GENERATION MODEL

Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering (2021.findings-emnlp)

Challenge:	Knowledge-enriched text generation poses unique challenges in modeling and learning . a roadmap will outline the state-of-the-art methods to tackle these challenges .
Approach:	They propose a roadmap to tackle the challenges of knowledge-enriched text generation . they will dive deep into various technical components to illustrate how to represent knowledge .
Outcome:	This tutorial outlines the state-of-the-art methods to tackle the problem . it aims to show how to represent knowledge, feed knowledge into a generation model, evaluate results .

Copied to clipboard

Chenyu You, Nuo Chen, Yuexian Zou

DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation (2021.naacl-demos)

Challenge:	Experimental results show that our model achieves state-of-the-art results on three SQA benchmarks.
Approach:	They propose a self-supervised training stage and a contrastive representation learning stage for spoken question answering with auxiliary tasks and augmentation strategies.
Outcome:	The proposed model achieves state-of-the-art results on three SQA benchmarks.

Copied to clipboard

Sarik Ghazarian, Zixi Liu, Tuhin Chakrabarty, Xuezhe Ma, Aram Galstyan, Nanyun Peng

Boundary Matters: Leveraging Structured Text Plots for Long Text Outline Generation (2025.findings-emnlp)

Challenge:	Recent advances in transformer-based language models and their applications to dialogue systems have succeeded to generate fluent and human-like responses.
Approach:	They propose to leverage conversational lines as controllable and informative content-planning elements to guide the generation model produce engaging and informative responses.
Outcome:	The proposed system generates engaging and informative responses using convlines as controllable and informative content-planning elements.

Copied to clipboard

Yuanchi Ma, Jiamou Liu, Hui He, Libo Zhang, Haoyuan Li, Zhendong Niu

Challenge:	Existing methods for generating readable outlines are inability to segment long texts .
Approach:	They propose an unsupervised framework to guide large language model outline generation . framework ensures each structured plot encapsulates complete causality by accurately identifying plot boundaries.
Outcome:	The proposed framework ensures that each structured plot encapsulates complete causality by accurately identifying plot boundaries.

Generating Sentential Arguments from Diverse Perspectives on Controversial Topic (D19-50)

Copied to clipboard

ChaeHun Park, Wonsuk Yang, Jong Park

Challenge:	ArgDiver model generates high-quality sentential arguments from multiple perspectives . retrieval-based systems do not have sufficient flexibility for input with missing keywords or topics unseen .
Approach:	They propose a neural method to generate sentential arguments from multiple perspectives . their model generates high-quality sentential argument, but shows higher diversity .
Outcome:	The proposed model generates high-quality sentential arguments from multiple perspectives . it shows that it can provide diverse perspectives on a controversial topic .

Yu Sheng: Human-in-Loop Classical Chinese Poetry Generation System (2023.eacl-demo)

Copied to clipboard

Jingkun Ma, Runzhe Zhan, Derek F. Wong

Improving Chinese Story Generation via Awareness of Syntactic Dependencies and Semantics (2022.aacl-short)

Challenge:	Existing systems for poetry generation are not flexible in polishing and customization.
Approach:	They propose a web-based poetry generation system that provides customization options for users with different backgrounds to engage in the process of poetry composition.
Outcome:	The proposed system can generate and polish classical Chinese poetry compared to other vanilla models.

Copied to clipboard

Henglin Huang, Chen Tang, Tyler Loakman, Frank Guerin, Chenghua Lin

Representation Learning

Challenge:	Current neural models for Chinese story generation struggle to generate high-quality long text narratives due to ambiguity in syntactically parsing the Chinese language.
Approach:	They propose a framework that enhances the feature capturing mechanism by informing the generation model of dependencies between words and additionally augmenting the semantic representation learning through synonym denoising training.
Outcome:	The proposed framework outperforms the state-of-the-art Chinese generation models on all evaluation metrics, showing that it enhances dependency and semantic representation learning.

Review-based Question Generation with Adaptive Instance Transfer and Augmentation (2020.acl-main)

Copied to clipboard

Qian Yu, Lidong Bing, Qiong Zhang, Wai Lam, Luo Si

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

Challenge:	Existing methods to generate questions for verbose reviews are inefficient for potential consumers . lack of training data hinders efficient review digestion, authors say .
Approach:	They propose to generate questions that can be answered by corresponding review sentences . they propose an iterative learning framework with adaptive instance transfer and augmentation .
Outcome:	The proposed model can generate questions that can be answered by review sentences . it is easier to find critical review parts that are important for potential consumers .

Copied to clipboard

Zihao Fu, Bei Shi, Lidong Bing, Wai Lam

Event-Centric Query Expansion in Web Search (2023.acl-industry)

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

Yanan Zhang, Weijie Cui, Yangfan Zhang, Xiaoling Bai, Zhe Zhang, Jin Ma, Xiang Chen, Tianhua Zhou

Information Retrieval

Challenge:	Existing studies rely on long-term search log mining to improve search experience . EQE system is a novel event retrieval framework that can select the best expansion from a significant amount of potential events quickly and accurately.
Approach:	They propose a QE system that uses a four-stage event retrieval framework . they collect news headlines and then refine a dual-tower semantic model to serve as an encoder .
Outcome:	The proposed system can select the best expansion from a significant amount of potential events quickly and accurately.

Metric-guided Distillation: Distilling Knowledge from the Metric to Ranker and Retriever for Generative Commonsense Reasoning (2022.emnlp-main)

Copied to clipboard

Xingwei He, Yeyun Gong, A-Long Jin, Weizhen Qi, Hang Zhang, Jian Jiao, Bartuer Zhou, Biao Cheng, Sm Yiu, Nan Duan

Building Adaptive Acceptability Classifiers for Neural NLG (2021.emnlp-main)

Challenge:	Existing work on commonsense generation requires models to have relational reasoning and compositional generalization capabilities.
Approach:	They propose a metric distillation rule to distill knowledge from a standard metric to a ranker and transfer it to re-ranking a retriever.
Outcome:	The proposed method surpasses the previous SOTA.

Copied to clipboard

Soumya Batra, Shashank Jain, Peyman Heidari, Ankit Arun, Catharine Youngs, Xintong Li, Pinar Donmez, Shawn Mei, Shiunzu Kuo, Vikas Bhardwaj, Anuj Kumar, Michael White

Information Retrieval

Challenge:	Existing approaches to generate synthetic data using simple sentence transformations and/or model-based techniques may not generate realistic error samples with respect to the NLG models.
Approach:	They propose a framework to train models to classify acceptability of responses generated by natural language generation models using a 2-stage approach . they use existing sentence transformations to generate samples that better resemble the output of the generation models.
Outcome:	The proposed approach outperforms existing techniques and can be used in few-shot settings using self-training.

Learning Health-Bots from Training Data that was Automatically Created using Paraphrase Detection and Expert Knowledge (2020.coling-main)

Copied to clipboard

Anna Liednikova, Philippe Jolivet, Alexandre Durand-Salmon, Claire Gardent

Paraphrasing

Challenge:	Current dialog models require large quantities of training data due to privacy issues . current methods require large amounts of training and are even scarcer in the health domain .
Approach:	They propose a method for creating dialog corpora from physician-patient interaction data . they combine expert knowledge provided by physicians with automatic paraphrase extraction techniques .
Outcome:	The proposed method outperforms existing models in the health domain . it provides a natural way of guiding learning and improves quality of human-machine interactions .

Using Semantic Similarity as Reward for Reinforcement Learning in Sentence Generation (P19-2)

Copied to clipboard

Go Yasui, Yoshimasa Tsuruoka, Masaaki Nagata

Read before Generate! Faithful Long Form Question Answering with Machine Reading (2022.findings-acl)

Challenge:	Existing models for sentence generation use cross-entropy loss as the loss function . however, cross-etropy is unable to evaluate sentences as a whole and lacks flexibility . et al., 2018: a novel approach to improve sentence generation models .
Approach:	They propose a method to train a model using estimated semantic similarity between output and reference sentences to alleviate cross-entropy loss problems.
Outcome:	The proposed model improves the BLEU scores from the baseline LSTM NMT model.

Copied to clipboard

Dan Su, Xiaoguang Li, Jindi Zhang, Lifeng Shang, Xin Jiang, Qun Liu, Pascale Fung

Natural Language Interfaces

Challenge:	Long-form question answering (LFQA) generates a paragraph-length answer for a given question.
Approach:	They propose a framework that jointly models answer generation and machine reading.
Outcome:	The proposed model generates a more factually accurate answer from millions of documents retrieved from a large dataset.

NovaCOMET: Open Commonsense Foundation Models with Symbolic Knowledge Distillation (2023.findings-emnlp)

Copied to clipboard

Peter West, Ronan Bras, Taylor Sorensen, Bill Lin, Liwei Jiang, Ximing Lu, Khyathi Chandu, Jack Hessel, Ashutosh Baheti, Chandra Bhagavatula, Yejin Choi

Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (P19-1)

Challenge:	a new commonsense knowledge model, NovaCOMET, combines knowledge and general task models.
Approach:	They propose an open commonsense knowledge model that combines knowledge and general task models.
Outcome:	The proposed model matches or exceeds existing knowledge models on commonsense reasoning tasks.

Copied to clipboard

Anusha Balakrishnan, Jinfeng Rao, Kartikeya Upasani, Michael White, Rajen Subba

El Volumen Louder Por Favor: Code-switching in Task-oriented Semantic Parsing (2021.eacl-main)

Challenge:	Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems.
Approach:	They propose using tree-structured semantic representations for better discourse-level structuring and sentence-level planning and introduce a challenging dataset using this representation for the weather domain.
Outcome:	The proposed model improves discourse-level structuring and sentence-level planning on a weather domain and can be decoded to improve semantic correctness.

Copied to clipboard

Arash Einolghozati, Abhinav Arora, Lorena Sainz-Maza Lecanda, Anuj Kumar, Sonal Gupta

A Dataset and Baselines for Multilingual Reply Suggestion (2021.acl-long)

Challenge:	Code-switching (CS) is the alternation of languages within an utterance or conversation.
Approach:	They propose to use translation-and-align and augment with a generation model followed by match-and filter to improve CS generalizability of cross-lingual models when data for only one language is available.
Outcome:	The proposed models improve when only English data is available alongside zero or a few CS training instances.

Copied to clipboard

Mozhi Zhang, Wei Wang, Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah

Multilinguality

Challenge:	Reply suggestion models help users process emails and chats faster.
Approach:	They present a multilingual reply suggestion dataset with ten languages . they build a generation model and a retrieval model as baselines for MRS .
Outcome:	The proposed model complements existing benchmarks for cross-lingual generalization . the model has different strengths in the English monolingual setting and requires different strategies to generalize across languages.

LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting (2023.findings-acl)

Copied to clipboard

Rita Ramos, Bruno Martins, Desmond Elliott

Counterfactual Data Augmentation via Perspective Transition for Open-Domain Dialogues (2022.emnlp-main)

Challenge:	Existing captioning models are mostly available on English or are specialised for other high-resource languages.
Approach:	They propose an image-blind few-shot multilingual captioning model that prompts a language model with retrieved captions.
Outcome:	The proposed model is competitive with fully-supervised multilingual captioning models without requiring any supervised training on captioning data.

Copied to clipboard

Jiao Ou, Jinchao Zhang, Yang Feng, Jie Zhou

A Generation-based Deductive Method for Math Word Problems (2023.emnlp-main)

Challenge:	Existing methods to augment dialogue datasets are labor-intensive and time-consuming . Currently, smoking is harmful for your health.
Approach:	They propose a data augmentation method to augment dialogue responses with different semantics by counterfactual inference.
Outcome:	The proposed method outperforms baselines on multiple downstream tasks.

Copied to clipboard

Yuxuan Hu, Jing Zhang, Haoyang Li, Cuiping Li, Hong Chen

Learning to Generate Clinically Coherent Chest X-Ray Reports (2020.findings-emnlp)

Challenge:	Existing generation methods suffer from repeated sub-expression generation and deductive methods are restricted to dealing with binary operations.
Approach:	They propose a multivariate directed acyclic graph (mDAG) which generates the topological ordering of mDAg by equipping a generation model with a re-encoder to keep the deductive property but avoid the expensive enumeration of deductive methods.
Outcome:	The proposed model performs well on the widely used benchmarks and solves multivariate operators on the CMWPA benchmark.

Copied to clipboard

Justin Lovelace, Bobak Mortazavi

Headline Token-based Discriminative Learning for Subheading Generation in News Article (2023.findings-eacl)

Challenge:	Existing abstractive methods for radiology report generation produce fluent, but clinically incorrect reports.
Approach:	They propose a radiology report generation model that uses the transformer architecture to extract clinical information from generated reports and fine-tune the model to produce more clinically coherent reports.
Outcome:	The proposed model produces superior reports as measured by standard language generation and clinical coherence metrics compared to competitive baselines.

Copied to clipboard

Joonwon Jang, Misuk Kim

Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning (2021.findings-emnlp)

Challenge:	Existing models that generate news subheadings rely on topical headline information to capture topical knowledge from the article.
Approach:	They propose a model that uses topical headline information to generate news subheadings using masked headline tokens.
Outcome:	The proposed model outperforms the comparative models on three news datasets written in two languages and performs robustly on a small dataset and various masking ratios.

Copied to clipboard

Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, Xiaodan Zhu

Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation (2021.emnlp-main)

Challenge:	Existing approaches fail to generalize well to concepts that are not observed during training.
Approach:	They propose a framework that revolves around probing several similar image caption training instances and performing analogical reasoning over relevant entities in retrieved prototypes.
Outcome:	The proposed framework improves on the widely used image captioning benchmarks and on composition-related evaluation metrics.

Copied to clipboard

Feng Jiang, Yaxin Fan, Xiaomin Chu, Peifeng Li, Qiaoming Zhu

Text Classification

Challenge:	Existing methods of implicit discourse relation recognition (IDRR) focus on three aspects: enhancing discourse units representation, enhancing semantic interaction, and joint learning with other tasks.
Approach:	They propose a joint model to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously.
Outcome:	The proposed model achieves the best performance against several state-of-the-art systems on Chinese and English datasets.

Low-Resource Response Generation with Template Prior (D19-1)

Copied to clipboard

Ze Yang, Wei Wu, Jian Yang, Can Xu, Zhoujun Li

Multimodal Dialogue Response Generation (2022.acl-long)

Challenge:	Existing open domain response generation models are limited to paired data, but are less explored in real-world applications.
Approach:	They propose to train a neural response generation model with unpaired data and paired data as prior.
Outcome:	The proposed model outperforms state-of-the-art models in both automatic and human evaluation when only a few pairs are available.

Copied to clipboard

Qingfeng Sun, Yujing Wang, Can Xu, Kai Zheng, Yaming Yang, Huang Hu, Fei Xu, Jessica Zhang, Xiubo Geng, Daxin Jiang

MedWriter: Knowledge-Aware Medical Text Generation (2020.coling-main)

Challenge:	Existing studies focus on multimodal dialogue models but neglect generation methods.
Approach:	They propose a multimodal dialogue response generation task which requires multimodal dialogs containing both texts and images which are difficult to obtain.
Outcome:	Experiments show that the proposed model can generate informative text and high-resolution image responses.

Copied to clipboard

Youcheng Pan, Qingcai Chen, Weihua Peng, Xiaolong Wang, Baotian Hu, Xin Liu, Junying Chen, Wenxiu Zhou

Structured Data in NLP

Challenge:	Recent studies focus on the information of unstructured text rather than structured information of the knowledge graph.
Approach:	They propose a knowledge-aware text generation model for medical domains that incorporates knowledge graphs into the model to improve the quality of generated text.
Outcome:	The proposed model improves the quality of generated text and has robust superiority over other methods.

Stylized Story Generation with Style-Guided Planning (2021.findings-acl)

Copied to clipboard

Xiangzhe Kong, Jialiang Huang, Ziquan Tung, Jian Guan, Minlie Huang

Exploring Graph Pre-training for Aspect-based Sentiment Analysis (2023.findings-emnlp)

Challenge:	Current storytelling systems focus more on generating stories with coherent plots regardless of the narration style.
Approach:	They propose a novel task, stylized story generation, that first plans stylized keywords and then generates the whole story with the guidance of the keywords.
Outcome:	The proposed model can generate emotion-driven or event-driven stories based on the ROCStories dataset .

Copied to clipboard

Xiaoyi Bao, Zhongqing Wang, Guodong Zhou

Sentiment Analysis

Challenge:	Existing studies tend to extract the sentiment elements in a generative manner to avoid complex modeling of sentiment elements.
Approach:	They propose a generative model with an Element-level Graph Pre-training paradigm and a Task Decomposition Pre- training paradigm to make it generalizable and robust against irregular sentiment quadruples.
Outcome:	The proposed model is generalizable and robust against irregular sentiment quadruples.

A Unified Framework for Pun Generation with Humor Principles (2022.findings-emnlp)

Copied to clipboard

Yufei Tian, Divyanshu Sheth, Nanyun Peng

Argument Generation with Retrieval, Planning, and Realization (P19-1)

Challenge:	Existing models for generating homophonic and homographic puns lack the linguistic attributes of successful puns to resolve the split-up in existing work.
Approach:	They propose a framework to generate both homophonic and homographic puns to resolve the split-up in existing works by incorporating three linguistic attributes of puns into the language models: ambiguity, distinctiveness, and surprise.
Outcome:	The proposed model over strong baselines shows that it can generate both homophonic and homographic puns.

Copied to clipboard

Xinyu Hua, Zhe Hu, Lu Wang

Sentence Mover’s Similarity: Automatic Evaluation for Multi-Sentence Texts (P19-1)

Challenge:	a novel argument generation framework is used to generate counter-arguments . CANDELA uses a text planning decoder to retrieve arguments of different perspectives .
Approach:	They propose a powerful retrieval system and a novel two-step argument generation framework . they use a retrieval-based retrieval platform indexed with 12 million articles from Wikipedia .
Outcome:	The proposed framework yields higher BLEU, ROUGE, and METEOR scores than state-of-the-art models.

Copied to clipboard

Elizabeth Clark, Asli Celikyilmaz, Noah A. Smith

Challenge:	Existing automatic metrics for evaluating text are expensive and time-consuming.
Approach:	They propose automatic metrics that evaluate text in a continuous space using word and sentence embeddings.
Outcome:	The proposed method outperforms ROUGE on machine-generated summaries and human-authored essays on human-generated texts.

Latent Reasoning for Low-Resource Question Generation (2021.findings-acl)

Copied to clipboard

Xinting Huang, Jianzhong Qi, Yu Sun, Rui Zhang

Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks (2020.emnlp-main)

Challenge:	Existing approaches to multihop question generation require extensive data collection and decomposition.
Approach:	They propose a generative approach that optimizes the two-phase model without question decomposition data.
Outcome:	The proposed approach outperforms baselines on HOTPOTQA, a benchmark multi-hop question answering dataset.

Copied to clipboard

Yufan Zhao, Can Xu, Wei Wu

Contextualizing Generated Citation Texts (2024.lrec-main)

Challenge:	Existing approaches to multi-turn response generation for open-domain dialogues have a complexity problem . auxiliary tasks that relate to context understanding can guide the learning of the generation model .
Approach:	They propose a multi-turn response generation model that has a simple structure yet can effectively leverage conversation contexts for response generation.
Outcome:	The proposed model outperforms state-of-the-art models in response quality and human judgment . it also enjoys a faster decoding process .

Copied to clipboard

Biswadip Mandal, Xiangci Li, Jessica Ouyang

Abstractive Summarization of Bengali Academic Videos Based on Audio Subtitles (2026.findings-eacl)

Challenge:	Abstractive citation text generation is usually framed as an infilling task . however, examining a recent LED-based citation generation system, we find that many of the generated citations are generic summaries of the reference paper’s main contribution, ignoring the citation context’s focus on a different topic.
Approach:	They propose a modification to the citation text generation task by training the generation model to generate a citation given a reference paper and the context window around the target.
Outcome:	The proposed model can generate citations based on the entire context window, including the target citation.

Copied to clipboard

Lamisa Bintee Mizan Deya, Farhatun Shama, Abdul Aziz, Md Kaykobad Reza, Md Shahidul Salim

Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding (2021.findings-emnlp)

Challenge:	Existing methods for summarizing educational videos in Bengali are limited due to the rapid growth of educational video content.
Approach:	They propose an end-to-end pipeline for the abstractive summarization of Bengali videos . they fine-tuned the BanglaT5 model on a new benchmark dataset .
Outcome:	The proposed system preprocesses audio and converts speech to text using Google's Speech Recognition API.

Copied to clipboard

Zexue He, Bodhisattwa Prasad Majumder, Julian McAuley

Refer, Reuse, Reduce: Generating Subsequent References in Visual and Conversational Contexts (2020.emnlp-main)

Challenge:	Written language carries explicit and implicit biases that can distract from meaningful signals; at worst they can lead to unfair outcomes.
Approach:	They propose a gradient-based rewriting framework that detects and perturbs sensitive components and regenerates fluent alternatives that are neutral in the sensitive attribute while maintaining the semantics of other attributes.
Outcome:	The proposed framework regenerates fluent alternatives that are neutral in the sensitive attribute while maintaining the semantics of other attributes.

Copied to clipboard

Ece Takmaz, Mario Giulianelli, Sandro Pezzelle, Arabella Sinclair, Raquel Fernández

Visual Data in NLP

Challenge:	Subsequent references exploit the common ground accumulated by the interlocutors and tend to be shorter and reuse expressions that were effective in previous mentions.
Approach:	They propose a model that generates first and subsequent references in visually grounded dialogue . they also implement a reference resolution system to assess the referring effectiveness .
Outcome:	The proposed model produces better, more effective referring utterances than one not grounded in the dialogue context.

Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation (2024.emnlp-main)

Copied to clipboard

Zhiyu Cao, Peifeng Li, Yaxin Fan, Qiaoming Zhu

Paraphrasing

Challenge:	Existing generation methods on Incomplete Utterance Rewriting (IUR) can generate coherent utterances, but they often include irrelevant and redundant tokens in rewritten utteras .
Approach:	They propose a multi-task learning framework that uses editing operation labels to guide generation model to focus on critical tokens in dialogue context.
Outcome:	The proposed model outperforms state-of-the-art models on open-domain and task-oriented dialogues on three datasets.

UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity Mixture-of-Experts (2026.acl-long)

Copied to clipboard

Zhenyu Liu, Yunxin li, Xuanyu Zhang, Qixun Teng, Shenyuan Jiang, Xinyu Chen, Haoyuan Shi, Haolan Chen, Fanbo Meng, Mingjun Zhao, Yu Xu, Yancheng He, Baotian Hu, Haizhou Li, Min Zhang

RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering (2022.acl-long)

Challenge:	Recent advances in unified multimodal models indicate a clear trend towards comprehensive content generation.
Approach:	They propose a unified speech and music generation model built upon a novel framework . they propose specialized MoE architectures and curated training strategies to tackle data imbalances .
Outcome:	The proposed model achieves state-of-the-art performance on major speech and music generation benchmarks.

Copied to clipboard

Xi Ye, Semih Yavuz, Kazuma Hashimoto, Yingbo Zhou, Caiming Xiong

Natural Language Interfaces

Challenge:	Existing KBQA approaches struggle with generalization of unseen KB schema items . Rank-and-generate approach solves coverage issue with strong generalization .
Approach:	They propose a Rank-and-Generate approach for KBQA that uses a generation model to generalize to unseen KB schema items.
Outcome:	The proposed approach outperforms the prior state-of-the-art on GrailQA and WebQSP datasets.

Diversifying Question Generation over Knowledge Base via External Natural Questions (2024.lrec-main)

Copied to clipboard

Shasha Guo, Jing Zhang, Xirui Ke, Cuiping Li, Hong Chen

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors (2024.emnlp-main)

Challenge:	Existing methods on knowledge base question generation focus on refining the quality of a single generated question.
Approach:	They propose a new diversity evaluation metric which measures the diversity among top-k generated questions for each instance while ensuring their relevance to the ground truth.
Outcome:	The proposed model outperforms pre-trained language model baselines and text-davinci-003 in diversity while achieving comparable performance with ChatGPT.

Copied to clipboard

Nico Daheim, Jakub Macina, Manu Kapur, Iryna Gurevych, Mrinmaya Sachan

Visual and Memory–Augmented Soccer Commentary Generation (2026.acl-long)

Challenge:	Existing models for dialog tutoring fail to detect student errors and tailor their feedback to them.
Approach:	They propose to build dialog tutoring models to scaffold students' problem-solving and verify student solutions by using automatic and human evaluation.
Outcome:	The proposed model improves the quality of the tutor response generation by detecting student errors and adjusting the feedback to the errors.

Copied to clipboard

Haoran Sun, Natthawut Kertkeidkachorn, Kiyoaki Shirai

Visual Data in NLP

Challenge:	Existing datasets produce incomplete commentary that lacks semantic richness and does not convey full visual information present in standard video clips.
Approach:	They propose a method that transforms incomplete annotations into MatchText, a semantically complete and structurally standardized dataset.
Outcome:	The proposed model outperforms baselines on constructed soccer commentary datasets.

Mix-Initiative Response Generation with Dynamic Prefix Tuning (2024.naacl-long)

Copied to clipboard

Yuxiang Nie, Heyan Huang, Xian-Ling Mao, Lizi Liao

GRACE: Gradient-guided Controllable Retrieval for Augmenting Attribute-based Text Generation (2023.findings-acl)

Challenge:	Existing dialogue systems focus on training a holistic response generation model without any distinction between different initiatives.
Approach:	They propose a general mix-Initiative Dynamic Prefix Tuning framework to decouple different initiatives from the generation model.
Outcome:	The proposed framework outperforms baselines on two public dialogue datasets on human evaluations and automatic metrics.

Copied to clipboard

Zhihua Wen, Zhiliang Tian, Zhen Huang, Yuxin Yang, Zexin Jian, Changjian Wang, Dongsheng Li

EpLSA: Synergy of Expert-prefix Mixtures and Task-Oriented Latent Space Adaptation for Diverse Generative Reasoning (2024.lrec-main)

Challenge:	Existing methods for controlling the generation of pre-trained language models infuse domain bias into the generation process, making it difficult to generate out-of-domain texts.
Approach:	They propose a retrieval-augmented generation framework that uses retrieval to generate fluent sentences with high attribute relevance.
Outcome:	The proposed method can generate fluent sentences with high attribute relevance while keeping domain bias out of the model.

Copied to clipboard

Fujun Zhang, Xiangdong Su, Jiang Li, Rong Yan, Guanglai Gao

Describe Me an Auklet: Generating Grounded Perceptual Category Descriptions (2023.emnlp-main)

Challenge:	Existing models for diverse generative reasoning struggle to generate multiple unique and plausible results.
Approach:	They propose a model based on expert-prefix mixtures and task-oriented latent space adaptation for diverse generative reasoning.
Outcome:	The proposed model outperforms existing models on three types of generative reasoning tasks.

Copied to clipboard

Bill Noble, Nikolai Ilinykh

CLOMO: Counterfactual Logical Modification with Large Language Models (2024.acl-long)

Challenge:	Learning and using abstract perceptual concepts is under-investigated in the language-and-vision field.
Approach:	They propose a framework for testing category-level perceptual grounding in multi-modal language models by using separate neural networks to generate and interpret descriptions of visual categories.
Outcome:	The proposed framework compares prototype- and interpretation-based representations with the performance of the generation model and the interpretation model, which is an indicator of perceptual grounding.

Copied to clipboard

Yinya Huang, Ruixin Hong, Hongming Zhang, Wei Shao, Zhicheng Yang, Dong Yu, Changshui Zhang, Xiaodan Liang, Linqi Song

Low-Resource Generation of Multi-hop Reasoning Questions (2020.acl-main)

Challenge:	Existing studies on evaluating model reasoning are limited in both form and content.
Approach:	They propose a task to cultivate counterfactual thought processes within large language models and an evaluation metric to evaluate their natural language output instead of modeling the task as a multiple-choice problem.
Outcome:	The proposed evaluation metric aligns well with human preference.

Copied to clipboard

Jianxing Yu, Wei Liu, Shuang Qiu, Qinliang Su, Kai Wang, Xiaojun Quan, Jian Yin

AMPERE: AMR-Aware Prefix for Generation-Based Event Argument Extraction Model (2023.acl-long)

Challenge:	Existing methods to generate valid and fluent questions from text are limited and insufficient for training.
Approach:	They propose to generate multi-hop reasoning questions from the raw text in a low resource circumstance by deducing over multiple relations on several sentences in the text.
Outcome:	The proposed model can be applied to the task of machine reading comprehension and achieve significant performance improvements.

Copied to clipboard

I-Hung Hsu, Zhiyu Xie, Kuan-Hao Huang, Prem Natarajan, Nanyun Peng

Information Extraction & Text Mining

Challenge:	Existing generation-based EAE models focus on problem re-formulation and prompt design without incorporating additional information that has been shown to be effective for classification-based models.
Approach:	They propose to incorporate AMR into generation-based EAE models by generating AMR-aware prefixes for every layer of the generation model.
Outcome:	The proposed model generates AMR-aware prefixes for every layer of the generation model and improves the generation.

Improving Grammatical Error Correction via Contextual Data Augmentation (2024.findings-acl)

Copied to clipboard

Yixuan Wang, Baoxin Wang, Yijun Liu, Qingfu Zhu, Dayong Wu, Wanxiang Che

Discourse Structure-Aware Prefix for Generation-Based End-to-End Argumentation Mining (2024.findings-acl)

Challenge:	Increasing use of synthetic data due to inconsistent error distribution and noisy labels is limiting the use of these data.
Approach:	They propose a method for augmentation of synthetic data with a more consistent error distribution.
Outcome:	The proposed method outperforms strong baselines and achieves state-of-the-art with only a few synthetic data.

Copied to clipboard

Yang Sun, Guanrong Chen, Caihua Yang, Jianzhu Bao, Bin Liang, Xi Zeng, Min Yang, Ruifeng Xu

Gradient-guided Unsupervised Lexically Constrained Text Generation (2020.emnlp-main)

Challenge:	Recent advances in AM models overlook the integration of supplementary discourse structure information, resulting in suboptimal outcomes.
Approach:	They propose a framework which generates discourse structure-aware prefixes for each layer of the generation model.
Outcome:	The proposed framework achieves state-of-the-art performance on two AM benchmarks.

Copied to clipboard

Lei Sha

CritiqueLLM: Towards an Informative Critique Generation Model for Evaluation of Large Language Model Generation (2024.acl-long)

Challenge:	Existing methods for lexically constrained generation fail when the search space is too large . a novel method to solve the problem is based on gradient-guided optimization .
Approach:	They propose a method to solve lexically-constrained generation as an unsupervised gradient-guided optimization problem.
Outcome:	The proposed method achieves state-of-the-art compared to previous methods . it is free of parallel data training, flexible to be used in the inference stage of any pre-trained generation model.

Copied to clipboard

Pei Ke, Bosi Wen, Andrew Feng, Xiao Liu, Xuanyu Lei, Jiale Cheng, Shengyuan Wang, Aohan Zeng, Yuxiao Dong, Hongning Wang, Jie Tang, Minlie Huang

On the Limitations of Reference-Free Evaluations of Generated Text (2022.emnlp-main)

Challenge:	Existing models for NLP evaluations lack the ability to generate informative critiques in pointwise grading and pairwise comparison especially without references.
Approach:	They propose a method which can acquire pointwise grading critiques with pseudo references and revise these critiques via multi-path prompting to obtain informative evaluation data in different tasks and settings.
Outcome:	The proposed method outperforms all open-source models and even GPT-4 in system-level correlations of pointwise grading.

Copied to clipboard

Daniel Deutsch, Rotem Dror, Dan Roth

StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing (2023.acl-long)

Challenge:	a recent study has shown that evaluation metrics which accurately estimate the quality of generated text are limited in their ability to evaluate generated text.
Approach:	They argue that reference-free metrics are limited in their ability to evaluate generated text . they recommend that they be used as diagnostic tools for analyzing and understanding model behavior .
Outcome:	The proposed evaluation metrics are limited in their ability to evaluate generated text . they can be optimized at test time, can be biased against models with similar outputs .

Copied to clipboard

Xuekai Zhu, Jian Guan, Minlie Huang, Juan Liu

Representation Learning

Challenge:	Existing studies on text style transfer neglect long style transfer at the discourse level.
Approach:	They propose a model that transfers text style into target styles with learnable style embeddings . they use a mask-and-fill framework to explicitly fuse style-specific keywords into generation .
Outcome:	The proposed model outperforms baselines in style transfer and content preservation.

RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Meng Xi, Sihan Lv, Yechen Jin, Guanjie Cheng, Naibo Wang, Ying Li, Jianwei Yin

Robustness in NLP

Challenge:	Existing methods to generate RAG documents require knowledge of the target RAG system’s internal composition and implementation details, whereas black-box methods are unable to utilize interactive information.
Approach:	They propose a RIPRAG attack framework that treats the target RAG system as a black box and leverages a Reinforcement Learning from Black-box Feedback (RLBF) method to optimize the generation model for poisoned documents.
Outcome:	The proposed method achieves an attack success rate (ASR) improvement of up to 0.72 compared to baseline methods.

Reading Does Not Equal Reading: Comparing, Simulating and Exploiting Reading Behavior across Populations (2024.lrec-main)

Copied to clipboard

David R. Reich, Shuwen Deng, Marina Björnsdóttir, Lena Jäger, Nora Hollenstein

Think Before you Write: QA-Guided Reasoning for Character Descriptions in Books (2026.findings-acl)

Challenge:	Existing corpora of eye-tracking-while-reading corporata lack diversity, limiting their ability to include primarily native speakers.
Approach:	They expand the eye-tracking-while-reading dataset CopCo by incorporating a new dataset of L2 readers with diverse L1 backgrounds.
Outcome:	The extended CopCo corpus comprises neurotypical L1 and L1 readers with dyslexia as well as L2 readers reading the same materials.

Copied to clipboard

Argyrios Papoudakis, Mirella Lapata, Frank Keller