach significantly improves the performance of existing methods.

RichRAG: Crafting Rich Responses for Multi-faceted Queries in Retrieval-Augmented Generation (2025.coling-main)

Copied to clipboard

Shuting Wang, Xin Yu, Mang Wang, Weipeng Chen, Yutao Zhu, Zhicheng Dou

SHARE: a System for Hierarchical Assistive Recipe Editing (2022.emnlp-main)

Challenge:	Existing studies focus on question scenarios with clear user intents and concise answers, but it is prevalent that users issue broad, open-ended queries with diverse sub-intents.
Approach:	They propose a framework that includes a sub-aspect explorer and a multi-faceted retriever to build a candidate pool of diverse external documents related to these sub-intents.
Outcome:	The proposed framework provides comprehensive and satisfying responses to users on two publicly available datasets.

Copied to clipboard

Shuyang Li, Yufei Li, Jianmo Ni, Julian McAuley

Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion (2021.emnlp-main)

Challenge:	Existing recipe websites do not provide options for users with dietary restrictions . a growing population follows some form of dietary restriction, with many people following it for a variety of reasons .
Approach:	They propose a system for hierarchical assistive recipe editing that performs simultaneous ingredient substitution before generating natural-language steps using the edited ingredients.
Outcome:	The proposed system can adapt a recipe to satisfy a user-specified dietary constraint.

Copied to clipboard

Lingyong Yan, Xianpei Han, Le Sun

Handwritten Character Generation using Y-Autoencoder for Character Recognition Model Training (2022.lrec-1)

Challenge:	Existing methods for entity set expansion define the expansion boundary using seed-based distance metrics, which are hard to adjust due to the extremely sparse supervision.
Approach:	They propose a new learning method for bootstrapping which jointly models the bootstraping process and boundary learning process in a GAN framework.
Outcome:	The proposed method achieves the new state-of-the-art performance for entity set expansion.

Copied to clipboard

Tomoki Kitagawa, Chee Siang Leow, Hiromitsu Nishizaki

HGAdapter: Hypergraph-based Adapters in Language Models for Code Summarization and Clone Detection (2025.findings-emnlp)

Challenge:	re-emergence of deep learning since third winter of artificial intelligence has led to mainstreaming of deep-learning systems that use large amounts of data to train a model.
Approach:	They propose a Y-Autoencoder-based handwritten character generator to generate Japanese Hiragana characters with a single image to increase the amount of data needed for character recognition.
Outcome:	The proposed system generates Japanese Hiragana characters with a single image . the results show that the Y-AE-based generator produces an improved F1 score .

Copied to clipboard

Guang Yang, Yujie Zhu

Automatic Transmission for LLM Tiers: Optimizing Cost and Accuracy in Large Language Models (2025.findings-acl)

Challenge:	Pre-trained language models (PLMs) are increasingly being applied to code-related tasks.
Approach:	They propose a hypergraph-based adapter to capture high-order data correlations in code tokens . they improve hypergraph neural networks and combine it with adapter tuning to propose adapter .
Outcome:	The proposed adapter can encode high-order data correlations and be inserted into PLMs to enhance performance.

Copied to clipboard

Injae Na, Keonwoong Noh, Woohwan Jung

What Comes Next? Evaluating Uncertainty in Neural Text Generators Against Human Production Variability (2023.emnlp-main)

Challenge:	Large Language Models (LLMs) are powerful tools for a wide range of natural language tasks.
Approach:	They propose an LLM automatic transmission framework that automatically selects LLM tiers without training.
Outcome:	The proposed framework achieves superior performance while reducing costs.

Copied to clipboard

Mario Giulianelli, Joris Baan, Wilker Aziz, Raquel Fernández, Barbara Plank

Generator-Assistant Stepwise Rollback Framework for Large Language Model Agent (2025.emnlp-main)

Challenge:	In Natural Language Generation tasks, multiple communicative goals are plausible and any goal can be put into words, or produced, in multiple ways.
Approach:	They characterise the extent to which human production varies lexically, syntactically, and semantically across four NLG tasks, connecting human production variability to aleatoric or data uncertainty.
Outcome:	The proposed model can be calibrated to human production variability using multiple samples and, when possible, multiple references.

Copied to clipboard

Xingzuo Li, Kehai Chen, Yunfei Long, Xuefeng Bai, Yong Xu, Min Zhang

More Than Spoken Words: Nonverbal Message Extraction and Generation (2023.emnlp-main)

Challenge:	Existing approaches to integrate thoughts with actions can cause irreversible error propagation . Xi et al., 2023; Zhang eet coll., 2023) have focused on enhancing large language model (LLM) agents capable of helping humans tackle real-world challenges.
Approach:	They propose a framework called Generator-Assistant Stepwise Rollback to induce better decision-making for LLM agents by integrating a generator and an assistant to examine each action produced by the generator.
Outcome:	The proposed framework improves on three widely used benchmarks and can integrate seamlessly with other methods.

Copied to clipboard

Dian Yu, Xiaoyang Wang, Wanshun Chen, Nan Du, Longyue Wang, Haitao Mi, Dong Yu

Reinforced IR: A Self-Boosting Framework For Domain-Adapted Information Retrieval (2025.acl-long)

Challenge:	Existing studies focus on extracting NMs from small-scale well-structured corpora such as movie scripts wherein NM is enclosed in parentheses by scriptwriters, which greatly decreases the difficulty of extraction.
Approach:	They propose to extract nonverbal messages (NMs) from written text and NMs from spoken text by using a semi-supervised learning algorithm.
Outcome:	The extracted NMs can generate more relevant, valid, and factually consistent NM than the purely supervised generator.

Copied to clipboard

Chaofan Li, Jianlyu Chen, Yingxia Shao, Chaozhuo Li, Quanqing Xu, Defu Lian, Zheng Liu

Gradient-Guided Multi-Judge Prompt Optimization (2026.acl-long)

Challenge:	Existing retrieval methods struggle with highly specialized situations that require extensive domain expertise.
Approach:	They propose a method that integrates additional information from an LLM-based generator to enhance query performance and train the retriever to better discriminate the relevant documents identified by the generator.
Outcome:	The proposed method outperforms existing domain adaptation methods by a large margin and leads to substantial improvements in retrieval quality across a wide range of application scenarios.

Copied to clipboard

ChenZhuo Zhao, Xinda Wang, Pu Zhao, Yue Huang, Junting Lu, Ziqian Liu, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang

s3: You Don’t Need That Much Data to Train a Search Agent via RL (2025.emnlp-main)

Challenge:	Existing approaches to prompt optimization trade off signal quality against computational cost.
Approach:	They propose a framework that uses a first-order gradient approximation to score segment importance in a continuous masking direction.
Outcome:	The proposed framework improves efficiency and robustness by using a first-order gradient approximation to score segment importance in a continuous masking direction.

Copied to clipboard

Pengcheng Jiang, Xueqiang Xu, Jiacheng Lin, Jinfeng Xiao, Zifeng Wang, Jimeng Sun, Jiawei Han

DiffusionAttacker: Diffusion-Driven Prompt Manipulation for LLM Jailbreak (2025.emnlp-main)

Challenge:	Existing approaches to optimize retrieval using search-only metrics ignore downstream utility and fine-tune entire LLM to jointly reason and retrieve limit retrieval utility and compatibility with frozen or proprietary models.
Approach:	They propose a lightweight, model-agnostic framework that decouples the searcher from the generator and trains the search user using a Gain Beyond RAG reward.
Outcome:	The proposed framework outperforms baselines trained on over 70 more data with 2.4k training samples.

Copied to clipboard

Hao Wang, Hao Li, Junda Zhu, Xinyuan Wang, Chengwei Pan, Minlie Huang, Lei Sha

BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers? (2026.acl-long)

Challenge:	Large Language Models (LLMs) are susceptible to generating harmful content when prompted with carefully crafted inputs, a vulnerability known as LLM jailbreaking.
Approach:	They propose an end-to-end generative approach for jailbreak rewriting inspired by diffusion models that uses a sequence-tosequence (seq2sequ) diffusion model as a generator, conditioning on the original prompt and guiding the denoising process with a novel attack loss.
Outcome:	Experiments on Advbench and Harmbench show that the proposed method outperforms autoregressive jailbreak models across evaluation metrics including ASR, fluency, diversity and diversity.

Copied to clipboard

Fengqing Jiang, Yichen Feng, Yuetai Li, Luyao Niu, Basel Alomair, Radha Poovendran

Challenge:	Existing evidence suggests that LLMs are not able to detect scientifically unsound work from malicious or poorly designed research agents.
Approach:	They develop a framework that evaluates whether fabrication-oriented paper generation agents can deceive multi-model LLM review systems.
Outcome:	The proposed framework shows that fabricated papers achieve acceptance rates up to 18% . the framework shows only marginal improvements, with detection accuracy barely exceeding random chance.

S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA (2026.acl-long)

Copied to clipboard

Minghan Li, Junjie Zou, Xinxuan Lv, Chao Zhang, Guodong Zhou

Question Answering

Challenge:	Retrieval-augmented generation grounds language models in external evidence, but multi-hop question answering remains difficult . iterative pipelines must control what to retrieve next and when evidence is adequate.
Approach:	They propose an iterative framework with an explicit controller, S2G-Judge . they map structured gap items into the next retrieval query to produce stable retrieval trajectories .
Outcome:	Experiments on TriviaQA, HotpotQA, and 2WikiMultiHopQA show that S2G-RAG improves multi-hop QA performance and robustness under multi-turn retrieval.

Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation (2026.acl-long)

Copied to clipboard

Qianchi Zhang, Hainan Zhang, Liang Pang, Hong-Wei Zheng, Zhiming Zheng

Third-Person Appraisal Agent: Simulating Human Emotional Reasoning in Text with Large Language Models (2025.findings-emnlp)

Challenge:	Existing RAG methods focus on enhancing LLM robustness to low-quality retrieval, but neither address permutation sensitivity.
Approach:	They propose a method that exploits permutation sensitivity to mitigate hallucinations in Large Language Models.
Outcome:	The proposed model improves answer accuracy, reasoning consistency, and generalization across datasets, retrievers, and input lengths compared with strong baselines.

Copied to clipboard

Simin Hong, Jun Sun, Hongyang Chen

Beyond Local vs. External: A Game-Theoretic Framework for Trustworthy Knowledge Acquisition (2026.findings-acl)

Challenge:	Emotional reasoning is essential for improving human-AI interactions, especially in mental health support and empathetic systems.
Approach:	They propose a third-person appraisal agent that simulates human-like emotional reasoning through three phases: Primary Appraisal, Secondary Appraisals, and Reappraisal.
Outcome:	The proposed model outperforms baseline LLMs in various emotional reasoning tasks, demonstrating superior generalization and interpretability.

Copied to clipboard

Rujing Yao, Yufei Shi, Yang Wu, Ang Li, Zhuoren Jiang, XiaoFeng Wang, Haixu Tang, Xiaozhong Liu

Chinese Inertial GAN for Handwriting Signal Generation and Recognition (2025.acl-long)

Challenge:	Cloud-hosted Large Language Models (LLMs) offer unmatched reasoning capabilities and dynamic knowledge, yet submitting raw queries to these services can expose sensitive user intent.
Approach:	They propose a framework that formulates the trade-off between knowledge utility and privacy as a strategic game.
Outcome:	The proposed framework reduces intent leakage while maintaining high-fidelity answer quality.

Copied to clipboard

Yifeng Wang, Yi Zhao

CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution (2026.acl-long)

Challenge:	Inertial sensors can measure the acceleration and angular velocity of moving objects and are widely used in electronic devices such as smartphones, smartwatches, and fitness bands.
Approach:	They propose to use Chinese glyph encoding, forced optimal transport, and semantic relevance alignment to acquire unlimited training samples for Chinese inertial writing recognition.
Outcome:	The proposed system improves the performance of six widely used classifiers from 6.7% to 98.4%.

Copied to clipboard

Teng Pan, Yuchen Yan, Zixuan Wang, Ruiqing Zhang, Guiyang Hou, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen

CPR-RAG: Clinical Prior-Regularized Retrieval for Anatomy-Aware 3D CT Report Generation (2026.acl-long)

Challenge:	Label-free reinforcement learning enables large language models to improve reasoning capabilities . but as training maximizes self-consistency, output diversity collapses, authors say . authors propose a framework where a single model alternates between generator and verifier roles .
Approach:	They propose a framework where a model alternates between generator and verifier roles, bootstrapping each other.
Outcome:	Experiments show that CoVerRL outperforms label-free baselines on reasoning benchmarks . the framework can be used to improve reasoning abilities without ground-truth supervision .

Copied to clipboard

Sungkyu Yang, Kang-Min Kim, Mansu Kim

Improving LLM Code Reasoning via Semantic Equivalence Self-Play with Formal Verification (2026.findings-acl)

Challenge:	Existing approaches to grounding radiology reports from 3D volumetric data are limited due to visual-semantic ambiguity and lack of "normal" context.
Approach:	They propose a model-agnostic retrieval-augmented generation framework that integrates clinical priors into the retrieval process.
Outcome:	The proposed model improves clinical efficacy across state-of-the-art models.

Copied to clipboard

Poon Tsz Nok, Antonio Valerio Miceli Barone

LLM-Powered Benchmark Factory: Reliable, Generic, and Efficient (2026.acl-long)

Challenge:	Existing approaches to training large language models fail to capture deep semantic properties and edge cases.
Approach:	They propose a framework that leverages Liquid Haskell proofs for validating equivalence and execution-based counterexamples for inequivalent training.
Outcome:	The proposed framework achieves 13.3pp accuracy gain on EquiBench and consistent gains on PySecDB.

Copied to clipboard

Peiwen Yuan, Shaoxiong Feng, Yiwei Li, Xinglin Wang, Yueqi Zhang, Jiayi Shi, Chuyi Tan, Boyuan Pan, Yao Hu, Kan Li

D-RAG: Differentiable Retrieval-Augmented Generation for Knowledge Graph Question Answering (2025.emnlp-main)

Challenge:	Using generic and efficient benchmark generators, human annotators are limited by inefficiency . current benchmark generator methods rely on seed signals, leading to long cycles and high costs .
Approach:	They propose a framework to evaluate LLMs as generic benchmark generators and integrate them as BenchMaker.
Outcome:	The proposed framework achieves comparable performance to human-annotated benchmarks on most metrics.

Copied to clipboard

Guangze Gao, Zixuan Li, Chunfeng Yuan, Jiawei Li, Wu Jianzhuo, Yuehao Zhang, Xiaolong Jin, Bing Li, Weiming Hu

Explain the Synth: Interpretable Evaluation of LLM Data Synthesis (2026.acl-long)

Challenge:	Existing approaches to Knowledge Graph Question Answering (KGQA) use Retrieval-Augmented Generation (RAG) but subgraph selection process is non-differentiable, preventing end-to-end training of the retriever and the generator.
Approach:	They propose a Differentiable RAG approach that optimizes the retriever and the generator for KGQA.
Outcome:	The proposed approach outperforms state-of-the-art approaches on WebQSP and CWQ.

Copied to clipboard

Yue Yang, Fan Yang, Yu Bai, Hao Wang

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) are increasingly used to generate tabular data.
Approach:	They propose a framework that uses a rule-based model as a shared explanatory language to examine the explanation of real versus synthetic data.
Outcome:	The proposed framework compares the explanatory structure induced by real versus synthetic data.

Rethinking Retrieval-Augmented Generation as a Cooperative Decision-Making Problem (2026.findings-acl)

Copied to clipboard

Lichang Song, Ting Long, Yi Chang