LANGUAGE GENERATION

Hello, It’s GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems (D19-56)

Challenge:	Existing open-domain dialogue models fail to capture and utilize external knowledge, leading to repetitive or generic responses to unseen utterances.
Approach:	They propose to use social media comments to improve the raw conversation ability of open-domain dialogue systems.
Outcome:	The proposed model improves the raw conversation ability of open-domain dialogue systems by mimicking human responses through casual interactions found on social media.

Copied to clipboard

Paweł Budzianowski, Ivan Vulić

Knowledge-Augmented Methods for Natural Language Processing (2022.acl-tutorials)

Challenge:	Statistical conversational systems are complex, timeintensive, expensive, and not easily transferable due to data scarcity.
Approach:	They propose a task-oriented dialogue model that operates on text input . they validate it on multi-domain task-orientated dialogues from a multi-word dataset .
Outcome:	The proposed model bypasses explicit policy and language generation modules on multi-domain task-oriented dialogues from the MultiWOZ dataset.

Copied to clipboard

Chenguang Zhu, Yichong Xu, Xiang Ren, Bill Yuchen Lin, Meng Jiang, Wenhao Yu

Reasoning

Challenge:	Knowledge in natural language processing (NLP) is a rising trend especially after the advent of large scale pre-trained models.
Approach:	This tutorial introduces the key steps in integrating knowledge into natural language processing (NLP) it introduces knowledge grounding from text, knowledge representation and fusing.
Outcome:	This tutorial introduces the key steps in integrating knowledge into natural language processing including knowledge grounding from text, knowledge representation and fusing.

Generating Text from Language Models (2023.acl-tutorials)

Copied to clipboard

Afra Amini, Ryan Cotterell, John Hewitt, Luca Malagutti, Clara Meister, Tiago Pimentel

On the probability–quality paradox in language generation (2022.acl-short)

Challenge:	a growing percentage of natural language processing tasks focus on the generation of text from probabilistic language models.
Approach:	They will provide a centralized discussion of critical considerations when choosing how to generate from a language model.
Outcome:	This tutorial will provide a centralized discussion of critical considerations when choosing how to generate from a language model.

Copied to clipboard

Clara Meister, Gian Wiher, Tiago Pimentel, Ryan Cotterell

Mitigating Societal Harms in Large Language Models (2023.emnlp-tutorial)

Challenge:	a recent study suggests that mode-seeking decoding methods produce unnatural language . a higher probability text is perceived as more human-like, but this is not the case with stochastic decoding .
Approach:	They propose to explain why higher-probability text is perceived as more human-like . they argue that human-type language should contain an amount of information close to entropy .
Outcome:	The proposed model produces lower-probability text, which is perceived as more human-like . elucidation of this hypothesis supports the hypothesis .

Copied to clipboard

Sachin Kumar, Vidhisha Balachandran, Lucille Njoo, Antonios Anastasopoulos, Yulia Tsvetkov

Knowledge Control for Responsible Generative AI: Bridging Academia, Industry, and Society (2026.acl-tutorials)

Challenge:	Recent studies have highlighted societal harms that can be caused by language generation models deployed in the wild.
Approach:	They propose to use a typology of technical approaches to mitigating harms of language generation models to provide an overview of potential social issues in language generation including toxicity, social biases, misinformation, factual inconsistency, and privacy violations.
Outcome:	The proposed typology addresses toxicity, biases, misinformation, factual inconsistency, and privacy violations in language generation models.

Copied to clipboard

Zheyuan Liu, Yixin Wan, Kai-Wei Chang, Meng Jiang, Jieyu Zhao, Nouha Dziri, Yuning Mao, Jia-Chen Gu, Jindong Gu

Creative Natural Language Generation (2023.emnlp-tutorial)

Challenge:	This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods.
Approach:	This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods.
Outcome:	This tutorial introduces the foundations of post-training knowledge control and showcases recent frontier methods . key motivations and failure modes, harmful generation and stereotype reinforcement, are addressed . core methods such as machine unlearning, knowledge editing, and inference-time interventions are also included .

Copied to clipboard

Tuhin Chakrabarty, Vishakh Padmakumar, He He, Nanyun Peng

Generating Text through Adversarial Training Using Skip-Thought Vectors (N19-3)

Challenge:	This tutorial aims to bring awareness of the important and emerging research area of open-domain creative generation.
Approach:	They will review recent studies on creative language generation at sentence level as well as longer forms of text.
Outcome:	This paper reviews recent studies on creative language generation at sentence level as well as longer forms of text.

Copied to clipboard

Afroz Ahamad

Robustness in NLP

Challenge:	Existing approaches to use word embeddings for text generation have been limited.
Approach:	They propose to use GANs with word embeddings to reproduce writing style in text . they use a sentence embeddable vector to model people's way of expression .
Outcome:	The proposed model outperforms baseline text generation networks across several metrics including BLEU-n, METEOR and ROUGE.

PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable (2020.acl-main)

Copied to clipboard

Siqi Bao, Huang He, Fan Wang, Hua Wu, Haifeng Wang

Interpreting Language Models with Contrastive Explanations (2022.emnlp-main)

Challenge:	Existing pre-training models for dialogue generation have been proven effective for a wide range of tasks.
Approach:	They propose a dialogue generation pre-training framework that leverages bi-directional context and uni-directional characteristic of language generation.
Outcome:	The proposed framework is superior to existing models on three publicly available datasets.

Copied to clipboard

Kayo Yin, Graham Neubig

Explainability & Interpretability in NLP

Challenge:	Existing explanation methods conflate evidence for various features to predict a token . existing explanation methods are less interpretable for human understanding .
Approach:	They propose to explain language models contrastively by looking for salient input tokens that explain why the model predicted one token instead of another.
Outcome:	The proposed explanations are better than non-contrastive explanations for language models . they show that contrastive explanations improve simulability for human observers .

Aligning Generative Language Models with Human Values (2022.findings-naacl)

Copied to clipboard

Ruibo Liu, Ge Zhang, Xinyu Feng, Soroush Vosoughi

Sounding Board: A User-Centric and Content-Driven Social Chatbot (N18-5)

Challenge:	Existing methods for learning human values do not consider contextual and abstract nature of human values.
Approach:	They propose a reinforcement learning based method that embeds human values judgements into each step of language generation.
Outcome:	The proposed method improves on human values judgements and shows higher alignment performance.

Copied to clipboard

Hao Fang, Hao Cheng, Maarten Sap, Elizabeth Clark, Ari Holtzman, Yejin Choi, Noah A. Smith, Mari Ostendorf

A Natural Bias for Language Generation Models (2023.acl-short)

Challenge:	Sounding Board is a social chatbot that can hold a coherent conversation with humans . the system is user-centric in that users can control the topic of conversation, while the system adapts to the user's needs.
Approach:	They present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize.
Outcome:	The system is user-centric in that users can control the topic of conversation, while the system adapts to the user's needs.

Copied to clipboard

Clara Meister, Wojciech Stokowiec, Tiago Pimentel, Lei Yu, Laura Rimell, Adhiguna Kuncoro

O2NA: An Object-Oriented Non-Autoregressive Approach for Controllable Video Captioning (2021.findings-acl)

Challenge:	a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, making it difficult to estimate the probability distribution over next tokens.
Approach:	They propose to initialise bias terms in a model's final linear layer with the log-unigram distribution and use it to output the unigram frequency statistics as prior knowledge.
Outcome:	The proposed method improves learning efficiency and improves overall performance.

Copied to clipboard

Fenglin Liu, Xuancheng Ren, Xian Wu, Bang Yang, Shen Ge, Xu Sun

Fact-Aware Multimodal Retrieval Augmentation for Accurate Medical Radiology Report Generation (2025.naacl-long)

Challenge:	Existing methods for video captioning consider a sequence of frames and biases towards focused objects.
Approach:	They propose an Object-Oriented Non-Autoregressive approach to video captioning . it performs three steps: 1) identify the focused objects and predict their locations . 2) generate related attribute words and relation words of these focused objects to form a draft caption .
Outcome:	The proposed method achieves competitive results with the state-of-the-art methods but with higher diversity and faster inference speed.

Copied to clipboard

Liwen Sun, James Jialun Zhao, Wenjing Han, Chenyan Xiong

Information Retrieval

Challenge:	Existing multimodal foundation models suffer from serious factual inaccuracy in radiology report generation.
Approach:	They propose a fact-aware multimodal retrieval-augmented pipeline for generating accurate radiology reports using RadGraph.
Outcome:	The proposed multimodal retrieval-augmented pipeline outperforms state-of-the-art retrievers on language generation and radiology-specific metrics.

PyOpenDial: A Python-based Domain-Independent Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules (D19-3)

Copied to clipboard

Youngsoo Jang, Jongmin Lee, Jaeyoung Park, Kyeng-Hun Lee, Pierre Lison, Kee-Eung Kim

Towards Robust and Semantically Organised Latent Representations for Unsupervised Text Style Transfer (2022.naacl-main)

Challenge:	a recent development of spoken dialogue systems has enabled deep learning to achieve state-of-the-art performance.
Approach:	They propose a Python-based domain-independent, open-source toolkit for spoken dialogue systems.
Outcome:	The proposed toolkit extends OpenDial's Java-based architecture and provides new functions for neural dialogue state tracking and action planning.

Copied to clipboard

Sharan Narasimhan, Suvodip Dey, Maunendra Desarkar

Dialz: A Python Toolkit for Steering Vectors (2025.acl-demo)

Challenge:	Recent studies show that auto-encoders perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner.
Approach:	They propose a discrete token-based perturbation approach to map "similar" sentences close by in latent space.
Outcome:	The proposed model can generate and perform language generation, style transfer and sentence interpolation tasks on unlabelled datasets in a zero-shot manner.

Copied to clipboard

Zara Siddique, Liam Turner, Luis Espinosa-Anke

Challenge:	Dialz is a Python library for advancing research on steering vectors for open-source LMs.
Approach:	They propose a Python library for advancing research on steering vectors for open-source LMs.
Outcome:	The proposed method reduces harmful outputs and provides insights into model behaviour across different layers.

Handling and Presenting Harmful Text in NLP Research (2022.findings-emnlp)

Copied to clipboard

Hannah Kirk, Abeba Birhane, Bertie Vidgen, Leon Derczynski

Listen Again and Choose the Right Answer: A New Paradigm for Automatic Speech Recognition with Large Language Models (2024.findings-acl)

Challenge:	Text data can pose a risk of harm, but the risks remain unresolved in the NLP community.
Approach:	They propose an analytical framework categorising harms on three axes: harm type, whether harm sought as a feature of research design, whether harmful content is encountered when working on unrelated problems, and who it affects .
Outcome:	The proposed framework categorises harms on three axes: harm type, whether harm sought as feature of research design, and whether harmful content is encountered when working on unrelated problems.

Copied to clipboard

Yuchen Hu, Chen Chen, Chengwei Qin, Qiushi Zhu, EngSiong Chng, Ruizhe Li

Natural Language Processing for Human Resources: A Survey (2025.naacl-industry)

Challenge:	Recent advances in large language models (LLMs) have promoted generative error correction (GER) for automatic speech recognition (ASR).
Approach:	They propose a multimodal LLM to receive source speech as extra input and reformat it as a cloze test with logits calibration to remove input information redundancy and simplify GER with clear instructions.
Outcome:	The proposed model improves on 9 popular ASR datasets and is faster than vanilla GER.

Copied to clipboard

Naoki Otani, Nikita Bhutani, Estevam Hruschka

Information Extraction & Text Mining

Challenge:	Recent advances in NLP have the potential to transform HR processes, from recruitment to employee management.
Approach:	They analyze key tasks such as information extraction and text classification and their roles in downstream applications like recommendation and language generation while discussing ethical concerns.
Outcome:	The proposed frameworks can be applied to HR tasks and to recommendation, language generation, and interaction.

SkipCLM: Enhancing Crosslingual Alignment of Decoder Transformer Models via Contrastive Learning and Skip Connection (2025.naacl-srw)

Copied to clipboard

Nikita Sushko, Alexander Panchenko, Elena Tutubalina

Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal (2022.findings-acl)

Challenge:	Existing contrastive learning methods for cross-lingual alignment are not effective for multilingual machine translation tasks.
Approach:	They propose a method that augments contrastive learning for cross-lingual alignment with a trainable skip connection to preserve information crucial for accurate target language generation.
Outcome:	Experiments with XGLM-564M on the Flores-101 benchmark show that the proposed method preserves crucial information crucial for accurate target language generation.

Copied to clipboard

Umang Gupta, Jwala Dhamala, Varun Kumar, Apurv Verma, Yada Pruksachatkun, Satyapriya Krishna, Rahul Gupta, Kai-Wei Chang, Greg Ver Steeg, Aram Galstyan

On Decoding Strategies for Neural Text Generators (2022.tacl-1)

Challenge:	Language models excel at generating coherent text, but can be biased in multiple ways, including the unfounded association of male and female genders with gender-neutral professions.
Approach:	They propose to modify teacher probabilities and augment the training set to learn a fair model during knowledge distillation by modifying teacher probability and augmenting the training sets.
Outcome:	The proposed approach reduces gender disparity in open-ended text generated from the distilled and finetuned models with only a minor compromise in utility.

Copied to clipboard

Gian Wiher, Clara Meister, Ryan Cotterell

A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis (2022.findings-naacl)

Challenge:	a recent study suggests that decoding strategies may be more important than the model architecture itself when generating text from probabilistic models.
Approach:	They propose to measure changes in attributes of generated text as a function of decoding strategy and task using human and automatic evaluation.
Outcome:	The proposed study shows that decoding strategies do not always transfer across tasks . authors show that the differences in attributes are not always consistent across tasks, they say .

Copied to clipboard

Ehsan Hosseini-Asl, Wenhao Liu, Caiming Xiong

How Do Inpainting Artifacts Propagate to Language? (2026.acl-short)

Challenge:	Pre-trained language models are often used to achieve state-of-the-art results . eval paper shows that generative language model can handle joint and multi-task settings .
Approach:	They propose to reformulate extraction and prediction tasks into a sequence generation task . they propose a generative language model with unidirectional attention that learns to accomplish the tasks via language generation .
Outcome:	The proposed model outperforms the state-of-the-art in few-shot and full-shot settings.

Copied to clipboard

Pratham Yashwante, Davit Abrahamyan, Shresth Grover, Sukruth Rao

USR: An Unsupervised and Reference Free Evaluation Metric for Dialog Generation (2020.acl-main)

Challenge:	Figure 1 shows representative examples of visual artifacts introduced by diffusion-based inpainting . despite visually plausible reconstructions, localized inpainding artifactors lead to object substitutions, attribute changes, or category-level errors in downstream captions.
Approach:	They propose a diagnostic setup in which masked image regions are reconstructed and then provided to captioning models.
Outcome:	The proposed diagnostic framework can be used to examine how visual artifacts affect language generation in vision-language models.

Copied to clipboard

Shikib Mehri, Maxine Eskenazi

Fairer Preferences Elicit Improved Human-Aligned Large Language Model Judgments (2024.emnlp-main)

Challenge:	Standard language generation metrics have been shown to be ineffective for dialog evaluation.
Approach:	They propose an unsupervised evaluation metric for dialog that trains unsupervised models to measure several desirable qualities of dialog.
Outcome:	The proposed evaluation metric strongly correlates with human judgment on Topical-Chat and PersonaChat.

Copied to clipboard

Han Zhou, Xingchen Wan, Yinhong Liu, Nigel Collier, Ivan Vulić, Anna Korhonen

Self-Debiasing Large Language Models: Zero-Shot Recognition and Reduction of Stereotypes (2025.naacl-short)

Challenge:	Large language models (LLMs) have shown promising abilities as cost-effective and reference-free evaluators for assessing language quality.
Approach:	They propose an automatic Zero-shot Evaluation-oriented Prompt Optimization framework which produces fairer preference decisions and improves human alignment.
Outcome:	The proposed framework produces fairer preference decisions and better aligns LLMs with humans.

Copied to clipboard

Isabel O. Gallegos, Ryan Aponte, Ryan A. Rossi, Joe Barrow, Mehrab Tanjim, Tong Yu, Hanieh Deilamsalehy, Ruiyi Zhang, Sungchul Kim, Franck Dernoncourt, Nedim Lipka, Deonna Owens, Jiuxiang Gu

A Multimodal In-Context Tuning Approach for E-Commerce Product Description Generation (2024.lrec-main)

Challenge:	Large language models exhibit harmful social biases, but they are often difficult to train and modify.
Approach:	They leverage the zero-shot capabilities of large language models to reduce stereotyping . they introduce a technique called zero- shot self-debiasing to reduce bias .
Outcome:	The proposed technique reduces stereotyping across nine different social groups while relying on the LLM itself and a simple prompt.

Copied to clipboard

Yunxin Li, Baotian Hu, Wenhan Luo, Lin Ma, Yuxin Ding, Min Zhang

EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamics (2025.naacl-long)

Challenge:	Existing methods for generating product descriptions from images are inaccurate and generic . e-commerce product descriptions are important for content marketing and increasing engagement .
Approach:	They propose a new setting for generating product descriptions from images, augmented by marketing keywords.
Outcome:	The proposed approach improves the accuracy and diversity of product descriptions by up to 3.3% on Rouge-L and 9.4% on D-5.

Copied to clipboard

Chenwei Wan, Matthieu Labeau, Chloé Clavel

Recipe Instruction Semantics Corpus (RISeC): Resolving Semantic Structure and Zero Anaphora in Recipes (2020.aacl-main)

Challenge:	Recent studies show that implicit strategy planning lacks transparency and that LLMs’ inherent preference bias towards certain socio-emotional strategies hinders the delivery of high-quality emotional support.
Approach:	They propose to decouple strategy prediction from language generation and introduce a new dialogue strategy prediction framework, EmoDynamiX, which models the discourse dynamics between user fine-grained emotions and system strategies using a heterogeneous graph for better performance and transparency.
Outcome:	The proposed framework outperforms state-of-the-art methods on two ESC datasets with a significant margin (better proficiency and lower preference bias).

Copied to clipboard

Yiwei Jiang, Klim Zaporojets, Johannes Deleu, Thomas Demeester, Chris Develder

Information Extraction & Text Mining

Challenge:	Existing approaches to understanding recipe instructions make assumptions that are domain specific.
Approach:	They propose a new dataset for information extraction on recipes . they avoid a priori pre-defining domain-specific predicates to recognize . instead, they focus on basic understanding of the expressed semantics .
Outcome:	The proposed dataset avoids a priori pre-defining domain-specific predicates to recognize . instead, it focuses on basic understanding of the expressed semantics rather than reducing them to a simplified state representation.

LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression (2025.findings-naacl)

Copied to clipboard

Souvik Kundu, Anahita Bhiwandiwalla, Sungduk Yu, Phillip Howard, Tiep Le, Sharath Nittur Sridhar, David Cobbley, Hao Kang, Vasudev Lal

Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models (2021.eacl-main)

Challenge:	LVLMs have been shown to perform well on simple uni-modal benchmarks, but their detailed study on multi-modal models is still lacking.
Approach:	They propose a framework to analyze the impact of compression on LVLMs on multi-modal input driven tasks.
Outcome:	The proposed framework analyzes the impact of compression on generative performance of large vision language models on multi-modal input driven tasks.

Copied to clipboard

Tianxing He, Jun Liu, Kyunghyun Cho, Myle Ott, Bing Liu, James Glass, Fuchun Peng

k-SemStamp: A Clustering-Based Semantic Watermark for Detection of Machine-Generated Text (2024.findings-acl)

Challenge:	a large-scale unsupervised pretraining has been shown to greatly boost the performance of natural language processing models.
Approach:	They propose an intuitive finetuning strategy to regularize the finetune process . they propose a mix-review strategy to alleviate the forgetting problem .
Outcome:	The proposed strategy regularizes the finetuning process, and the forgetting problem is alleviated . the proposed strategy also improves the performance of the resulting model .

Copied to clipboard

Abe Hou, Jingyu Zhang, Yichen Wang, Daniel Khashabi, Tianxing He

Robustness in NLP

Challenge:	Recent watermarked generation algorithms inject detectable signatures during language generation to facilitate post-hoc detection.
Approach:	They propose a watermark which assigns signatures to each watermarked sentence according to locality-sensitive hashing (LSH) they propose k-SemStamp, which uses kmeans clustering to partition the semantic space with awareness of inherent semantic structure.
Outcome:	The proposed watermark improves its robustness and sampling efficiency while preserving the generation quality, making it more effective for machine-generated text detection.

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

Copied to clipboard

Justin Lovelace, Bobak Mortazavi

Generating Radiology Reports via Memory-driven Transformer (2020.emnlp-main)

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

Zhihong Chen, Yan Song, Tsung-Hui Chang, Xiang Wan

Searching for Search Errors in Neural Morphological Inflection (2021.eacl-main)

Challenge:	Medical imaging reports are time-consuming and can be error-prone for inexperienced radiologists.
Approach:	They propose to generate radiology reports with memory-driven Transformer using relational memory and memory-based conditional layer normalization.
Outcome:	The proposed method outperforms existing models on IU X-Ray and MIMIC-CXR . it generates long reports with medical terms and meaningful image-text attention mappings .

Copied to clipboard

Martina Forster, Clara Meister, Ryan Cotterell

Syntactic Text Processing

Challenge:	Neural sequence-to-sequence models are the predominant choice for language generation tasks.
Approach:	They find that on word-level tasks, the empty string is often the global optimum . they suggest that the poor calibration of many neural models may stem from characteristics of a specific subset of tasks rather than general ill-suitedness of such models for language generation.
Outcome:	The results suggest that the poor calibration of many neural models may stem from characteristics of a specific subset of tasks rather than general ill-suitedness of such models for language generation.

A Persona-Based Corpus in the Diabetes Self-Care Domain - Applying a Human-Centered Approach to a Low-Resource Context (2024.lrec-main)

Copied to clipboard

Rossana Cunha, Thiago Castro Ferreira, Adriana Pagano, Fabio Alves

CR-Walker: Tree-Structured Graph Reasoning and Dialog Acts for Conversational Recommendation (2021.emnlp-main)

Challenge:	Human-centered design (HCD) is a new approach to natural language processing that uses personas, user profiles and other tools to build corpus.
Approach:	They propose to use personas to model interpersonal interaction in a healthcare domain to follow an HCD approach.
Outcome:	The proposed model improves the quality of human-centered design in a healthcare domain and overcomes the lack of in-depth human-centricity in the field.

Copied to clipboard

Wenchang Ma, Ryuichi Takanobu, Minlie Huang

Implicit Representations of Meaning in Neural Language Models (2021.acl-long)

Challenge:	Existing systems that explore user preference through conversational interactions do not exploit the context and knowledge to make accurate recommendations.
Approach:	They propose a model that performs tree-structured reasoning on a knowledge graph and generates informative dialog acts to guide language generation.
Outcome:	The proposed model can arrive at more accurate recommendation and generate more informative and engaging responses.

Copied to clipboard

Belinda Z. Li, Maxwell Nye, Jacob Andreas

Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale (2024.acl-long)

Challenge:	Neural language models (NLMs) encode lexical relations and syntactic structure, but their effectiveness is still unclear.
Approach:	They propose to use text as a model to model entities and situations as they evolve throughout a discourse.
Outcome:	The proposed models have functional similarities to linguistic models of dynamic semantics and can be learned with only text as training data.

Copied to clipboard

Xiang Hu, Pengyu Ji, Qingyang Zhu, Wei Wu, Kewei Tu

Creating Suspenseful Stories: Iterative Planning with Large Language Models (2024.eacl-long)

Challenge:	Existing syntactic language models require a gold tree and sequential training to generate sentences.
Approach:	They propose an unsupervised syntactic language model that incrementally generates a sentence with its syntaktic tree in a left-to-right manner.
Outcome:	The proposed model outperforms existing models on grammar induction and comprehension tasks while holding a substantial acceleration on training.

Copied to clipboard

Kaige Xie, Mark Riedl

A Large-Scale Multilingual Study of Visual Constraints on Linguistic Selection of Descriptions (2023.findings-eacl)

Challenge:	Automated story generation has been a challenge in NLP for many years.
Approach:	They propose an iterative-prompting-based method that is grounded in two theoretical foundations of story suspense from cognitive psychology and narratology.
Outcome:	The proposed method works in a fully zero-shot manner and does not rely on any supervised story corpora.

Copied to clipboard

Uri Berger, Lea Frermann, Gabriel Stanovsky, Omri Abend

Unleashing the Power of LLMs in Court View Generation by Stimulating Internal Knowledge and Incorporating External Knowledge (2024.findings-naacl)

Challenge:	a multilingual study examines how vision constrains linguistic choice . we use existing annotations to investigate the effect of different visual conditions on numeral expressions in captions .
Approach:	They propose a method that leverages existing corpora of images with captions written by native speakers to constrain linguistic choice.
Outcome:	The proposed method covers four languages and five linguistic properties, including verb transitivity and use of numerals.

Copied to clipboard

Yifei Liu, Yiquan Wu, Ang Li, Yating Zhang, Changlong Sun, Weiming Lu, Fei Wu, Kun Kuang

Unified Pragmatic Models for Generating and Following Instructions (N18-1)

Challenge:	Large Language Models (LLMs) have made remarkable strides in language generation, but they encounter difficulties in the knowledge-intensive legal domain.
Approach:	They propose to decompose court views into different parts, stimulate internal knowledge, and incorporate external information to unleash the power of LLMs in the task.
Outcome:	The proposed method generates more accurate and reliable court views on two real-world datasets LAIC2021 and CJO2022.

Copied to clipboard

Daniel Fried, Jacob Andreas, Dan Klein

Explainability & Interpretability in NLP

Challenge:	a new technique for layering explicit pragmatic inference on top of models for sequential tasks is proposed . explicit pragmatic reasoning is used to generate and follow natural language instructions .
Approach:	They propose a pragmatic speaker that uses the base listener to simulate the interpretation of candidate descriptions and a listener that reasons counterfactually about alternative descriptions.
Outcome:	The proposed model improves state-of-the-art models for interpreting human instructions and speaker models in diverse settings.

Mark-Evaluate: Assessing Language Generation using Population Estimation Methods (2020.coling-main)

Copied to clipboard

Gonçalo Mordido, Christoph Meinel

MIDLM: Multi-Intent Detection with Bidirectional Large Language Models (2025.coling-main)

Challenge:	Existing population estimation methods focus on open populations or closed populations, but our methods show a higher correlation to human evaluation than existing metrics on several challenging tasks.
Approach:	They propose a family of metrics to assess language generation derived from population estimation methods widely used in ecology.
Outcome:	The proposed methods show a higher correlation to human evaluation than existing metrics on several challenging tasks, namely unconditional language generation, machine translation, and text summarization.

Copied to clipboard

Shangjian Yin, Peijie Huang, Yuhong Xu

proScript: Partially Ordered Scripts Generation (2021.findings-emnlp)

Challenge:	Existing models that use autoregressive architectures restrict the sharing of token information within a sentence.
Approach:	They propose a framework that integrates intent number detection and multi-intent selection to enable autoregressive LLMs to leverage bidirectional information awareness through post-training.
Outcome:	The proposed framework outperforms existing models and pretrained baselines in the multi-intent detection task.

Copied to clipboard

Keisuke Sakaguchi, Chandra Bhagavatula, Ronan Le Bras, Niket Tandon, Peter Clark, Yejin Choi

Challenge:	Scripts represent structured commonsense knowledge about prototypical events in everyday situations/scenarios such as bake a cake.
Approach:	They collect 6.4k crowdsourced partially ordered scripts and develop models that combine language generation and graph structure prediction to generate scripts.
Outcome:	The proposed models perform well on two tasks: edge prediction and script generation.

BenLLM-Eval: A Comprehensive Evaluation into the Potentials and Pitfalls of Large Language Models on Bengali NLP (2024.lrec-main)

Copied to clipboard

Mohsinul Kabir, Mohammed Saidul Islam, Md Tahmid Rahman Laskar, Mir Tafseer Nayeem, M Saiful Bari, Enamul Hoque

Robust Conversational Agents against Imperceptible Toxicity Triggers (2022.naacl-main)

Challenge:	Large Language Models (LLMs) have emerged as one of the most important breakthroughs in natural language processing.
Approach:	They propose to evaluate LLMs in Bengali to benchmark their performance . they select Bangla NLP tasks such as text summarization, question answering, paraphrasing .
Outcome:	The proposed model performs better in some tasks than current models, but in most tasks, it is poor .

Copied to clipboard

Ninareh Mehrabi, Ahmad Beirami, Fred Morstatter, Aram Galstyan

Robustness in NLP

Challenge:	Existing work to generate adversarial attacks is costly and not scalable . despite the abundance of research in this area, little attention has been given to adversarials .
Approach:	They propose an adversarial attack mechanism that mitigates toxic language generation . they propose a defense mechanism that is scalable and can be generalized .
Outcome:	The proposed defense is effective at avoiding toxic language generation even against imperceptible toxicity triggers while preserving conversational flow.

REBEL: Relation Extraction By End-to-end Language generation (2021.findings-emnlp)

Copied to clipboard

Pere-Lluís Huguet Cabot, Roberto Navigli

Information Extraction & Text Mining

Challenge:	Existing approaches to extract relation triplets from text often involve multiple-step pipelines that propagate errors or are limited to a small number of relation types.
Approach:	They propose to use autoregressive seq2seq models to simplify Relation Extraction by expressing triplets as a sequence of text and a model that performs end-to-end relation extraction for more than 200 different relation types.
Outcome:	The proposed model achieves state-of-the-art on an array of Relation Extraction and Relation Classification benchmarks and achieves top performance in most of them.

Thought2Text: Text Generation from EEG Signal using Large Language Models (LLMs) (2025.findings-naacl)

Copied to clipboard

Abhijit Mishra, Shreya Shukla, Jose Torres, Jacek Gwizdka, Shounak Roychowdhury

Improving Abstraction in Text Summarization (D18-1)

Challenge:	Recent advances in NLP driven by powerful Large Language Models such as Ope-nAI GPT-4 have been demonstrated in ALS and stroke patients.
Approach:	They propose to use instruction-tuned Large Language Models (LLMs) with EEG data to decode and express brain activity in a comprehensible form.
Outcome:	The proposed approach enables multimodal description generation from EEG data and further refinement on embeddings to generate text directly from EMG during inference.

Copied to clipboard

Wojciech Kryściński, Romain Paulus, Caiming Xiong, Richard Socher

Performance-Guided LLM Knowledge Distillation for Efficient Text Classification at Scale (2024.emnlp-main)

Challenge:	Abstractive text summarization models do not capture the abstractive nature of high quality summaries.
Approach:	They propose to decompose a decoder into a contextual network and a pretrained language model that incorporates prior knowledge about language generation.
Outcome:	The proposed model achieves comparable results to state-of-the-art models, based on ROUGE scores and human evaluations, while producing a significantly higher level of abstraction.

Copied to clipboard

Flavio Palo, Prateek Singhi, Bilal Fadlallah

Information Retrieval

Challenge:	Large Language Models (LLMs) face high computational demands at inference time due to high computational costs.
Approach:	They propose a cost-effective and high-throughput solution for large language models . PGKD distills the knowledge of LLMs into smaller, task-specific models based on teacher-student knowledge distillation .
Outcome:	PGKD outperforms BERT-based models and other knowledge distillation methods on multi-class classification datasets.

Leveraging Pre-trained Language Models for Gender Debiasing (2022.lrec-1)

Copied to clipboard

Nishtha Jain, Declan Groves, Lucia Specia, Maja Popović

Programmable Annotation with Diversed Heuristics and Data Denoising (2022.coling-1)

Challenge:	Existing methods to reduce gender bias in natural language are costly and time-consuming.
Approach:	They propose a method to generate gender variants for a given text using pre-trained language models as the resource without any task-specific labelled data.
Outcome:	The proposed method can reduce gender bias in a language generation context without a task-specific labelled data.

Copied to clipboard

Ernie Chang, Alex Marin, Vera Demberg

Toward Stance-based Personas for Opinionated Dialogues (2020.findings-emnlp)

Challenge:	Neural natural language generation and understanding models require massive amounts of annotated data to be competitive.
Approach:	They propose a data programming framework that can jointly construct labeled data for language generation and understanding tasks by allowing annotators to modify an automatically-inferred alignment rule set between sequence labels and text.
Outcome:	The proposed framework generates high-quality data within a 1.48 BLEU and 6.42 slot F1 of 100% human-labeled data with just 100 labeled data samples outperforming benchmark annotation frameworks and other semi-supervised approaches.

Copied to clipboard

Thomas Scialom, Serra Sinem Tekiroğlu, Jacopo Staiano, Marco Guerini

Search Augmented Instruction Learning (2023.findings-emnlp)

Challenge:	chit-chat neural models lacking specificity and coherence, argues a new study on stance-based personas . stancebased personal representations lack generalization capability, allowing agents to sustain personal points of view both within the same conversation and across different discussions.
Approach:	They propose to investigate stance-based persona representations and their impact on claim generation by using a conversational dataset.
Outcome:	The proposed dataset shows that stance-based personas grasp abstract and profound aspects of the author persona.

Copied to clipboard

Hongyin Luo, Tianhua Zhang, Yung-Sung Chuang, Yuan Gong, Yoon Kim, Xixin Wu, Helen Meng, James Glass

MEGA: Multilingual Evaluation of Generative AI (2023.emnlp-main)

Challenge:	Large language models (LLMs) have been significantly improved by instruction fine-tuning, but still lack transparency and the ability to utilize up-to-date knowledge and information.
Approach:	They propose a search-augmented instruction learning model which grounds the language generation and instruction following abilities on complex search results generated by in-house and external search engines.
Outcome:	The proposed model outperforms plain LLMs on zero-shot language tasks and can generate both natural and programming languages following natural language guidance and requests.

Copied to clipboard

Kabir Ahuja, Harshita Diddee, Rishav Hada, Millicent Ochieng, Krithika Ramesh, Prachi Jain, Akshay Nambi, Tanuja Ganu, Sameer Segal, Mohamed Ahmed, Kalika Bali, Sunayana Sitaram

Multilinguality

Challenge:	Large Large Models (LLMs) have shown impressive performance on many natural language processing tasks such as language understanding, reasoning, and language generation.
Approach:	They present a framework for evaluating generative LLMs in the multilingual setting and provide directions for future progress in the field.
Outcome:	The proposed framework evaluates generative models on 16 NLP datasets across 70 typologically diverse languages and compares them to state-of-the-art non-autoregressive models.

Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models (2024.acl-long)

Copied to clipboard

Jinhao Duan, Hao Cheng, Shiqi Wang, Alex Zavalny, Chenan Wang, Renjing Xu, Bhavya Kailkhura, Kaidi Xu

FUDGE: Controlled Text Generation With Future Discriminators (2021.naacl-main)

Challenge:	Large Language Models (LLMs) show promising results in language generation but often “hallucinate”, making their outputs less reliable.
Approach:	They propose to shift attention to more relevant components at token- and sentence-levels for better UQ.
Outcome:	The proposed approach improves the performance of a range of popular “off-the-shelf” LLMs with model sizes extending up to 33B parameters.

Copied to clipboard

Kevin Yang, Dan Klein

Critic-Guided Decoding for Controlled Text Generation (2023.findings-acl)

Challenge:	Recent advances in large pretrained language models allow us to generate increasingly realistic text by modeling a distribution P (X) over natural language sequences X.
Approach:	They propose a flexible and modular method for controlled text generation that uses a Bayesian decomposition of the conditional distribution of G given an attribute predictor and can easily compose predictors for multiple desired attributes.
Outcome:	The proposed method can be easily composed and performs three tasks.

Copied to clipboard

Minbeom Kim, Hwanhee Lee, Kang Min Yoo, Joonsuk Park, Hwaran Lee, Kyomin Jung

Post-hoc Utterance Refining Method by Entity Mining for Faithful Knowledge Grounded Conversations (2023.emnlp-main)

Challenge:	Recent work has demonstrated reinforcement learning and weighted decoding as effective approaches to achieve a higher level of language control and quality with pros and cons.
Approach:	They propose a method that combines reinforcement learning and weighted decoding to train a critic from reward models.
Outcome:	The proposed method generates more coherent and well-controlled texts than previous methods on three controlled generation tasks, topic control, sentiment control, and detoxification.

Copied to clipboard

Yoonna Jang, Suhyune Son, Jeongwoo Lee, Junyoung Son, Yuna Hur, Jungwoo Lim, Hyeonseok Moon, Kisu Yang, Heuiseok Lim

Explaining How Transformers Use Context to Build Predictions (2023.acl-long)

Challenge:	Despite advances in language generation, models suffer from hallucinations that are either untrue or unfaithful to a given source.
Approach:	They propose a method to refine hallucinated utterances based on source knowledge . REM implicitly uses key entities in the knowledge to refine the utterant .
Outcome:	The proposed method reduces entity hallucination in the generated utterance and improves the quality of the model.

Copied to clipboard

Javier Ferrando, Gerard I. Gállego, Ioannis Tsiamas, Marta R. Costa-jussà

Explainability & Interpretability in NLP

Challenge:	Existing methods for analyzing input attributions for a model's prediction are unclear how prior words affect the model' s decision throughout the layers.
Approach:	They propose a procedure to analyze models for language generation using the Transformer and a comparison of their results with evidence of the linguistic phenomena.
Outcome:	The proposed method consistently aligns better than gradient-based and perturbation-based baselines and generates human-like source-target alignments for building predictions.

Summary Grounded Conversation Generation (2021.findings-acl)

Copied to clipboard

Chulaka Gunasekara, Guy Feigenblat, Benjamin Sznajder, Sachindra Joshi, David Konopnicki

Societal Biases in Language Generation: Progress and Challenges (2021.acl-long)

Challenge:	Existing datasets for conversation summarization are small due to the lack of large-scale datasets.
Approach:	They propose three approaches to generate summary grounded conversations, and evaluate the generated conversations using automatic measures and human judgements.
Outcome:	The proposed models can generate entire conversations with only a summary of a conversation as the input.

Copied to clipboard

Emily Sheng, Kai-Wei Chang, Prem Natarajan, Nanyun Peng

A Plug-and-Play Method for Controlled Text Generation (2021.findings-emnlp)

Challenge:	Language generation techniques can produce undesirable societal biases that can negatively impact marginalized populations.
Approach:	They propose to examine how decoding techniques contribute to biases in language generation . they also conduct experiments to quantify the effects of these techniques .
Outcome:	The proposed methods can reduce biases and improve user experience, the authors argue . they also show that the proposed techniques can reduce societal biase .

Copied to clipboard

Damian Pascual, Beni Egressy, Clara Meister, Ryan Cotterell, Roger Wattenhofer

RuCoLA: Russian Corpus of Linguistic Acceptability (2022.emnlp-main)

Challenge:	Existing methods for controlling language generation are not able to produce fluent text . current methods require additional models or fine-tuning to ensure specific words are included .
Approach:	They propose a plug-and-play decoding method that allows for controlled language generation . they add a shift in the probability distribution over our vocabulary towards semantically similar words .
Outcome:	The proposed method outperforms competing methods in human evaluations and does not impact fluency.

Copied to clipboard

Vladislav Mikhailov, Tatiana Shamardina, Max Ryabinin, Alena Pestova, Ivan Smurov, Ekaterina Artemova

The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding (2023.findings-acl)

Challenge:	Recent research has focused on evaluating the grammatical knowledge of language models with acceptability judgments.
Approach:	They propose to build a corpus of linguistic acceptability in Russian using a binary LA approach.
Outcome:	The proposed set of tests shows that the most widely used language models still fall behind humans by a large margin when detecting morphological and semantic errors.

Copied to clipboard

Hao Fang, Anusha Balakrishnan, Harsh Jhamtani, John Bufe, Jean Crawford, Jayant Krishnamurthy, Adam Pauls, Jason Eisner, Jacob Andreas, Dan Klein

Continuous Language Generative Flow (2021.acl-long)

Challenge:	In a task-oriented dialogue system, response generation is a conditional language model, but effective dialogue agents must balance fluent generation with stricter constraints.
Approach:	They propose a rule-based content selection model that transduces a dialogue agent’s actions and their results into context-free grammars representing the space of contextually acceptable responses.
Outcome:	The proposed architecture outperforms both rule-based and learned approaches in human evaluations of fluency, relevance, and truthfulness.

Copied to clipboard

Zineng Tang, Shiyue Zhang, Hyounghun Kim, Mohit Bansal

ContraCLM: Contrastive Learning For Causal Language Model (2023.acl-long)

Challenge:	Recent years have witnessed various types of generative models for natural language generation (NLG), especially RNNs or transformers.
Approach:	They propose a flow-based language generation model that adapts flow-derived generative models to language generation via continuous input embeddings, adapted affine coupling structures, and a novel architecture for autoregressive text generation.
Outcome:	The proposed model improves on QG and NMT and improves performance over baselines on SQuAD and TVQA and NML16.

Copied to clipboard

Nihal Jain, Dejiao Zhang, Wasi Uddin Ahmad, Zijian Wang, Feng Nan, Xiaopeng Li, Ming Tan, Ramesh Nallapati, Baishakhi Ray, Parminder Bhatia, Xiaofei Ma, Bing Xiang

INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback (2023.emnlp-main)

Challenge:	Existing studies show that causal language models lack expressiveness due to poor discrimination ability.
Approach:	They propose a contrastive learning framework that enhances discrimination of representations and bridges the gap with encoder-only models.
Outcome:	The proposed framework improves discrimination and source code generation capabilities on a variety of downstream tasks.

Copied to clipboard

Wenda Xu, Danqing Wang, Liangming Pan, Zhenqiao Song, Markus Freitag, William Wang, Lei Li

MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text (2022.emnlp-main)

Challenge:	Existing methods to evaluate the quality of language generation do not provide explicit explanation of their verdicts.
Approach:	They propose a fine-grained explainable evaluation metric for text generation that harnesses human instruction and implicit knowledge of GPT-4 to fine-tune it.
Outcome:	The proposed model outperforms all other unsupervised metrics on translation, captioning, data-to-text, and commonsense generation tasks.

Copied to clipboard

Wenhu Chen, Hexiang Hu, Xi Chen, Pat Verga, William Cohen

Top-Down Structurally-Constrained Neural Response Generation with Lexicalized Probabilistic Context-Free Grammar (N19-1)

Challenge:	Pre-trained language models store a massive amount of world knowledge implicitly in their parameters, but large models often fail to encode information about rare entities and events.
Approach:	They propose a retrieval-augmented model which accesses an external non-parametric memory to augment language generation.
Outcome:	The proposed model outperforms existing models by 10-20% absolute on two datasets and under distractor and full-wiki settings.

Copied to clipboard

Wenchao Du, Alan W Black

Few-Shot Pidgin Text Adaptation via Contrastive Fine-Tuning (2022.coling-1)

Challenge:	Neural encoder-decoder architectures have shown promise for natural language generation.
Approach:	They propose to generate words according to order of first appearance in lexicalized PCFG parse tree . they also combine neural model with symbolic approach to generate syntactic structure .
Outcome:	The proposed method improves over sequence-to-sequence baseline in diversity and relevance.

Copied to clipboard

Ernie Chang, Jesujoba O. Alabi, David Ifeoluwa Adelani, Vera Demberg

Optimus: Organizing Sentences via Pre-trained Modeling of a Latent Space (2020.emnlp-main)

Challenge:	Currently, low resource languages are not supported by proper translation systems or parallel corpus.
Approach:	They propose to fine-tune the pretrained language models to generate utterances in English-to-Pidgin by leveraging the proximity of the source and target languages and using positive and negative examples in constrastive training objectives.
Outcome:	The proposed method is sufficient to generate utterances in English-to-Pidgin, which are two closely-related languages.

Copied to clipboard

Chunyuan Li, Xiang Gao, Yuan Li, Baolin Peng, Xiujun Li, Yizhe Zhang, Jianfeng Gao

Annotating Modality Expressions and Event Factuality for a Japanese Chess Commentary Corpus (L18-1)

Challenge:	Existing models for language understanding and understanding can be trained to provide contextualized representations of words based on text data.
Approach:	They propose a large-scale language VAE model Optimus that is pre-trained on large text corpus and fine-tuned for various language generation and understanding tasks.
Outcome:	The proposed model achieves new state-of-the-art on VAE language modeling benchmarks.

Copied to clipboard

Suguru Matsuyoshi, Hirotaka Kameko, Yugo Murawaki, Shinsuke Mori

Challenge:	In recent years, there has been a surge of interest in the natural language processing related to the real world . shogi commentaries are an interesting testbed for these tasks, but can be grounded in the game tree .
Approach:	They propose to augment shogi commentaries with game states to generate a game commentary generator.
Outcome:	The proposed system can be used to ground symbols and events with factuality . it can be compared with other systems to find out if a commentator is a human .

Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data (D18-1)

Copied to clipboard

Guanghui Qin, Jin-Ge Yao, Xuening Wang, Jinpeng Wang, Chin-Yew Lin

“My Answer is C”: First-Token Probabilities Do Not Match Text Answers in Instruction-Tuned Language Models (2024.findings-acl)

Challenge:	Existing work on grounded language learning does not capture the semantics of correspondences between structured world state representations and texts.
Approach:	They propose to learn explicit latent semantic annotations from paired structured tables and texts . they use an adapted semi-hidden Markov model to impose a soft constraint to further improve performance .
Outcome:	The proposed framework improves on a semi-hidden Markov model and extracts templates for language generation.

Copied to clipboard

Xinpeng Wang, Bolei Ma, Chengzhi Hu, Leon Weber-Genzel, Paul Röttger, Frauke Kreuter, Dirk Hovy, Barbara Plank

DuNST: Dual Noisy Self Training for Semi-Supervised Controllable Text Generation (2023.acl-long)

Challenge:	Multiple choice questions are one of the most popular evaluation formats for understanding the capabilities of autoregressive large language models (LLMs).
Approach:	They evaluated how aligned first-token evaluation is with the text output along several dimensions, namely final option choice, refusal rate, choice distribution and robustness under prompt perturbation.
Outcome:	The proposed evaluation methods are misaligned on all dimensions, reaching mismatch rates over 60%.

Copied to clipboard

Yuxi Feng, Xiaoyuan Yi, Xiting Wang, Laks Lakshmanan, V.S., Xing Xie

WatME: Towards Lossless Watermarking Through Lexical Redundancy (2024.acl-long)

Challenge:	Existing approaches to augment self-training (ST) in attribute-controllable language generation are limited and limited.
Approach:	They propose a new ST framework that integrates self-generated pseudo text into attribute-controllable language generation.
Outcome:	The proposed framework can be applied to semi-supervised controllable language generation.

Copied to clipboard

Liang Chen, Yatao Bian, Yang Deng, Deng Cai, Shuaiyi Li, Peilin Zhao, Kam-Fai Wong

Challenge:	Existing methods for text watermarking rely on arbitrary vocabulary partitioning during decoding, which compromises the availability of suitable tokens and significantly degrades the quality of responses.
Approach:	They propose a method that leverages linguistic prior knowledge of lexical redundancies in LLM vocabularies to seamlessly integrate watermarks.
Outcome:	The proposed approach preserves the expressive power of large language models while preserving watermark detectability.

Determinantal Beam Search (2021.acl-long)

Copied to clipboard

Clara Meister, Martina Forster, Ryan Cotterell

Data-scarce Behavior Editing of Language Models (2025.findings-emnlp)

Challenge:	a new beam search approach allows for a diverse subset selection process . standard beam search does not encode interactions between candidates .
Approach:	They propose a beam search reformulation that casts subset selection as the subdeterminant optimization problem.
Outcome:	The proposed method offers competitive performance against other diverse set generation strategies while providing a more general approach to optimizing for diversity.

Copied to clipboard

Joykirat Singh, Subhabrata Dutta, Tanmoy Chakraborty

Ontologically Faithful Generation of Non-Player Character Dialogues (2024.emnlp-main)

Challenge:	Prior studies show that noisy neural circuitries coexist with generalizable abilities within LLMs.
Approach:	a new method is proposed to improve the generalizability of large-scale web-based text models . a TaRot method is based on learnable rotation matrices optimized for Bayesian optimization .
Outcome:	a new method for task adaptation improves on multiple classification and generation tasks . it improves upon zero- and few-shot performance, with average improvements of 14% and 15% .

Copied to clipboard

Nathaniel Weir, Ryan Thomas, Randolph d’Amore, Kellie Hill, Benjamin Van Durme, Harsh Jhamtani

GanLM: Encoder-Decoder Pre-training with an Auxiliary Discriminator (2023.acl-long)

Challenge:	a key challenge in creating NPC dialogues is that they should serve coherent narratives.
Approach:	They propose to use supervised and in-context learning techniques to generate trees of dialogue between video game characters that accurately reflect quest and entity specifications.
Outcome:	The proposed model performs well but room for improvement.

Copied to clipboard

Jian Yang, Shuming Ma, Li Dong, Shaohan Huang, Haoyang Huang, Yuwei Yin, Dongdong Zhang, Liqun Yang, Furu Wei, Zhoujun Li

Substance over Style: Document-Level Targeted Content Transfer (2020.emnlp-main)

Challenge:	Existing pre-training methods underutilize the benefits of language understanding for generation.
Approach:	They propose a GAN-style model for encoder-decoder pre-training with an auxiliary discriminator.
Outcome:	The proposed model outperforms existing pre-trained models and achieves state-of-the-art performance.

Copied to clipboard

Allison Hegel, Sudha Rao, Asli Celikyilmaz, Bill Dolan

Enhancing Image-to-Text Generation in Radiology Reports through Cross-modal Multi-Task Learning (2024.lrec-main)

Challenge:	Existing language models excel at writing from scratch, but many real-world scenarios require rewriting an entire document to fit a set of constraints.
Approach:	They propose a document-level targeted content transfer task that addresses the challenge of rewriting an entire document coherently by generating coherent and diverse rewrites that obey a constraint while remaining close to the original document.
Outcome:	The proposed model outperforms existing methods by generating coherent and diverse rewrites that obey the constraint while remaining close to the original document.

Copied to clipboard

Nurbanu Aksoy, Nishant Ravikumar, Serge Sharoff

Annotating Event Appearance for Japanese Chess Commentary Corpus (2020.lrec-1)

Challenge:	Image-to-text generation relies on independent models for image understanding and natural language generation, which often exhibit a semantic gap between visual and textual information.
Approach:	They propose a multi-task learning framework to leverage both visual and non-imaging data for generating radiology reports.
Outcome:	The proposed framework improves performance over single-task baselines across language generation metrics and mitigates overfitting in auxiliary tasks.

Copied to clipboard

Hirotaka Kameko, Shinsuke Mori

Challenge:	Recent studies show that text and non-text data are not always a “true” pair.
Approach:	They propose "Event Appearance" labels that show the relationship between events mentioned in texts and those happening in the real world.
Outcome:	The proposed labels show the relationship between events mentioned in texts and those happening in the real world.

Continuity of Topic, Interaction, and Query: Learning to Quote in Online Conversations (2020.emnlp-main)

Copied to clipboard

Lingzhi Wang, Jing Li, Xingshan Zeng, Haisong Zhang, Kam-Fai Wong

Context-Tuning: Learning Contextualized Prompts for Natural Language Generation (2022.coling-1)

Challenge:	Quotations are crucial for successful explanations and persuasions in interpersonal communications.
Approach:	They propose to use an encoder-decoder neural framework to continue the context with a quotation via language generation to capture latent topics, interactions with the dialogue history, and coherence to the existing contents.
Outcome:	The proposed model outperforms state-of-the-art models on two large-scale datasets in English and Chinese and shows that topic, interaction, and query consistency are helpful to learn how to quote in online conversations.

Copied to clipboard

Tianyi Tang, Junyi Li, Wayne Xin Zhao, Ji-Rong Wen

Erxin Yu, Jing Li, Chunpu Xu

Challenge:	Recent studies have shown that pretrained language models (PLMs) lack sufficient consideration of input semantics to generate natural language.
Approach:	They propose a continuous prompting approach to fine-tune PLMs for natural language generation by modeling an inverse generation process from output to input.
Outcome:	The proposed method fine-tunes only 0.12% of the parameters while maintaining good performance.

Copied to clipboard

Speculative Diffusion Decoding: Accelerating Language Generation through Diffusion (2025.naacl-long)

Challenge:	Existing studies show that the wording of tweets can significantly impact popularity, reflected by user replies, retweets, and likes.
Approach:	They propose a novel approach to generate popular quote tweets by leveraging augmented auto-responses from readers to align language generation with popularity.
Outcome:	The proposed model outperforms existing models that do not incorporate response augmentation and can generate popular quote tweets with augmented auto-responses.

Copied to clipboard

Jacob K Christopher, Brian R. Bartoldson, Tal Ben-Nun, Michael Cardei, Bhavya Kailkhura, Ferdinando Fioretto

Generating Sentences from Disentangled Syntactic and Semantic Spaces (P19-1)

Challenge:	Existing methods to accelerate large language model inference are limited by the reliance on incremental token generation in existing draft models.
Approach:	They propose an adaptation of speculative decoding which uses discrete diffusion models to generate draft sequences and allows parallelization of both the drafting and verification steps.
Outcome:	The proposed approach provides 7.2x speedups over standard generation processes and 1.75x speed ups over existing speculative decoding approaches.

Copied to clipboard

Yu Bao, Hao Zhou, Shujian Huang, Lei Li, Lili Mou, Olga Vechtomova, Xin-yu Dai, Jiajun Chen

Syntactic Text Processing

Challenge:	Variational auto-encoders (VAEs) are widely used in natural language generation due to the regularization of the latent space.
Approach:	They propose to generate sentences from disentangled syntactic and semantic spaces by using the linearized tree sequence.
Outcome:	The proposed method achieves similar or better performance in various tasks compared with state-of-the-art models.

FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction (2026.acl-long)

Copied to clipboard

Dong Shu, Yanguang Liu, Huopu Zhang, Mengnan Du

Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning (2020.emnlp-main)

Challenge:	Existing models for earnings surprise prediction rely on expensive, proprietary data.
Approach:	They propose to use textual transcripts and audio recordings to build a dataset for earnings surprise prediction.
Outcome:	The proposed dataset includes 2,688 unique conference calls from 2019 to 2021.

Copied to clipboard

Xiaoxiao Guo, Mo Yu, Yupeng Gao, Chuang Gan, Murray Campbell, Shiyu Chang

Machine Reading Comprehension

Challenge:	Interactive Fiction (IF) games with real human-written natural language texts provide a new natural evaluation for language understanding techniques.
Approach:	They propose to re-formulate IF game solving as Multi-Passage Reading Comprehension tasks using context-query attention mechanisms and structured prediction to efficiently generate and evaluate action outputs.
Outcome:	The proposed methods achieve high winning rates and low data requirements on the recent IF benchmark (Jericho)

Is GPT-4 a Good Data Analyst? (2023.findings-emnlp)

Copied to clipboard

Liying Cheng, Xingxuan Li, Lidong Bing

PALM: Pre-training an Autoencoding&Autoregressive Language Model for Context-conditioned Generation (2020.emnlp-main)

Challenge:	Large language models (LLMs) have shown their powerful capabilities in plenty of domains and tasks, including context understanding, code generation, language generation, data storytelling, etc.
Approach:	They propose to use GPT-4 as a data analyst to perform end-to-end data analysis with databases from a wide range of domains.
Outcome:	The proposed framework compares GPT-4 with human data analysts to perform end-to-end data analysis with databases from a wide range of domains.

Copied to clipboard

Bin Bi, Chenliang Li, Chen Wu, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, Luo Si

Distilling Knowledge Learned in BERT for Text Generation (2020.acl-main)

Challenge:	Existing techniques for natural language understanding and generation use autoencoding and/or autoregressive objectives to train models.
Approach:	They propose a self-supervised pre-training scheme that pre-trains an autoencoding and autoregressive language model on a large unlabeled corpus for generating new text conditioned on context.
Outcome:	The proposed scheme achieves state-of-the-art results on a variety of language generation benchmarks covering generative question answering, abstractive summarization and conversational response generation.

Copied to clipboard

Yen-Chun Chen, Zhe Gan, Yu Cheng, Jingzhou Liu, Jingjing Liu

SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation (2023.findings-acl)

Challenge:	Large-scale pre-trained language models such as BERT have revolutionized the state of the art in many language understanding tasks.
Approach:	They propose a conditional masked language modeling approach to fine tune BERT on target generation tasks by imposing global sequence-level supervision on conventional Seq2Seq models.
Outcome:	The proposed model outperforms strong Transformer baselines on multiple language generation tasks such as machine translation and text summarization.

Copied to clipboard

Xueliang Zhao, Tingchen Fu, Lemao Liu, Lingpeng Kong, Shuming Shi, Rui Yan

Get Confused Cautiously: Textual Sequence Memorization Erasure with Selective Entropy Maximization (2025.coling-main)

Challenge:	Existing studies on logical data-to-text generation rely on neural language models to generate the final table description, but they have difficulty working out key entities in the description.
Approach:	They propose a symbolic reasoning framework that reasons out each entity in the table description with a table-compatible programming language.
Outcome:	The proposed framework outperforms existing methods on three datasets and three backbones with an absolute improvement of 5.7%11.5% on SP-Acc.

Copied to clipboard

Zhaohan Zhang, Ziquan Liu, Ioannis Patras

Countering Reward Over-Optimization in LLM with Demonstration-Guided Reinforcement Learning (2024.findings-acl)

Challenge:	Existing methods for erasure of memorized text fail to unlearn large numbers of memorizable samples without jeopardizing model utility.
Approach:	They propose a method that allows LLMs to memorize and recite some training sequences verbatim . they propose an entropy-based loss method that is shown to be more stable .
Outcome:	The proposed method improves model utility and accuracy while preserving model ability in language generation and understanding.

Copied to clipboard

Mathieu Rita, Florian Strub, Rahma Chaabouni, Paul Michel, Emmanuel Dupoux, Olivier Pietquin

Challenge:	Existing approaches address ROO by adding KL regularization, requiring computationally expensive hyperparameter tuning.
Approach:	They propose a reinforcement learning approach that leverages human demonstrations and a reward model to recalibrate the reward objective.
Outcome:	The proposed approach achieves comparable performance to carefully tuned baselines while mitigating ROO in three RL language tasks.

Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control (2023.findings-acl)

Copied to clipboard

Xiang Fan, Yiwei Lyu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency

Large Language Models Are Poor Clinical Decision-Makers: A Comprehensive Benchmark (2024.emnlp-main)

Challenge:	Existing methods for controlling the distribution of generated text only work with quantified distributions, which require pre-defined categories, proportions of the distribution, or an existing corpus following the desired distributions.
Approach:	They propose a few-shot human-in-the-loop training algorithm that allows distribution control for text generation via human feedback.
Outcome:	The proposed algorithm achieves state-of-the-art results on single topic/attribute and quantified distribution control compared to previous works.

Copied to clipboard

Fenglin Liu, Zheng Li, Hongjian Zhou, Qingyu Yin, Jingfeng Yang, Xianfeng Tang, Chen Luo, Ming Zeng, Haoming Jiang, Yifan Gao, Priyanka Nigam, Sreyashi Nag, Bing Yin, Yining Hua, Xuan Zhou, Omid Rohanian, Anshul Thakur, Lei Clifton, David Clifton

Captioning for Text-Video Retrieval via Dual-Group Direct Preference Optimization (2025.findings-emnlp)

Challenge:	Existing studies focus on evaluating large language models in close-ended QA tasks, but many clinical decisions involve answering open-ended questions without pre-set options.
Approach:	They construct a benchmark to better understand large language models in the clinic . they use existing datasets to evaluate LLMs in clinical situations .
Outcome:	The proposed model outperforms human experts in multiple medical tasks.

Copied to clipboard

Ji Soo Lee, Byungoh Ko, Jaewon Cho, Howoong Lee, Jaewoon Byun, Hyunwoo J. Kim

ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning (2023.findings-emnlp)

Challenge:	auxiliary captions are generic and indistinguishable across visually similar videos . conventional captioning approaches are evaluated using language relevance scores .
Approach:	They propose a retrieval framework that directly optimizes caption generation using retrieval relevance scores.
Outcome:	The proposed retrieval framework optimizes caption generation using retrieval relevance scores . dual-group direct preference optimization is a learning strategy that supervises captioning .

Copied to clipboard

Viet Lai, Nghia Ngo, Amir Pouran Ben Veyseh, Hieu Man, Franck Dernoncourt, Trung Bui, Thien Nguyen

On the Robustness of Editing Large Language Models (2024.emnlp-main)

Challenge:	Recent advances in natural language processing (NLP) have led to significant breakthroughs in the field.
Approach:	They evaluate ChatGPT over multiple tasks with diverse languages and large datasets to provide more comprehensive information for multilingual NLP applications.
Outcome:	The proposed model can process and generate texts for multiple languages due to its multilingual training data.

Copied to clipboard

Xinbei Ma, Tianjie Ju, Jiyang Qiu, Zhuosheng Zhang, Hai Zhao, Lifeng Liu, Yulong Wang

Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis (2024.emnlp-main)

Challenge:	Existing studies have exhibited impressive success and significant potential.
Approach:	They propose to modify the knowledge memory with minimum computational cost while preserving the performance on the retained knowledge.
Outcome:	The proposed methods avoid retraining to update the model parameters and have demonstrated promising performance and efficiency.

Copied to clipboard

Guangliang Liu, Haitao Mao, Jiliang Tang, Kristen Johnson

Question Answering

Challenge:	Existing studies on the effectiveness of moral self-correction in large language models have not been conducted.
Approach:	They propose that moral self-correction is a computationally efficient method for reducing harmful content in LLMs.
Outcome:	The proposed method reduces harmful content in LLMs, but it remains under-explored . it can help LLM find shortcut to more morally correct output, the authors argue .

FactLens: Benchmarking Fine-Grained Fact Verification (2025.findings-acl)

Copied to clipboard

Kushan Mitra, Dan Zhang, Sajjadur Rahman, Estevam Hruschka

ECLM: Entity Level Language Model for Spoken Language Understanding with Chain of Intent (2025.acl-long)

Challenge:	Large Language Models (LLMs) have shown impressive capability in language generation and understanding, but their tendency to hallucinate and produce factually incorrect information remains a key limitation.
Approach:	They propose a benchmark to evaluate fine-grained fact verification where claims are broken down into smaller sub-claims for individual verification.
Outcome:	The proposed model enables more precise identification of inaccuracies, improved transparency, and reduced ambiguity in evidence retrieval.

Copied to clipboard

Shangjian Yin, Peijie Huang, JiaTian Chen, Haojing Huang, Yuhong Xu

JoPA: Explaining Large Language Model’s Generation via Joint Prompt Attribution (2025.acl-long)

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance, but their application to spoken language understanding remains challenging.
Approach:	They propose an Entity-level Language Model framework which reformulates slot-filling as an entity recognition task and introduces a new concept, Chain of Intent, to enable step-by-step multi-intent recognition.
Outcome:	The proposed framework outperforms strong baselines such as Uni-MIS and achieves gains of 3.7% and 3.1% on MixATIS and MixSNIPS.

Copied to clipboard

Yurui Chang, Bochuan Cao, Yujia Wang, Jinghui Chen, Lu Lin

Through the Magnifying Glass: Adaptive Perception Magnification for Hallucination-Free VLM Decoding (2026.acl-long)

Challenge:	Existing attempts to explain the entire language generation often treat input prompt texts independently, ignoring their combinatorial effects on the follow-up generation.
Approach:	They propose a framework for explaining how a few prompt texts collaboratively influences the LLM's complete generation.
Outcome:	The proposed explanations demonstrate faithfulness and efficiency of the proposed framework.

Copied to clipboard

Shunqi Mao, Chaoyi Zhang, Weidong Cai

CEBC: Conformal Evidence-Bounded Control for Low-Hallucination Vision–Language Generation (2026.acl-long)

Challenge:	Existing vision-language models suffer from visual hallucination, where the generated responses contain inaccuracies that are not grounded in the visual input.
Approach:	They propose a visual decoding method that iteratively isolates relevant visual tokens based on attention and magnifies the corresponding regions.
Outcome:	The proposed method reduces language biases and amplifies weights of visual embedding during decoding, while still preserving strong reasoning capabilities.

Copied to clipboard

Ashish Mishra, Tarun Kumar, Arpit Shah, Suparna Bhattacharya, Martin Foltin