Papers with natural language generation
Automatic and Human-AI Interactive Text Generation (with a focus on Text Simplification and Revision) (2024.acl-tutorials)
Copied to clipboard
| Challenge: | In this tutorial, we focus on text-to-text generation, a class of natural language generation tasks, that takes a piece of text as input and then generates a revision that is improved according to some specific criteria. |
| Approach: | This tutorial focuses on text-to-text generation, a class of natural language generation tasks that takes a piece of text as input and generates a revision that is improved according to some specific criteria. |
| Outcome: | This tutorial focuses on text-to-text generation, a class of natural language generation tasks, that takes a piece of text as input and generates a revision that is improved according to some specificcriteria. |
ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation (D19-3)
Copied to clipboard
| Challenge: | Generative modeling of editing text with respect to control attributes has seen increasing progress over the past few years. |
| Approach: | They propose an auxiliary text rewriting tool that facilitates the rewrite process for natural language generation tasks. |
| Outcome: | The proposed tool facilitates the rewriting process for natural language generation tasks, such as paraphrasing, text simplification, fairness-aware text rewrite, and text style transfer. |
An automated medical scribe for documenting clinical encounters (N18-5)
Copied to clipboard
Gregory Finley, Erik Edwards, Amanda Robinson, Michael Brenndoerfer, Najmeh Sadoughi, James Fone, Nico Axtmann, Mark Miller, David Suendermann-Oeft
| Challenge: | a medical scribe is a clinical professional who charts patient–physician encounters in real time. |
| Approach: | They propose to use multiple speech and language technologies to create an automated medical scribe. |
| Outcome: | a medical scribe can be used as an alternative to human scribes or as an assistive tool for physicians . the system relies on multiple speech and language technologies, including speaker diarization, medical speech recognition, knowledge extraction, and natural language generation. |
Deep Learning on Graphs for Natural Language Processing (2021.naacl-tutorials)
Copied to clipboard
| Challenge: | Graph Neural Networks (GNNs) are powerful tools for non-Euclidean data modeling and are used in many graph-related NLP tasks. |
| Approach: | This tutorial will cover applying deep learning on graph techniques to NLP using Graph Neural Networks (GNNs) Graph4NLP is the first library for researchers and practitioners for easy use of GNNs for various NLP tasks. |
| Outcome: | This tutorial will cover the latest developments in deep learning on graph techniques and their applications in various NLP tasks. |
ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing evaluation methods for natural language generation rely on token-level or embedding-level comparisons with text references. |
| Approach: | They propose to use text-to-image generator to generate an image as the embodied imagination for the text snippet and compute the imagination similarity using contextual embeddings. |
| Outcome: | The proposed metric improves existing evaluation metrics’ correlations with human similarity judgments in both reference-based and reference-free scenarios. |
Locally Typical Sampling (2023.tacl-1)
Copied to clipboard
| Challenge: | a discrepancy in probabilistic language generators has puzzled the language generation community for years . |
| Approach: | They propose a method for local typical sampling to enforce a conditional entropy criterion for probabilistic models. |
| Outcome: | The proposed method can provide new insights into why high-probability texts can be dull or repetitive. |
QiuNiu: A Chinese Lyrics Generation System with Passage-Level Input (2022.acl-demo)
Copied to clipboard
| Challenge: | Existing systems based on attributes or keywords render lyrics generation very limited . previous studies focused on generating lyrics based only on attributes and keywords . |
| Approach: | They propose to use Chinese passage-level text as input for lyrics generation . they initialize parameters with custom pretrained Chinese GPT-2 model and adopt a two-step process to fine-tune the model for better alignment between passage- level text and lyrics. |
| Outcome: | The proposed system is conditioned on passage-level text rather than attributes or keywords, rendering limited control over the content of the lyrics. |
LLM Comparative Assessment: Zero-shot NLG Evaluation through Pairwise Comparisons using Large Language Models (2024.eacl-long)
Copied to clipboard
| Challenge: | Recent advances in large language models have enabled impressive zero-shot capabilities across various natural language tasks. |
| Approach: | They propose two ways to exploit the emergent abilities of large language models for NLG assessment. |
| Outcome: | The proposed methods improve performance and positional biases in comparisons between candidates. |
Slot-consistent NLG for Task-oriented Dialogue Systems with Iterative Rectification Network (2020.acl-main)
Copied to clipboard
| Challenge: | Existing approaches to natural language generation are prone to errors, such as neglecting input slot values and generating redundant slot values. |
| Approach: | They propose an iterative rectification network to improve general NLG systems . they apply bootstrapping algorithms to sample training candidates and incorporate reward . |
| Outcome: | The proposed methods significantly reduce the slot error rate for strong baselines. |
HAD: HAllucination Detection Language Models Based on a Comprehensive Hallucination Taxonomy (2026.acl-industry)
Copied to clipboard
| Challenge: | relying on large language models for information has raised concerns about reliability and accuracy of outputs. |
| Approach: | They propose a hallucination taxonomy with 11 categories for various NLG tasks and propose HAllucination Detection models which integrate hallucinism detection, span-level identification, and correction into a single inference process. |
| Outcome: | The proposed models outperform baselines on HaluEval, FactCHD, and FaithBench, confirming their robustness and versatility. |
RankME: Reliable Human Ratings for Natural Language Generation (N18-2)
Copied to clipboard
| Challenge: | Existing studies have shown that human evaluation for natural language generation often suffers from inconsistent user ratings. |
| Approach: | They propose a rank-based magnitude estimation method which combines continuous scales and relative assessments to improve the reliability of human ratings. |
| Outcome: | The proposed method significantly improves the reliability and consistency of human ratings compared to traditional evaluation methods. |
kogito: A Commonsense Knowledge Inference Toolkit (2023.eacl-demo)
Copied to clipboard
| Challenge: | kogito provides an intuitive and extensible interface to interact with natural language generation models. |
| Approach: | They propose to use kogito to generate commonsense inferences from text . they use a standardized API for training and evaluating knowledge models . |
| Outcome: | The proposed tool provides an intuitive and extensible interface to interact with natural language generation models. |
Uncertainty in Language Models: Assessment through Rank-Calibration (2024.emnlp-main)
Copied to clipboard
Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban
| Challenge: | Language Models (LMs) have shown promising performance in natural language generation . however, it is crucial to correctly quantify their level of uncertainty in responding to inputs. |
| Approach: | They propose a framework to quantify uncertainty and confidence for Large Language Models . they use a Rank-calibration framework to measure uncertainty and confident responses . |
| Outcome: | The proposed framework assesses uncertainty and confidence measures for LMs. |
Few-Shot NLG with Pre-Trained Language Model (2020.acl-main)
Copied to clipboard
| Challenge: | Neural-based approaches to natural language generation are data-hungry and difficult to adopt in real-world applications. |
| Approach: | They propose a task of few-shot natural language generation from structured data or knowledge to generate coherent sentences from input data and language modeling to compose coherent sentences. |
| Outcome: | The proposed approach outperforms the strongest baseline approach by over 8.0 BLEU points improvement. |
Fluent Response Generation for Conversational Question Answering (2020.acl-main)
Copied to clipboard
| Challenge: | Question answering (QA) is an important aspect of open-domain conversational agents, garnering specific research focus in the conversational QA subtask. |
| Approach: | They propose a method for situating QA responses within a SEQ2SEQ NLG approach to generate fluent grammatical answer responses while maintaining correctness. |
| Outcome: | The proposed model outperforms baseline CoQA and QuAC models in generating conversational responses. |
DeepGen: Diverse Search Ad Generation and Real-Time Customization (2022.emnlp-demos)
Copied to clipboard
| Challenge: | Existing systems that generate ads manually are not effective in generating ad copy and generating millions of ads for large businesses. |
| Approach: | They propose a system that generates fluent ads from advertiser’s web pages in an abstractive fashion and solves practical issues such as factuality and inference speed. |
| Outcome: | The proposed system generates fluent ads from advertiser’s web pages in an abstractive fashion and solves practical issues such as factuality and inference speed. |
Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning (2022.coling-1)
Copied to clipboard
| Challenge: | In task-oriented dialogue systems, the role of the natural language generation component is to convert a system's intentions, called dialogue acts (DAs), into natural language utterances and to convey DAs accurately to users. |
| Approach: | They propose a method for Adaptive Natural language generation for Task-Oriented dialogue via Reinforcement learning that incorporates a natural language understanding module into the objective function of RL. |
| Outcome: | The proposed method generates adaptive utterances against speech recognition errors and the different vocabulary levels of users in a multi-world task-oriented dialogue system. |
Mixed Feelings: Natural Text Generation with Variable, Coexistent Affective Categories (P18-3)
Copied to clipboard
| Challenge: | a recent study has shown that language models which can generate emotional sentences are limited to one affective category out of a few. |
| Approach: | a new research proposal proposes a language model which can produce multiple emotions simultaneously. authors propose to use a long-term memory language model to allow for variation in multiple emotions. |
| Outcome: | a new language model allows for variation in multiple emotions simultaneously . the proposed model is based on a model of long-term memory . |
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications (2022.naacl-main)
Copied to clipboard
| Challenge: | Evaluating natural language generation systems is difficult, as there are many ways to express similar things in text. |
| Approach: | They combine interviews with NLG practitioners to examine ethical considerations and their implications for NLG evaluation. |
| Outcome: | The findings of the study surface goals, community practices, assumptions, and constraints that shape NLG evaluations, and examine their implications and how they embody ethical considerations. |
Probabilistically Masked Language Model Capable of Autoregressive Generation in Arbitrary Word Order (2020.acl-main)
Copied to clipboard
| Challenge: | Large-scale pretrained language models such as masked language model (MLM) have brought significant improvements to many NLU and NLG tasks. |
| Approach: | They propose a probabilistic masking scheme for the masked language model and a model with a uniform prior distribution on the masking ratio. |
| Outcome: | The proposed model outperforms BERT on a bunch of downstream NLG tasks. |
RoFT: A Tool for Evaluating Human Detection of Machine-Generated Text (2020.emnlp-demos)
Copied to clipboard
| Challenge: | Existing studies on how humans perceive machine-generated text are limited due to the prohibitive cost of running human evaluation studies. |
| Approach: | They propose a task to detect the boundary at which a text passage starts off human-written transitions to being machine-generated. |
| Outcome: | The proposed system evaluates machine-generated news articles on a wide range of domains. |
Evaluating the Evaluation of Diversity in Natural Language Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods for controlling diversity by tuning a “decoding parameter” affect form but not meaning. |
| Approach: | They propose a framework that measures correlation between a diversity metric and a parameter that controls some aspect of diversity in generated text. |
| Outcome: | The proposed framework outperforms existing methods in estimating diversity . it shows that humans outperformed existing methods but affect form but not meaning . |
VOLTA: Improving Generative Diversity by Variational Mutual Information Maximizing Autoencoder (2024.findings-naacl)
Copied to clipboard
| Challenge: | generative diversity is a critical yet underexplored issue in natural language generation . previous approaches to enhance diversity of Transformer models have been limited by their latent variables . |
| Approach: | They propose a framework that bridges Transformer with VAE to enhance generative diversity. |
| Outcome: | The proposed framework improves generative diversity while maintaining generative quality. |
FastSeq: Make Sequence Generation Faster (2021.acl-demo)
Copied to clipboard
Yu Yan, Fei Hu, Jiusheng Chen, Nikhil Bhendawade, Ting Ye, Yeyun Gong, Nan Duan, Desheng Cui, Bingyu Chi, Ruofei Zhang
| Challenge: | Transformer-based models have made tremendous impact in natural language generation, but inference speed is still a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. |
| Approach: | They propose an attention cache optimization, an efficient algorithm for detecting repeated n-grams, and an asynchronous generation pipeline with parallel I/O to accelerate sequence generation without loss of accuracy. |
| Outcome: | The proposed framework can accelerate the sequence generation by 4x to 9x with a simple one-line code change for a set of widely used and diverse models. |
Ecco: An Open Source Library for the Explainability of Transformer Language Models (2021.acl-demo)
Copied to clipboard
| Challenge: | Existing models that use the Transformer architecture are lag behind our ability to scale them. |
| Approach: | They propose an open-source library for the explainability of Transformer-based NLP models that captures, analyzes, visualizes, and interactively explores the inner mechanics of these models. |
| Outcome: | The proposed tools capture, analyze, visualize, and explore the inner workings of Transformer-based language models. |
Controlled Language Generation for Language Learning Items (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Recent advances in pre-trained language models have resulted in success in generating fluent English text. |
| Approach: | They propose to employ natural language generation to rapidly generate English language items . they experiment with deep pretrained models and develop methods for controlling items for factors relevant in language learning . |
| Outcome: | The proposed framework shows high grammatically scores for all models and higher complexity over baseline models. |
Automatic Generation of Personalized Comment Based on User Profile (P19-2)
Copied to clipboard
| Challenge: | Experimental results show that our model can generate natural, human-like and personalized comments. |
| Approach: | They propose a model that takes user profile into account when generating comments on social media and integrates it with a gated memory. |
| Outcome: | The proposed model can generate natural, human-like and personalized comments on social media. |
Breaking Writer’s Block: Low-cost Fine-tuning of Natural Language Generation Models (2021.eacl-demos)
Copied to clipboard
| Challenge: | Currently, it is standard procedure to fine-tune large pre-trained language models for information extraction tasks, but this is not the case for generation tasks, which relies on a variety of techniques for controlled language generation. |
| Approach: | They propose a system that fine-tunes a natural language generation model for the problem of solving writer’s block. |
| Outcome: | The proposed system obtains excellent results even with a small number of epochs and a total cost of USD 150. |
Inseq: An Interpretability Toolkit for Sequence Generation Models (2023.acl-demo)
Copied to clipboard
| Challenge: | Recent studies focused on classification tasks while largely overlooking generation settings due to a lack of dedicated tools. |
| Approach: | They propose to use Inseq to democratize access to interpretability analyses of sequence generation models by enabling intuitive extraction of models’ internal information and feature importance scores for popular decoder-only and encoder-decoder Transformers architectures. |
| Outcome: | The proposed library can extract models’ internal information and feature importance scores for popular decoder-only and encoder-decoder Transformers architectures. |
Is my Meeting Summary Good? Estimating Quality with a Multi-LLM Evaluator (2025.coling-industry)
Copied to clipboard
| Challenge: | Established metrics such as ROUGE and BERTScore have a relatively low correlation with human judgments and fail to capture nuanced errors. |
| Approach: | They propose a framework that uses a three-step assessment of individual error types, multi-agent discussion for decision refinement, and feedback-based self-training to refine error definition understanding and alignment with human judgment. |
| Outcome: | The proposed framework achieves high correlation with human judgment and a consistent rating and adaptability to custom error guidelines. |
Building Adaptive Acceptability Classifiers for Neural NLG (2021.emnlp-main)
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
| 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. |
BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla (2023.findings-eacl)
Copied to clipboard
| Challenge: | 'BanglaNLG' is a comprehensive benchmark for evaluating natural language generation models in Bangla, a widely spoken yet low-resource language. |
| Approach: | They propose to aggregate six conditional text generation tasks under the BanglaNLG benchmark and introduce a new dataset on dialogue generation in the process. |
| Outcome: | The proposed model outperforms several multilingual models by 9% absolute gain and 32% relative gain on all of these tasks. |
UniLG: A Unified Structure-aware Framework for Lyrics Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Existing works ignore musical attributes hidden behind lyrics and structure of lyrics . existing works ignore structure of generated lyrics and do not consider structure of songs . |
| Approach: | They propose a framework for conditional lyrics generation that considers structure and relationship between lyrics and music. |
| Outcome: | The proposed framework improves the structure modeling and unifies different conditions for different types of lyrics generation. |
Injecting Entity Types into Entity-Guided Text Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in deep generative modeling have led to significant advances in natural language generation (NLG). |
| Approach: | They propose to model the entity type carefully in the decoding phase to generate contextual words accurately. |
| Outcome: | The proposed model produces a target sequence based on a given list of entities. |
UCTG: A Unified Controllable Text Generation Framework for Query Auto-Completion (2025.coling-industry)
Copied to clipboard
| Challenge: | Existing approaches to control text generation (CTG) are essentially challenging to adapt to various control objectives and constraints, which results in mixed success. |
| Approach: | They propose a unified controllable text generation framework which integrates a control module, a prompt module, and a generation module. |
| Outcome: | The proposed framework significantly improves query accuracy and coherence in tasks with different objectives and constraints. |
Evaluating Morphological Compositional Generalization in Large Language Models (2025.naacl-long)
Copied to clipboard
Mete Ismayilzada, Defne Circi, Jonne Sälevä, Hale Sirin, Abdullatif Köksal, Bhuwan Dhingra, Antoine Bosselut, Duygu Ataman, Lonneke Van Der Plas
| Challenge: | Large language models (LLMs) have demonstrated significant progress in various natural language generation and understanding tasks. |
| Approach: | They define morphemes as compositional primitives and design a suite of generative and discriminative tasks to assess morphological productivity and systematicity. |
| Outcome: | The proposed models can identify individual morphological combinations better than chance, but their performance lacks systematicity, leading to significant accuracy gaps compared to humans. |
Compositional Zero-Shot Domain Transfer with Text-to-Text Models (2023.tacl-1)
Copied to clipboard
Fangyu Liu, Qianchu Liu, Shruthi Bannur, Fernando Pérez-García, Naoto Usuyama, Sheng Zhang, Tristan Naumann, Aditya Nori, Hoifung Poon, Javier Alvarez-Valle, Ozan Oktay, Stephanie L. Hyland
| Challenge: | Existing approaches to zero-shot domain transfer are limited by domain gap and lack of in-domain labels. |
| Approach: | They propose a compositional transfer learning framework (DoT51) that learns domain knowledge and task knowledge in a multi-task manner without access to in-domain labels. |
| Outcome: | The proposed framework outperforms the current state-of-the-art in zero-shot domain transfer by over 7 absolute points in accuracy on RadNLI. |
Towards Unsupervised Language Understanding and Generation by Joint Dual Learning (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work exploits dual property between understanding and generation to improve performance of modular dialogue systems. |
| Approach: | They propose a dual supervised learning framework that exploits the dual property between understanding and generation. |
| Outcome: | The proposed framework improves both NLU and NLG performance by incorporating supervised and unsupervised learning algorithms. |
ATGen: A Framework for Active Text Generation (2025.acl-demo)
Copied to clipboard
Akim Tsvigun, Daniil Vasilev, Ivan Tsvigun, Ivan Lysenko, Talgat Bektleuov, Aleksandr Medvedev, Uliana Vinogradova, Nikita Severin, Mikhail Mozikov, Andrey Savchenko, Ilya Makarov, Grigorev Rostislav, Ramil Kuleev, Fedor Zhdanov, Artem Shelmanov
| Challenge: | Despite the surging popularity of natural language generation tasks, the application of active learning (AL) to NLG has been limited. |
| Approach: | They propose a framework that bridges AL with text generation tasks and provides a unified platform for smooth implementation and benchmarking of novel AL strategies tailored to NLG tasks. |
| Outcome: | The proposed framework simplifies AL-empowered annotation in NLG tasks using both human annotators and automatic annotation agents based on large language models (LLMs). |
NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Parameter-efficient fine-tuning is essential for adapting large language models (LLMs). However, LoRA suffers from slow convergence and some recent LoRA variants, such as PiSSA, rely on Singular Value Decomposition (SVD) for initialization. |
| Approach: | They propose to introduce a small intermediate matrix between the low-rank matrices (A) and (B) and propose NyströmLoRA (NLoRA) which leverages Nyström-based initialization for SLoRA to improve its effectiveness and efficiency. |
| Outcome: | The proposed approach improves on 5 natural language generation tasks and 8 natural language understanding tasks with minimal parameter overhead. |
HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation (2022.acl-long)
Copied to clipboard
Zhoujun Cheng, Haoyu Dong, Zhiruo Wang, Ran Jia, Jiaqi Guo, Yan Gao, Shi Han, Jian-Guang Lou, Dongmei Zhang
| Challenge: | Existing studies on table reasoning focus on flat tables and hierarchical tables . a new dataset, HiTab, aims to examine numerical reasoning over hierarchic tables based on hierarchically structured tables - a strong challenge for existing baselines and a valuable benchmark for future research. |
| Approach: | They propose a hierarchical question answering and natural language generation dataset to study hierarchic tables. |
| Outcome: | The proposed model shows that it is effective in QA and natural language generation over hierarchical tables. |
Do GPTs Produce Less Literal Translations? (2023.acl-short)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are general-purpose language models capable of many natural language generation or understanding tasks. |
| Approach: | They investigate how LLMs differ qualitatively from standard Neural Machine Translation models by measuring literalness and monotonicity. |
| Outcome: | The proposed models achieve close to state-of-the-art translation performance under few-shot prompting . the results are backed up by human evaluations and a newer MT quality metrics . |
FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metrics for Automatic Text Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation metrics are not reliable, but require significant computational resources. |
| Approach: | They propose a method to learn a fixed, low cost version of any expensive NLG metric while retaining most of its original performance. |
| Outcome: | The proposed approach retains most of the original performance while running faster and faster. |
Dolphin: A Challenging and Diverse Benchmark for Arabic NLG (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing benchmarks for Arabic are limited, but they can be used to measure performance of different languages. |
| Approach: | They propose a benchmark for Arabic that addresses the need for a framework dedicated to Arabic languages and varieties. |
| Outcome: | The proposed benchmark covers 13 different tasks in Arabic and spans 50 test splits. |
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to fine-tune pre-trained language models are parameter efficient . fine- tuning the models requires multiple copies of the parameters, which is inefficient. |
| Approach: | They propose to use kernel-based adapters to tune only a few parameters while freezing the rest of the parameters. |
| Outcome: | The proposed methods achieve or improve strong performance over a diverse set of natural language generation and understanding tasks. |
Thesis Proposal: Intentional Inference for Insight Generation (2026.acl-srw)
Copied to clipboard
| Challenge: | Large language models excel at surface-level fluency but struggle with consistent logical inference beyond surface- level patterns. |
| Approach: | They propose to shift focus from surface-level generation to assumption-aware deeper inferences . authors argue that underspecification leads to unintentional assumptions . |
| Outcome: | The proposed model underspecification leads to unintentional assumptions, the authors argue . they also examine how to improve reasoning to enable deeper inferences, focusing on code generation and qualitative reasoning. |
Generating Counter Narratives against Online Hate Speech: Data and Strategies (2020.acl-main)
Copied to clipboard
| Challenge: | Hate Speech (HS) is a pervasive issue that spreads quickly and widely . research has focused on avoiding undesired effects that come with content moderation . |
| Approach: | They propose to use large scale unsupervised language models to generate responses to hate effectively using large scale models. |
| Outcome: | The proposed methods lack quality data and produce generic/repetitive responses. |
DEBATE: Devil’s Advocate-Based Assessment and Text Evaluation (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evaluating the quality of machine-generated texts have a relatively low correlation with human performance. |
| Approach: | They propose an NLG evaluation framework based on multi-agent scoring system augmented with a concept of Devil’s Advocate. |
| Outcome: | The proposed evaluation framework outperforms the previous state-of-the-art methods in two meta-evaluation benchmarks in NLG evaluation, SummEval and TopicalChat. |
Embedding and Gradient Say Wrong: A White-Box Method for Hallucination Detection (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for hallucination detection have attracted more attention from the community. |
| Approach: | They propose to model the distributional distance between the regular conditional output and the unconditional output, which is generated without a given input text. |
| Outcome: | The proposed model achieves state-of-the-art on the hallucination benchmarks HADES and other datasets. |
Multi-task Learning for Natural Language Generation in Task-Oriented Dialogue (D19-1)
Copied to clipboard
| Challenge: | Existing methods to generate natural language for task-oriented dialogues lack naturalness and variation in language. |
| Approach: | They propose a multi-task learning framework for natural language generation that explicitly targets for naturalness in generated responses via an unconditioned language model. |
| Outcome: | The proposed framework outperforms existing models across multiple datasets in the study of natural language generation. |
ThemePro: A Toolkit for the Analysis of Thematic Progression (2020.lrec-1)
Copied to clipboard
| Challenge: | Thematic progression is relevant to natural language processing applications dealing with discourse structure, argumentation structure, natural language generation, summarization and topic detection. |
| Approach: | They propose a toolkit for automatic analysis of thematic progression using a web interface. |
| Outcome: | ThemePro provides a visualization of the results including syntactic trees, hierarchical thematicity over propositions and thematic progression over whole texts. |
D.Va: Validate Your Demonstration First Before You Use It (2025.acl-long)
Copied to clipboard
| Challenge: | In-context learning (ICL) heavily relies on selecting effective demonstrations to achieve outputs that better align with the expected results. |
| Approach: | They propose a method which integrates a demonstration validation perspective into this field and integrates it into the learning paradigm. |
| Outcome: | The proposed method surpasses all retrieval-based in-context learning techniques across both natural language understanding (NLU) and natural language generation (NLG) tasks. |
Revisiting Generative Commonsense Reasoning: A Pre-Ordering Approach (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to generative commonsense reasoning hypothesize that pre-trained models lack sufficient parametric knowledge for this task. |
| Approach: | They propose to use order-agnostic input to elaborately manipulate the order of the given concepts before generation to evaluate their commonsense knowledge. |
| Outcome: | The proposed approach outperforms more sophisticated models with a lot of external data and resources in the task of generating a logical sentence from a set of concepts. |
Injecting knowledge into language generation: a case study in auto-charting after-visit care instructions from medical dialogue (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in language modeling have enabled applications across multiple domains such as education, jurisprudence, and healthcare. |
| Approach: | They propose a method to use knowledge to identify which rare words are important and uplift their conditional probability. |
| Outcome: | The proposed approach reduces the uncertainty of the model and improves factuality and coherence without negatively impacting fluency. |
Near-Negative Distinction: Giving a Second Life to Human Evaluation Datasets (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluating progress in natural language generation tasks are expensive, difficult to reproduce, and non-reusable. |
| Approach: | They propose a new automatic evaluation method for NLG called Near-Negative Distinction that repurposes prior human annotations into NND tests. |
| Outcome: | The proposed method achieves higher correlation with human judgments than standard NLG evaluation metrics. |
ICE-Score: Instructing Large Language Models to Evaluate Code (2024.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in the field of natural language generation have facilitated the use of large language models to assess the quality of generated text. |
| Approach: | They propose a new evaluation metric by instructing large language models for code assessments using a set of programming languages. |
| Outcome: | The proposed evaluation metric surpasses state-of-the-art metrics for code generation, delivering high levels of accuracy and consistency across programming languages and tasks. |
BMX: Boosting Natural Language Generation Metrics with Explainability (2024.findings-eacl)
Copied to clipboard
| Challenge: | Modern language model (LM) based natural language generation evaluation metrics achieve astonishing results in grading machine generated sentences like humans would. |
| Approach: | They use word-level explanations to convert a word- level score into a segment-level score and combine this segment- level with the original metric to obtain a better metric. |
| Outcome: | The proposed metrics improve across MT and summarization datasets while achieving small improvements on machine translation. |
Rethinking Task-Oriented Dialogue Systems: From Complex Modularity to Zero-Shot Autonomous Agent (2024.acl-long)
Copied to clipboard
| Challenge: | Task-oriented dialogue systems are designed to be composed of several functional modules, but lacks a general-purpose instruction-following language model. |
| Approach: | They propose a fully zero-shot autonomous TOD agent that leverages a general-purpose instruction-following language model to decide what to do at each dialogue turn. |
| Outcome: | The proposed agent can perform tasks in real-life scenarios with a general-purpose instruction-following language model. |
G-Eval: NLG Evaluation using Gpt-4 with Better Human Alignment (2023.emnlp-main)
Copied to clipboard
| Challenge: | Conventional reference-based metrics have low correlation with human judgments, especially for open-ended generation tasks. |
| Approach: | They propose to use large language models as reference-free NLG evaluators to assess the quality of NLG outputs. |
| Outcome: | The proposed framework outperforms all previous methods in two generation tasks, and has a Spearman correlation of 0.514 with human on summarization task, and a large variance in human judgments. |
Learning to Generate Move-by-Move Commentary for Chess Games from Large-Scale Social Forum Data (P18-1)
Copied to clipboard
| Challenge: | Using a large-scale chess commentary dataset, we generate a set of comments for individual moves in a game. |
| Approach: | They propose a large-scale chess commentary dataset and a method to generate commentary for individual moves in a chessian game. |
| Outcome: | The proposed method is rated similar to ground truth commentary texts in terms of correctness and fluency. |
A Generative Model for Joint Natural Language Understanding and Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Natural language understanding (NLU) and natural language generation (NLG) have opposite goals. |
| Approach: | They propose a generative model which couples NLU and NLG through a shared latent variable. |
| Outcome: | The proposed model achieves state-of-the-art performance on two dialogue datasets with flat and tree-structured formal representations. |
Personalized Multimodal Feedback Generation in Education (2020.coling-main)
Copied to clipboard
| Challenge: | In this paper, we propose a novel Personalized Multimodal Feedback Generation Network (PMFGN) that generates personalized feedback for teachers to evaluate assignments involving multimodal inputs. |
| Approach: | They propose a Personalized Multimodal Feedback Generation Network (PMFGN) that generates personalized feedback for teachers to evaluate assignments involving multimodal inputs such as images, audios, and texts. |
| Outcome: | The proposed model outperforms baseline models on real-world K-12 education data and detailed ablation experiments to deepen understanding of the proposed framework. |
An Empirical Study of Clinical Note Generation from Doctor-Patient Encounters (2023.eacl-main)
Copied to clipboard
| Challenge: | Medical doctors spend 52 to 102 minutes per day writing clinical notes from patient encounters. |
| Approach: | They propose to use a new dataset to generate automated and manual clinical notes from doctor-patient conversations in a clinical setting. |
| Outcome: | The proposed model could reduce the time spent writing clinical notes from doctor-patient conversations in a clinical setting. |
Unifying Human and Statistical Evaluation for Natural Language Generation (N19-1)
Copied to clipboard
| Challenge: | Human evaluation captures quality but fails to capture diversity . statistical evaluation fails to catch models that plagiarize from training set . |
| Approach: | They propose a framework which evaluates both diversity and quality based on the optimal error rate of predicting whether a sentence is human-generated. |
| Outcome: | The proposed framework evaluates diversity and quality on summarization and chit-chat dialogue. |
A Dog Is Passing Over The Jet? A Text-Generation Dataset for Korean Commonsense Reasoning and Evaluation (2022.findings-naacl)
Copied to clipboard
Jaehyung Seo, Seounghoon Lee, Chanjun Park, Yoonna Jang, Hyeonseok Moon, Sugyeong Eo, Seonmin Koo, Heuiseok Lim
| Challenge: | Korean pretrained language models struggle to generate short sentences with a given condition based on compositionality and commonsense reasoning. |
| Approach: | They propose a Korean text-generation dataset for Korean generative commonsense reasoning and language model evaluation using a semi-automatic dataset construction approach. |
| Outcome: | The proposed dataset is available at http://aihub.or.kr/opendata/korea-university. |
Language Generation via DAG Transduction (P18-1)
Copied to clipboard
| Challenge: | Existing formal frameworks for graph manipulation are underexploited. |
| Approach: | They propose a DAG transducer to perform graph-to-program transformation using a declarative programming language. |
| Outcome: | The proposed transducer achieves a BLEU-4 score of 68.07 for natural language generation from type-logical semantic graphs. |
The Case for a Single Model that can Both Generate Continuations and Fill-in-the-Blank (2022.findings-naacl)
Copied to clipboard
| Challenge: | a natural language generation system can be used to create text at the end of a passage . fill in the blank (FITB) is a task of inserting text into a specified position in a text . |
| Approach: | They evaluate the feasibility of using a single model to perform both tasks . they show that models pre-trained with a FitB-style objective are capable of both tasks. |
| Outcome: | The proposed model can perform both fill in the blank and continuation tasks. |
Reproducibility Issues for BERT-based Evaluation Metrics (2022.emnlp-main)
Copied to clipboard
| Challenge: | Reproducibility is of utmost concern in machine learning and natural language processing . lexical-overlap metrics are still the dominant metric in natural language generation . |
| Approach: | They ask whether results and claims from four recent BERT-based evaluation metrics can be reproduced. |
| Outcome: | The proposed metrics outperform the dominant metric, BLEU, and show that they can be reproduced. |
Contextualization of Morphological Inflection (N19-1)
Copied to clipboard
| Challenge: | In this paper, we isolate the task of predicting a fully inflected sentence from its partially lemmatized version. |
| Approach: | They propose a task that requires morphological features to be inferred from sentential context . they propose morphology-based models that explicitly reconstruct morphologic features before predicting inflected forms . |
| Outcome: | The proposed model is able to predict inflected sentences without relying on morphological annotations. |
RoViST: Learning Robust Metrics for Visual Storytelling (2022.findings-naacl)
Copied to clipboard
| Challenge: | Visual storytelling is the task of generating a story paragraph that describes a given image sequence. |
| Approach: | They propose 3 evaluation metrics sets that analyze which aspects we would look for in a good story . they compare their correlation with human judgement scores on a sample of machine stories . |
| Outcome: | The proposed evaluation metrics outperform other metrics on human correlation on a sample of machine stories from state-of-the-art models. |
Retrieval-Augmented Controllable Review Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing approaches to generate reviews using attribute identifiers are limited and dependent on how well they can capture vector representations of attributes. |
| Approach: | They propose to leverage attributes as inputs for review generation by using reference sets . they propose to use these references to enrich inductive biases of given attributes . |
| Outcome: | The proposed model improves over previous approaches on automatic and human evaluation metrics. |
Long-form evaluation of model editing (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing evaluations of model editing only use the ‘next few tokens’ completions after a prompt. |
| Approach: | They propose a new evaluation protocol that measures the efficacy and impact of model editing in long-form generative settings by using a machine-rated survey and a classifier which correlates well with human ratings. |
| Outcome: | The proposed evaluation protocol has little relationship with short-form metrics despite being designed to extend efficacy, generalization, locality, and portability into a long-form setting. |
How Does Knowledge Selection Help Retrieval Augmented Generation? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is a powerful method for enhancing natural language generation by integrating external knowledge into a model’s output. |
| Approach: | They empirically analyze how knowledge selection influences downstream generation performance in RAG systems by simulating different retrieval and selection conditions through a controlled mixture of gold and distractor knowledge. |
| Outcome: | The proposed model is based on a controlled mixture of gold and distractor knowledge and simulated with a gold and distractors. |
Multi-style Generative Reading Comprehension (P19-1)
Copied to clipboard
Kyosuke Nishida, Itsumi Saito, Kosuke Nishida, Kazutoshi Shinoda, Atsushi Otsuka, Hisako Asano, Junji Tomita
| Challenge: | Current studies on generative reading comprehension (RC) focus on extracting an answer span from textual evidence and natural language generation (NLG). |
| Approach: | They propose a multi-style abstractive summarization model for question answering called Masque. |
| Outcome: | The proposed model achieves state-of-the-art performance on the Q&A and Q& A + NLG tasks of MS MARCO and NarrativeQA. |
Pluralizing Nouns across Agglutinating Bantu Languages (C18-1)
Copied to clipboard
| Challenge: | Pluralization of nouns is a challenge for the Bantu language family . results show that the language's definition of noune classes is inadequate for computational purposes due to non-determinism in prefixes. |
| Approach: | They investigated the approach to pluralization in isiZulu and Runyankore for seven languages across three different Guthrie language zones. |
| Outcome: | The results show that the proposed pluralizers achieved over 93% accuracy and 94% accuracy on a random sample. |
Finetuning LLMs for Comparative Assessment Tasks (2025.coling-main)
Copied to clipboard
| Challenge: | Automated assessment in natural language generation is a challenging task. |
| Approach: | They propose a framework for fine-tuning LLMs for comparative assessment to align the model’s output with the target distribution of comparative probabilities. |
| Outcome: | The proposed framework improves state-of-the-art performance while maintaining high performance with an efficient subset of comparisons. |
INSET: Sentence Infilling with INter-SEntential Transformer (2020.acl-main)
Copied to clipboard
| Challenge: | Missing sentence generation fosters a wide range of applications in natural language generation . Developing models for sentence infilling can potentially facilitate many text generation applications . |
| Approach: | They propose a framework to decouple the problem from natural language processing . they propose generating missing sentences that can syntactically and semantically bridge context . |
| Outcome: | The proposed model learns a sentence representation and generates 'missing sentences' the proposed model can be used for document auto-completion and meeting note expansion . |
Controllable Natural Language Generation with Contrastive Prefixes (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing work on controllable natural language generation has focused on fine-tuning existing models or using attribute discriminators. |
| Approach: | They propose a lightweight framework for controllable GPT2 generation that utilizes attribute-specific vectors to steer natural language generation. |
| Outcome: | The proposed framework can guide generation towards desired attributes while keeping high linguistic quality. |
FIREBALL: A Dataset of Dungeons and Dragons Actual-Play with Structured Game State Information (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that large language models that have access to state information can generate higher quality game turns than LLMs that use dialog history alone. |
| Approach: | They present a dataset of game play sessions from real D&D gameplay on Discord with true game state info. |
| Outcome: | The proposed model can generate executable Avrae commands, especially after fine tuning. |
Enhancing Task-oriented Dialogue Systems with Generative Post-processing Networks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent work proposes a method to optimize pipelined dialogue systems by fine-tuning modules directly. |
| Approach: | They propose a new post-processing component for natural language generation (NLG) they use dialogue act contribution to evaluate contribution of GenPPN-generated utterances . |
| Outcome: | The proposed method improves the performance of task-oriented dialogue systems by modifying arbitrary modules including non-differentiable ones. |
Calibrating LLM-Based Evaluator (2024.lrec-main)
Copied to clipboard
Yuxuan Liu, Tianchi Yang, Shaohan Huang, Zihan Zhang, Haizhen Huang, Furu Wei, Weiwei Deng, Feng Sun, Qi Zhang
| Challenge: | Existing models for large language models lack the ability to calibrate their outputs towards human preference. |
| Approach: | They propose a multi-stage, gradient-free approach to calibrate an LLM-based evaluator toward human preference. |
| Outcome: | The proposed approach improves correlation with expert evaluation on multiple text quality evaluation datasets. |
Investigating the Representation of Backchannels and Fillers in Fine-tuned Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Backchannels and fillers are important linguistic expressions in dialogue, but often ignored in modern transformer-based language models. |
| Approach: | They use clustering analysis to learn backchannels and fillers in dialogues in English and Japanese and use natural language generation metrics to confirm this. |
| Outcome: | The proposed models can learn representations of backchannels and fillers using three fine-tuning strategies. |
Balancing the Effect of Training Dataset Distribution of Multiple Styles for Multi-Style Text Transfer (2023.findings-acl)
Copied to clipboard
| Challenge: | Text style transfer requires a high-quality paired dataset and quality training data. |
| Approach: | They propose to use a pseudo-parallel dataset to adjust the style distribution in training data to balance the style transfer model. |
| Outcome: | The proposed model produces more effective control effects over multiple styles than an imbalanced or skewed one. |
Learning to Plan and Realize Separately for Open-Ended Dialogue Systems (2020.findings-emnlp)
Copied to clipboard
Sashank Santhanam, Zhuo Cheng, Brodie Mather, Bonnie Dorr, Archna Bhatia, Bryanna Hebenstreit, Alan Zemel, Adam Dalton, Tomek Strzalkowski, Samira Shaikh
| Challenge: | Existing approaches to natural language generation are construed as end-to-end systems . however, some issues persist, such as coherence of output and repetition/hallucination of tokens . |
| Approach: | They propose to decouple natural language generation into two phases: planning and realization. |
| Outcome: | The proposed approach performs better than an end-to-end approach. |
ZmBART: An Unsupervised Cross-lingual Transfer Framework for Language Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in NLP focus on large annotated training data. |
| Approach: | They propose an unsupervised framework that does not use parallel or pseudo-parallel/back-translated data. |
| Outcome: | The proposed framework does not use parallel or pseudo-parallel/back-translated data. |
Modelling Context Emotions using Multi-task Learning for Emotion Controlled Dialog Generation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent research has tackled this task using neural generative methods by augmenting emotion classes with the input sequences. |
| Approach: | They propose to use a self-attention based encoder and a decoder with dot product attention mechanism to generate a viable response with a specified emotion. |
| Outcome: | The proposed model outperforms baselines on automatic evaluation measures such as F1 and BLEU scores, thus resulting in more fluent and adequate responses. |
AMR-TST: Abstract Meaning Representation-based Text Style Transfer (2023.findings-acl)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic representation that can enhance natural language generation (NLG) by providing a logical semantic input. |
| Approach: | They propose an AMR-based text style transfer technique that converts source text to an AML graph and generates transferred text based on the AMR graph modified by a TST policy named style rewriting. |
| Outcome: | The proposed method achieves state-of-the-art results compared with baseline models in automatic and human evaluations. |
Reward Gaming in Conditional Text Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work has used reward functions learned from human annotations to align conditional text generation models with desired behaviors. |
| Approach: | They propose to use reinforcement learning to train conditional text generation models with reward functions learned from human annotations to align outputs with desired behaviors. |
| Outcome: | The proposed framework improves the quality of generated summaries by using saliency and faithfulness metrics. |
Systematic Task Exploration with LLMs: A Study in Citation Text Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) provide unprecedented flexibility in defining and executing complex, creative natural language generation tasks. |
| Approach: | They propose a framework that consists of input manipulation, reference data, and output measurement to explore citation text generation. |
| Outcome: | The proposed framework explores citation text generation, a popular scholarly NLP task that lacks consensus on the task definition and evaluation metric and has not yet been tackled within the LLM paradigm. |
Multi-Style Transfer with Discriminative Feedback on Disjoint Corpus (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for style transfer require joint annotations across all stylistic dimensions, limiting their application to multiple styles. |
| Approach: | They initialize an encoder-decoder setup with transformer-based language model pre-trained on a generic corpus and enhance its re-writing capability to multiple target style dimensions by employing multiple style-aware language models as discriminators. |
| Outcome: | The proposed model can control styles across multiple style dimensions while preserving content of the input text. |
Beyond Words: Integrating Theory of Mind into Conversational Agents for Human-Like Belief, Desire, and Intention Alignment (2025.findings-acl)
Copied to clipboard
| Challenge: | Empirical evaluations of LLaMA-3 models demonstrate that ToM-informed alignment improves response quality, achieving win rates of 63% and 67%, respectively. |
| Approach: | They investigate whether open-source LLaMA models can represent and retain ToM-related constructs and whether they can be used to generate more aligned responses. |
| Outcome: | The proposed models can represent and retain ToM-related constructs and improve response quality. |
Towards Controllable Biases in Language Generation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | a new method to induce societal biases in natural language generation is being developed . a method to equalize the amount of biased text across demographics is effective . |
| Approach: | They propose a method to induce societal biases in natural language generation by using demographic inequalities. |
| Outcome: | The proposed method is effective at equalizing biases across demographics while generating less negatively biased text overall. |
A Sentiment-Controllable Topic-to-Essay Generator with Topic Knowledge Graph (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Topic-to-essay generation is a promising task for natural language generation. |
| Approach: | They propose a Sentiment Controllable topic-to- essay generator with a Topic Knowledge Graph enhanced decoder to generate essays with only several given topic words. |
| Outcome: | The proposed model outperforms the state-of-the-art model on automatic and human evaluation. |
NLG-Metricverse: An End-to-End Library for Evaluating Natural Language Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Natural language generation models are a key component of deep learning, says aaron eliott . he says it is crucial to develop and apply better metrics for NLG evaluation . |
| Approach: | a new open-source library for NLG evaluation is created to facilitate researchers to judge the effectiveness of their models. the framework provides a living collection of NLG metrics in a unified and easy-to-use environment. |
| Outcome: | a new open-source library for NLG evaluation aims to improve performance of models . the framework provides tools to apply, analyze, compare, and visualize the metrics . |
RSA-Control: A Pragmatics-Grounded Lightweight Controllable Text Generation Framework (2024.emnlp-main)
Copied to clipboard
| Challenge: | RSA-Control is a training-free controllable text generation framework . existing studies rely on fine-tuning pre-trained language models . external components could hurt coherence and accuracy of the model . |
| Approach: | They propose a training-free controllable text generation framework grounded in pragmatics that directs the generation process by recursively reasoning between imaginary speakers and listeners. |
| Outcome: | The proposed framework achieves strong attribute control while maintaining fluency and content consistency. |
Tiny Budgets, Big Gains: Parameter Placement Strategy in Parameter Super-Efficient Fine-Tuning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods such as LoRA and VeRA use memory-efficient methods to fine-tune large language models. |
| Approach: | They propose a method that uses only 1–5% of the standard LoRA parameters and achieves state-of-the-art performance across a wide range of tasks. |
| Outcome: | The proposed method achieves state-of-the-art performance across a wide range of tasks using only 1–5% of the standard LoRA parameters. |
On the Multilingual Capabilities of Very Large-Scale English Language Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Generative Pre-trained Transformers (GPTs) have been scaled to unprecedented sizes in the history of machine learning. |
| Approach: | They investigate the potential and limits of Generative Pre-trained Transformers in three tasks . they find it can be almost as useful for many languages as it is for English . |
| Outcome: | The proposed model can perform tasks in five different languages, and its potential is explored . it can learn from a few examples "via text interaction" and is scalable to many languages . |
Event Graph based Sentence Fusion (2021.emnlp-main)
Copied to clipboard
| Challenge: | Sentence fusion is a conditional generation task that merges related sentences into a coherent text. |
| Approach: | They propose to build an event graph from the input sentences to capture related events in a structured way and use the constructed event graph to guide sentence fusion. |
| Outcome: | The proposed method achieves state-of-the-art on two datasets . it is based on the input sentences and shows that it is effective . |
Learning to Judge: LLMs Designing and Applying Evaluation Rubrics (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models are increasingly used as evaluators for natural language generation . human rubrics are often static and misaligned with how models internally represent language quality. |
| Approach: | They propose to use large language models to generate interpretable and task-aware evaluation dimensions and apply them within models. |
| Outcome: | The proposed model improves the semantic coherence and scoring reliability of LLM-defined criteria and their alignment with human criteria. |
The Woman Worked as a Babysitter: On Biases in Language Generation (D19-1)
Copied to clipboard
| Challenge: | a systematic study of biases in natural language generation (NLG) is presented . a study of language models in NLG is conducted by examining language models. |
| Approach: | They propose a systematic study of biases in natural language generation by analyzing text generated from prompts that contain mentions of different demographic groups. |
| Outcome: | The proposed method reveals biases in natural language generation (NLG) by analyzing text generated from demographic prompts. |
Continuous Language Generative Flow (2021.acl-long)
Copied to clipboard
| 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. |
When to Trust LLMs: Aligning Confidence with Response Quality (2024.findings-acl)
Copied to clipboard
Shuchang Tao, Liuyi Yao, Hanxing Ding, Yuexiang Xie, Qi Cao, Fei Sun, Jinyang Gao, Huawei Shen, Bolin Ding
| Challenge: | Existing methods express reliability by confidence level, but lack objective guidance . Existing approaches express reliability but lack guidance on when to trust LLMs . |
| Approach: | They propose a reward-based approach to align confidence with quality to ensure reliability . they propose 'conqORD' to help model to verbalize greater confidence for higher quality responses . |
| Outcome: | Experiments show that CONQORD significantly improves confidence and response accuracy . the proposed approach can be used to determine reliability of large language models . |
Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References (2024.naacl-long)
Copied to clipboard
Tianyi Tang, Hongyuan Lu, Yuchen Jiang, Haoyang Huang, Dongdong Zhang, Xin Zhao, Tom Kocmi, Furu Wei
| Challenge: | Existing evaluation benchmarks with limited references may not accurately reflect the quality of the model’s hypotheses. |
| Approach: | They propose a method to enrich evaluation benchmarks by diversifying the expression of a single reference into multiple high-quality ones to cover the semantic space of the reference sentence as much as possible. |
| Outcome: | The proposed method can enhance evaluation benchmarks by diversifying the expression of reference into multiple high-quality ones to cover the semantic space of the reference sentence as much as possible. |
A Parallel WordNet for English, Swedish and Bulgarian (2020.lrec-1)
Copied to clipboard
| Challenge: | a new WordNet resource for Swedish and Bulgarian is created that is tightly aligned with the Princeton WordNet. |
| Approach: | They propose a WordNet resource for Swedish and Bulgarian that is tightly aligned with Princeton WordNet. |
| Outcome: | The proposed resource is tightly aligned with the Princeton WordNet for Swedish and Bulgarian . the new resource is open-source and in its development used only existing resources. |
kNN For Whisper And Its Effect On Bias And Speaker Adaptation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Speech recognition performance varies by language, domain, speaker characteristics such as accent . fine-tuning models on any of these categories may lead to catastrophic forgetting . |
| Approach: | They propose a nonparametric method that adapts to any category without training the model. |
| Outcome: | The proposed method improves the performance of a transformer end-to-end speech model on transcribed audio in over 680,000 hours of training data on a wide variety of languages. |
Generating Textual Explanations for Machine Learning Models Performance: A Table-to-Text Task (2022.lrec-1)
Copied to clipboard
| Challenge: | Numerical tables are widely used to communicate or report the classification performance of machine learning models with respect to a set of evaluation metrics. |
| Approach: | They propose a task where neural models are trained to generate textual explanations based on the metrics’ scores reported in numerical tables. |
| Outcome: | The proposed model outperforms existing methods and can be used to explain the performance of ML models. |
Perspective Taking through Generating Responses to Conflict Situations (2024.findings-acl)
Copied to clipboard
| Challenge: | Language models struggle to understand and explain the beliefs of others, despite improving performance on a wide variety of tasks. |
| Approach: | They propose to modify the social-chem-101 corpus to allow for perspective-taking, the process of conceptualizing the point of view of another person. |
| Outcome: | The proposed models outperform the recent models conditioned on self-disclosures with high similarity to the conflict situation. |
AdTEC: A Unified Benchmark for Evaluating Text Quality in Search Engine Advertising (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing pre-trained language models outperform them in certain domains, indicating that there is significant potential for further improvement in this area. |
| Approach: | They propose to use pre-trained language models to evaluate ad texts from multiple perspectives within real-world advertising operations to define five tasks and construct a Japanese dataset. |
| Outcome: | The proposed benchmark outperforms existing pre-trained language models in several tasks, but humans outperformed them in certain domains. |
Pay Attention when you Pay the Bills. A Multilingual Corpus with Dependency-based and Semantic Annotation of Collocations. (P19-1)
Copied to clipboard
| Challenge: | resulting corpus can be useful for different NLP tasks such as natural language understanding or natural language generation. |
| Approach: | They propose to annotate 155k tokens and 1,526 collocations in context in a multilingual corpus in English, Portuguese, and Spanish. |
| Outcome: | The new corpus can be used to evaluate different approaches for collocation identification, which can be useful for different NLP tasks such as natural language understanding or natural language generation. |
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs (2024.lrec-main)
Copied to clipboard
Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong
| Challenge: | Large language models have demonstrated exceptional capability in natural language understanding and generation, but their generation speed is limited by the inherently sequential nature of their decoding process. |
| Approach: | They propose a method that accelerates decoding process without sacrificing quality . they propose lexical unit decoding, which can be integrated with other methods . |
| Outcome: | The proposed method significantly reduces decoding time while maintaining quality while maintaining output quality. |
ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees (2024.findings-emnlp)
Copied to clipboard
Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Heng Tao Shen, Xiaofeng Zhu
| Challenge: | Uncertainty quantification (UQ) in natural language generation tasks remains an open challenge . however, black-box uncertainty measures require investigating with the proliferation of LLMs served via APIs. |
| Approach: | They propose a conformal uncertainty measure and a method to transform heuristic uncertainty notions into rigorous prediction sets. |
| Outcome: | Empirical results show that the proposed method outperforms state-of-the-art methods and can provide reliable guarantees for open-ended NLG tasks. |
Judge the Judges: A Large-Scale Evaluation Study of Neural Language Models for Online Review Generation (D19-1)
Copied to clipboard
| Challenge: | Existing evaluation methods for natural language generation are inadequate . distinguishing machine-generated text is challenging even for human evaluators . |
| Approach: | They compare human-based evaluators with automated evaluation procedures . they find human evaluers do not correlate well with discriminative evalators . |
| Outcome: | The proposed evaluation methods are compared with a dozen state-of-the-art generators for online product reviews. |
SEEval: Advancing LLM Text Evaluation Efficiency and Accuracy through Self-Explanation Prompting (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achieved remarkable success in various natural language generation tasks, but their performance in automatic text evaluation is not ready as human replacements. |
| Approach: | They propose a prompt-based text evaluator that incorporates self-explanation, a metacognitive strategy, to enhance automatic text evaluation. |
| Outcome: | The proposed method achieves competitive and often superior performance compared to the two state-of-the-art baselines – G-Eval and Analyze-Rate – and is 20 times more efficient in terms of run-time. |
Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing report generation systems suffer from incomplete and inconsistent generation, despite achieving high performance on natural language metrics such as CIDEr and BLEU. |
| Approach: | They propose two new rewards that encourage the generation of factually complete and consistent radiology reports by using an existing semantic equivalence metric. |
| Outcome: | The proposed system significantly improves the F1 score of a clinical information extraction performance on two open radiology report datasets. |
Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning (2021.emnlp-main)
Copied to clipboard
| Challenge: | a proposed model for question-answer pairs with self-contained, summary-centric questions and length-constrained, article-summarizing answers is based on suggested question generation in conversational news recommendation systems. |
| Approach: | They propose a model for generating question-answer pairs with self-contained, summary-centric questions and length-constrained, article-summarizing answers. |
| Outcome: | The proposed model captures the central gists of the articles and achieves high answer accuracy. |
Investigating Memorization of Conspiracy Theories in Text Generation (2021.findings-acl)
Copied to clipboard
| Challenge: | Existing studies examine conspiracy theories in social media, but they have not evaluated their presence in generative language models. |
| Approach: | They examine the ability of generative language models to generate conspiracy theory text . they highlight the difficulties of this task and discuss the drawbacks . |
| Outcome: | The proposed model can generate conspiracy theories without access to training data. |
Controllable Meaning Representation to Text Generation: Linearization and Data Augmentation Strategies (2020.emnlp-main)
Copied to clipboard
| Challenge: | Using task-oriented dialogue generation benchmarks, we compare the effect of four input linearization strategies on controllability and faithfulness. |
| Approach: | They compare the effect of four input linearization strategies on controllability and faithfulness . they also evaluate how a phrase-based data augmentation method can improve performance . |
| Outcome: | The proposed model can generate utterances whose phrases follow the order of the provided plan. |
A Human Evaluation of AMR-to-English Generation Systems (2020.coling-main)
Copied to clipboard
| Challenge: | a recent human evaluation of AMR generation systems is compared to automated metrics. |
| Approach: | They propose a human evaluation which collects fluency and adequacy scores and categorization of error types for AMR generation systems. |
| Outcome: | The results show that human evaluations are more nuanced than automated metrics. |
Multi-Loss Fusion: Angular and Contrastive Integration for Machine-Generated Text Detection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Modern natural language generation systems have led to the development of synthetic human-like open-ended texts, posing concerns as to who the original author of a text is. |
| Approach: | They propose a custom DeBERTa model with angular loss and contrastive loss functions for effective class separation in neural text classification tasks. |
| Outcome: | The proposed model improves on binary machine-generated text detection and multi-class neural authorship attribution tasks on a number of benchmark datasets. |
WaveDetect: Robust Framework for Machine-Generated Text Detection via Wavelet Transform (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting LLM-generated texts falter when faced with adversarial perturbations, cross-domain shifts, and the rapid temporal evolution of the foundation model. |
| Approach: | They propose a framework that reformulates text detection as a signal processing task within the time-frequency domain. |
| Outcome: | The proposed framework achieves superior accuracy and robustness against sophisticated attacks and generalization across out-of-distribution topics. |
COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generation (2025.acl-long)
Copied to clipboard
Raghvendra Kumar, Mohammed Salman S A, Aryan Sahu, Tridib Nandi, Pragathi Y P, Sriparna Saha, Jose G Moreno
| Challenge: | COSMMIC is a multimodal, multilingual dataset featuring nine major Indian languages. |
| Approach: | They propose a multimodal, multilingual multimodal multimodal dataset that integrates text, images and user feedback to enhance summarization. |
| Outcome: | The proposed dataset is based on 4,959 article-image pairs and 24,484 reader comments with ground-truth summaries available in all included languages. |
LOLA – An Open-Source Massively Multilingual Large Language Model (2025.coling-main)
Copied to clipboard
Nikit Srivastava, Denis Kuchelev, Tatiana Moteu Ngoli, Kshitij Shetty, Michael Roeder, Hamada Zahera, Diego Moussallem, Axel-Cyrille Ngonga Ngomo
| Challenge: | Using a sparse Mixture-of-Experts Transformer architecture, our model is highly efficient and efficient across languages. |
| Approach: | They propose a multilingual large language model trained on more than 160 languages using a sparse Mixture-of-Experts Transformer architecture. |
| Outcome: | The proposed model performs well on natural language generation and understanding tasks while avoiding the common pitfalls of multilinguality. |
On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation (2025.findings-naacl)
Copied to clipboard
| Challenge: | Hallucination is a popular topic in natural language generation (NLG). |
| Approach: | They propose to use large language models to evaluate faithfulness of guided NLGs by a rubric template and large language inference models to score the generation on quantifiable scales. |
| Outcome: | The proposed system can provide accurate judgement and explain whether a source and generation are factually consistent. |
CAMIEval: Enhancing NLG Evaluation through Multidimensional Comparative Instruction-Following Analysis (2025.naacl-long)
Copied to clipboard
| Challenge: | Evaluating the quality of texts generated by language models has always been a challenging task in natural language processing (NLP). |
| Approach: | They propose a multidimensional comparative evaluation method based on instruction-following that combines relevance, factuality, and adherence with a concrete Chain-of-Thoughts process to enhance the accuracy of evaluations. |
| Outcome: | The proposed method outperforms existing methods in correlation with human evaluations on two NLG evaluation benchmarks. |
Text Style Transfer with Contrastive Transfer Pattern Mining (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text style transfer only focus on the transformation between styles, yet they do not take into account that this transformation can be achieved via different hidden transfer patterns. |
| Approach: | They propose a novel approach which automatically mines hidden transfer patterns to improve TST . they use a clustering module to automatically discover hidden transfer pattern from the data . |
| Outcome: | The proposed method can be applied in a plug-and-play manner to enhance other methods to further improve their performance. |
Learning to Rank Visual Stories From Human Ranking Data (2022.acl-long)
Copied to clipboard
| Challenge: | Existing studies on visual storytelling (VIST) use automated evaluation metrics for text generation. |
| Approach: | They develop a Vrank metric that repurposes human evaluation results for automatic evaluation. |
| Outcome: | The proposed model is more accurate than existing metrics and is generalizable to textual stories. |
Universal Self-Adaptive Prompting (2023.emnlp-main)
Copied to clipboard
| Challenge: | a hallmark of modern large language models is their impressive general zero-shot and few-shot abilities . however, zero- shot performances are weaker due to the lack of guidance and the difficulty of applying existing automatic prompt design methods in general tasks. |
| Approach: | They propose an automatic prompt design approach specifically tailored for zero-shot learning that categorizes a possible NLP task into one of three possible task types and then uses a selector to select the most suitable queries and zero- shot model-generated responses as pseudo-demonstrations. |
| Outcome: | The proposed approach is able to generalize ICL to zero-shot learning tasks while also allowing for a more efficient and efficient prompt design. |
Diverse Keyphrase Generation with Neural Unlikelihood Training (2020.coling-main)
Copied to clipboard
| Challenge: | Recent advances in neural natural language generation have made possible remarkable progress on the task of keyphrase generation, however, the importance of diversity in keyphrases has been largely ignored. |
| Approach: | They propose to train a sequence-to-sequence keyphrase generation model from the perspective of diversity. |
| Outcome: | The proposed model achieves large diversity gains while maintaining competitive output quality. |
Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to pretrain language models are limited by one-size-fits-all vocabulary . embeddings of mismatch tokens can be efficiently initialized in downstream tasks . |
| Approach: | They propose to extend pretrain-finetune pipeline with an embedding transfer step . plug-and-play embeddable generator is introduced to generate any input token . |
| Outcome: | The proposed approach allows for more efficient and better performed NLG models. |
Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | In this paper, we analyze the problem of multi-reward reinforcement learning to optimize for multiple text qualities for natural language generation. |
| Approach: | They propose to use multi-reward reinforcement learning to optimize for multiple text qualities for natural language generation by using bandits. |
| Outcome: | The proposed techniques outperform existing naive and bandit baselines, showcasing their potential for enhancing language models. |
OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics (2021.acl-long)
Copied to clipboard
Jian Guan, Zhexin Zhang, Zhuoer Feng, Zitao Liu, Wenbiao Ding, Xiaoxi Mao, Changjie Fan, Minlie Huang
| Challenge: | Existing automatic metrics are observed to correlate poorly with human evaluation. |
| Approach: | They propose to use OpenMEVA to evaluate open-ended story generation metrics. |
| Outcome: | The proposed test suite assesses the capabilities of open-ended story generation metrics on annotated stories and auto-constructed test examples. |
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts (2021.acl-long)
Copied to clipboard
Alisa Liu, Maarten Sap, Ximing Lu, Swabha Swayamdipta, Chandra Bhagavatula, Noah A. Smith, Yejin Choi
| Challenge: | Decoding-time Experts is a decoding- time method for controlled text generation . it combines a pretrained language model with "expert" LMs and/or "anti-expert" experts . |
| Approach: | They propose a decoding-time method that combines a pretrained language model with "expert" LMs and/or "anti-expert" experts to generate controlled text. |
| Outcome: | The proposed method outperforms existing controllable generation methods on automatic and human evaluations. |
Enhancing Court View Generation with Knowledge Injection and Guidance (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods of natural language generation (NLG) rely on the extensive parameters of pretrained language models (PLMs) but their effectiveness may be compromised by insufficient domain-specific knowledge. |
| Approach: | They propose a knowledge-injected prompt encoder to incorporate domain knowledge during the training stage, thereby reducing computational overhead. |
| Outcome: | The proposed approach outperforms established baselines on real-world data in responsivity of claims and in the ability to transfer domain knowledge. |
Uncertainty Quantification of Large Language Models through Multiple Uncertainty Sources (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for uncertainty quantification fail to capture multifaceted nature of natural language generation. |
| Approach: | They propose a multi-resource Uncertainty Quantification framework that integrates heterogeneous uncertainty signals into a unified measure. |
| Outcome: | The proposed framework outperforms existing methods on CoQA, NQ_Open, and HotpotQA. |
Multi-Dimensional Evaluation of Text Summarization with In-Context Learning (2023.findings-acl)
Copied to clipboard
Sameer Jain, Vaishakh Keshava, Swarnashree Mysore Sathyendra, Patrick Fernandes, Pengfei Liu, Graham Neubig, Chunting Zhou
| Challenge: | In-context learning-based evaluators are competitive with learned evaluation frameworks for text summarization tasks. |
| Approach: | They propose to use large language models as multi-dimensional evaluators using in-context learning to evaluate text summarization tasks. |
| Outcome: | The proposed frameworks are competitive with existing frameworks on relevance and factual consistency, the authors show . |
DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering (2023.acl-long)
Copied to clipboard
| Challenge: | Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability. |
| Approach: | They propose a metric that evaluates natural language generation tasks as an instruction-style question answering task and utilizes instruction-tuned pre-trained language models without training on evaluation datasets. |
| Outcome: | The proposed metric achieves state-of-the-art performance in untrained metrics for evaluating text summarization and dialogue generation, which exhibits strong dimension-level / task-level generalization ability and interpretability. |
CoELM: Construction-Enhanced Language Modeling (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies show that integrating constructional information can improve the performance of pre-trained language models. |
| Approach: | They propose a construction-Enhanced language model that embeds constructional semantics into language models for natural language generation. |
| Outcome: | The proposed model outperforms existing models on various benchmarks. |
Dual Supervised Learning for Natural Language Understanding and Generation (P19-1)
Copied to clipboard
| Challenge: | Natural language understanding and natural language generation are important research topics in the NLP and dialogue fields. |
| Approach: | They propose a dual-supervised learning framework for natural language understanding and generation on top of dual supervised learning. |
| Outcome: | The proposed framework boosts the performance of both tasks simultaneously in the benchmark experiments. |
Context-Tuning: Learning Contextualized Prompts for Natural Language Generation (2022.coling-1)
Copied to clipboard
| 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. |
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization (2022.coling-1)
Copied to clipboard
| Challenge: | Experimental results show that our method outperforms full-model tuning in few-shot abstractive summarization tasks. |
| Approach: | They propose a soft prompts architecture with prompt pre-training and prompt fine-tuning paradigm to support few-shot abstractive summarization. |
| Outcome: | The proposed model outperforms Prompt Tuning and Profix-Tuning on CNN/DailyMail and XSum datasets and outperfies Profix Tuning by a large margin. |
NeuroAda: Activating Each Neuron’s Potential for Parameter-Efficient Fine-Tuning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for parameter-efficient fine-tuning are limited and require computational and memory resources. |
| Approach: | They propose a parameter-efficient fine-tuning method that enables fine-grained model finetunation while maintaining high memory efficiency. |
| Outcome: | The proposed method reduces CUDA memory usage by up to 60% while maintaining high performance. |
CoCGAN: Contrastive Learning for Adversarial Category Text Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Experimental results on synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generators. |
| Approach: | They propose to incorporate contrastive learning into adversarial category text generation by using a discriminator to optimize a contrastive learn objective to capture more flexible data-to-class relations and data- to-data relations among training samples. |
| Outcome: | The proposed model improves on synthetic and real category text generation datasets. |
MVP: Multi-task Supervised Pre-training for Natural Language Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have achieved remarkable success in natural language generation tasks. |
| Approach: | They propose to use a large-scale natural language generation corpus to pre-train a text generation model MVP in a supervised manner. |
| Outcome: | The proposed model outperforms BART and Flan-T5 on 13 out of 17 datasets and outperformed BART by 9.3% and FlaN-T5. |
Low-Resource Language Expansion and Translation Capacity Enhancement for LLM: A Study on the Uyghur (2025.coling-main)
Copied to clipboard
Kaiwen Lu, Yating Yang, Fengyi Yang, Rui Dong, Bo Ma, Aihetamujiang Aihemaiti, Abibilla Atawulla, Lei Wang, Xi Zhou
| Challenge: | Extensive experiments have shown that our strategy effectively expands the low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data. |
| Approach: | They propose a direct preference optimization based on translation self-evolution to expand low-resource languages into large language models by using Uyghur as an example. |
| Outcome: | The proposed strategy expands low-resource languages supported by large language models and significantly enhances the model’s translation ability in Uyghur with less parallel data. |
LaMDA: Large Model Fine-Tuning via Spectrally Decomposed Low-Dimensional Adaptation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Low-rank adaptation (LoRA) fine-tunes large language models due to its significant reduction in trainable parameters, but its backward updates require storing high-dimensional intermediate activations and optimizer states, requiring high peak GPU memory. |
| Approach: | They propose a low-dimensional adaptation approach to fine-tune large language models which freezes a first projection matrix while introducing a lower-dimensional trainable square matrix. |
| Outcome: | The proposed approach reduces trainable parameters and peak GPU memory footprint while preserving low-dimensional trainable square matrix. |
Natural Language Deduction with Incomplete Information (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing systems for reasoning given incomplete information are inadequate . current approaches to reasoning are based on latent reasoning by large language models . |
| Approach: | They propose a system that generates a natural language "proof" by abductively inferring a premise from another premise and a conclusion. |
| Outcome: | The proposed system can handle the underspecified setting where not all premises are stated at the outset; additional assumptions need to be materialized to prove a claim. |
All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text (2021.acl-long)
Copied to clipboard
| Challenge: | evaluators distinguish between human- and machine-authored text in three domains without training . evals' accuracy improved up to 55%, but it did not significantly improve across the three domain. |
| Approach: | They examine the role untrained human evaluations play in NLG evaluation and propose ways to improve their evaluations. |
| Outcome: | The evaluators distinguished between human- and machine-authored text at random chance level without training, but their accuracy did not improve across the three domains. |
DisGeM: Distractor Generation for Multiple Choice Questions with Span Masking (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Multiple-choice cloze tests are a prevalent form of assessment that evaluates students' comprehension and inference abilities. |
| Approach: | They propose a framework for distractor generation using readily available pre-trained language models . human evaluations confirm that their approach produces more effective distractors . |
| Outcome: | The proposed framework outperforms existing methods without training or fine-tuning human evaluations confirm it. |
Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Prediction (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are powerful automatic evaluators for natural language generation (NLG) tasks, but their uncertainty may limit their deployment in many applications. |
| Approach: | They propose a conformal prediction framework that provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average. |
| Outcome: | The proposed framework provides a prediction interval with coverage guarantees and a midpoint-based score as a low-bias alternative to raw model score and weighted average. |
Generating Sentences from Disentangled Syntactic and Semantic Spaces (P19-1)
Copied to clipboard
| 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. |
Learning to Control the Fine-grained Sentiment for Story Ending Generation (P19-1)
Copied to clipboard
| Challenge: | Existing studies focus on controlling the sentiment of story endings. |
| Approach: | They propose a generic and novel framework which controls fine-grained sentiment intensity for automatic story ending generation without manually annotating sentiment labels. |
| Outcome: | The proposed framework can generate story endings which meet the given sentiment intensity better. |
Large-Scale Transfer Learning for Natural Language Generation (P19-1)
Copied to clipboard
Sergey Golovanov, Rauf Kurbanov, Sergey Nikolenko, Kyryl Truskovskyi, Alexander Tselousov, Thomas Wolf
| Challenge: | Large-scale pretrained language models define state of the art in natural language processing, achieving outstanding performance on a variety of tasks. |
| Approach: | They propose to apply large-scale pretrained language models to natural language generation tasks by comparing architectural and training schemes. |
| Outcome: | The proposed architectures perform well on open-domain dialog as a typical high entropy generation task. |
PrExMe! Large Scale Prompt Exploration of Open Source LLMs for Machine Translation and Summarization Evaluation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) are useful for low-resource scenarios and time-restricted applications. |
| Approach: | They propose a large-scale evaluation tool for large language models that uses prompts . they evaluate 720 prompt templates for open-source LLM-based metrics on MT and summarization datasets a 6.6M evaluations. |
| Outcome: | The proposed model evaluates 720 prompt templates on machine translation and summarization datasets. |
Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation schemes focus on a teacher as a source of knowledge and a gauge to detect miscalibration of a student. |
| Approach: | They propose a method that uses a teacher model as a source of knowledge and a model as an error detector to detect miscalibration of a student. |
| Outcome: | The proposed scheme improves model generalization and significantly lowers calibration error. |
VisToT: Vision-Augmented Table-to-Text Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing models for data-to-text generation are wrongly generating estate in the output text. |
| Approach: | They propose a task that incorporates visual cues from tables and associated images to generate relevant text. |
| Outcome: | The proposed task incorporates visual cues from tables and associated images to generate relevant text. |
Zero-shot Faithfulness Evaluation for Text Summarization with Foundation Language Model (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing work evaluates faithfulness using models trained on related tasks or in-domain synthetic data. |
| Approach: | They propose to do zero-shot faithfulness evaluation with a foundation language model. |
| Outcome: | The proposed model outperforms ChatGPT on faithfulness and inconsistency detection with 24x fewer parameters and is competitive with existing models. |
Cheetah: Natural Language Generation for 517 African Languages (2024.acl-long)
Copied to clipboard
| Challenge: | Low-resource African languages pose unique challenges for natural language processing (NLG) We demonstrate the effectiveness of Cheetah through comprehensive evaluations across six generation downstream tasks. |
| Approach: | They develop a multilingual NLG language model for African languages called Cheetah . they demonstrate that Cheethah outperforms other models in six tasks . |
| Outcome: | The proposed model outperforms other models in five of six generation tasks. |
IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation (2021.emnlp-main)
Copied to clipboard
Samuel Cahyawijaya, Genta Indra Winata, Bryan Wilie, Karissa Vincentio, Xiaohong Li, Adhiguna Kuncoro, Sebastian Ruder, Zhi Yuan Lim, Syafri Bahar, Masayu Khodra, Ayu Purwarianti, Pascale Fung
| Challenge: | Lack of publicly available NLG benchmarks for low-resource languages poses a challenge . authors show that IndoBART and IndoGPT achieve competitive performance on all tasks . |
| Approach: | They propose a benchmark to measure natural language generation progress in three low-resource languages of Indonesia . they use a corpus of pretraining datasets to build their models . |
| Outcome: | The proposed benchmark measures progress in Indonesian, Javanese, and Sundanese . the results highlight the importance of pretraining on closely related, localized languages . |
Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated impressive performance across various tasks, but current training approaches combine cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance performance. |
| Approach: | They evaluate the use of established semantic segmentation loss functions in natural language generation to create a versatile, practical, and scalable solution for fine-tuning different architectures. |
| Outcome: | The proposed models improve on Math Word Problems and question answering tasks without additional data or human feedback. |
Quantifying Contamination in Evaluating Code Generation Capabilities of Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies have shown that large language models are contaminated with data from pretraining and finetuning tasks. |
| Approach: | They perform extensive analysis on the factors that affect model memorization and generalization, such as model size, problem difficulty, and question length. |
| Outcome: | The results show that models perform better on the subset of the benchmarks where similar solutions are seen during training. |
GS-Quant: Granular Semantic and Generative Structural Quantization for Knowledge Graph Completion (2026.acl-long)
Copied to clipboard
| Challenge: | Existing quantization-based approaches to knowledge Graph Completion (KGC) are incomplete. |
| Approach: | They propose a framework that generates semantically coherent discrete codes for KG entities . they introduce a Granular Semantic Enhancement module that injects hierarchical knowledge into the codebook . |
| Outcome: | The proposed framework outperforms existing text-based and embedding-based baselines in the KGC domain. |
Explanation Regeneration via Information Bottleneck (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work builds on prompt engineering to generate free-text explanations without specific training, but they lack sufficiency and conciseness due to the prompt complexity and hallucination issues. |
| Approach: | They propose to generate explanations via the information bottleneck theory by polishing the single-pass output of large pretrained language models but retaining the information that supports the contents being explained by balancing two information bottle neck objectives. |
| Outcome: | The proposed explanations are based on the information bottleneck theory . they are able to explain black-box predictions naturally and accurately . |
Selecting Better Samples from Pre-trained LLMs: A Case Study on Question Generation (2023.findings-acl)
Copied to clipboard
Xingdi Yuan, Tong Wang, Yen-Hsiang Wang, Emery Fine, Rania Abdelghani, Hélène Sauzéon, Pierre-Yves Oudeyer
| Challenge: | Large Language Models (LLMs) have demonstrated impressive prowess in natural language generation. |
| Approach: | They propose a method to select high-quality questions from LLM-generated candidates using round-trip and prompt-based scoring. |
| Outcome: | The proposed approach can select high-quality questions from a set of LLM-generated candidates without modification of the underlying model nor rely on human annotations. |
StoryTrans: Non-Parallel Story Author-Style Transfer with Discourse Representations and Content Enhancing (2023.acl-long)
Copied to clipboard
| 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. |
Finetuning Pretrained Transformers into RNNs (2021.emnlp-main)
Copied to clipboard
Jungo Kasai, Hao Peng, Yizhe Zhang, Dani Yogatama, Gabriel Ilharco, Nikolaos Pappas, Yi Mao, Weizhu Chen, Noah A. Smith
| Challenge: | Efficient transformers outperform recurrent neural networks in natural language generation, but this comes with significant computational cost and memory footprint during generation. |
| Approach: | They propose to convert a pretrained transformer into its efficient recurrent counterpart, improving efficiency while maintaining accuracy. |
| Outcome: | The proposed transformers outperform recurrent neural networks in natural language generation but come with significant computational and memory footprint during generation. |
Efficient Sparse Attention needs Adaptive Token Release (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks, however, their ‘large’ scale introduces significant computational and storage challenges, particularly in managing the key-value states of the transformer, which limits their wider applicability. |
| Approach: | They propose to release resources from caches and rebuild key-value states by a lightweight controller module to approximate an ideal top-K sparse attention. |
| Outcome: | The proposed method achieves a significant throughput improvement of 221.8% over full attention and a model with 7 billion tokens. |
A French Corpus for Semantic Similarity (2020.lrec-1)
Copied to clipboard
| Challenge: | Semantic textual similarity is a subtask of Natural Language Processing. |
| Approach: | They propose to use an annotation corpus for French to assess semantic similarity . they use an annotated corpus with 1,010 sentence pairs with five annotators . |
| Outcome: | The proposed corpus for French is the first that we know of. |
KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies indicate that language models generate non-factual information that is not supported by evidence with a high level of confidence. |
| Approach: | They propose a knowledge-constrained decoding method that guides a frozen LLM to generate text aligned with the reference knowledge at each decoding step. |
| Outcome: | The proposed method reduces the risk of misinformation generated by LLMs by reducing training costs and catastrophic forgetting for multi-tasking models. |
KELE: A Multi-Agent Framework for Structured Socratic Teaching with Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Socratic teaching places high demands on teachers’ expertise and real-time feedback capabilities, making it difficult to scale in large educational settings. |
| Approach: | They propose a multi-agent framework for structured Socratic teaching with LLMs that integrates a structured SocRule and a consultant-teacher collaborative teaching mechanism. |
| Outcome: | The proposed framework outperforms existing LLMs in natural language generation and dialogue comprehension in the classroom. |
Themis: A Reference-free NLG Evaluation Language Model with Flexibility and Interpretability (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for evaluation of natural language generation tasks lack reliable data. |
| Approach: | They propose to use annotations from human and GPT-4 to construct a corpus for NLG evaluation. |
| Outcome: | The proposed corpus can perform flexible and interpretable evaluations without references and surpasses existing models. |
Self-Ensemble of N-best Generation Hypotheses by Lexically Constrained Decoding (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have improved generation quality by explicitly reranking N-best candidates. |
| Approach: | They propose a method that ensembles N-best hypotheses to improve natural language generation by combining high-quality fragments of N- best hypothese . they use tokens that should or should not be present in the final output as lexical constraints to improve quality of generation. |
| Outcome: | Empirical results show that the proposed method outperforms strong N-best reranking methods on paraphrase generation, summarisation, and constrained text generation. |
Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization? (2024.emnlp-main)
Copied to clipboard
| Challenge: | Text summarization is a key natural language generation task, but the high cost of inaccurate summaries raises concerns about the reliability of uncertainty estimation on text summarisation (UE-TS) evaluation methods. |
| Approach: | They propose a UE-TS benchmark that evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets. |
| Outcome: | The proposed benchmark evaluates the uncertainty estimation capabilities of two large language models and one pre-trained language model on three datasets, with human-annotation analysis incorporated where applicable. |
Hallucination Detection for Generative Large Language Models by Bayesian Sequential Estimation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detecting hallucinations require large numbers of observations to be retrieved, increasing response times. |
| Approach: | They propose a framework that leverages Bayesian sequential analysis to optimize the trade-off between costs and benefits during the hallucination detection process. |
| Outcome: | The proposed framework surpasses existing methods in efficiency and precision of hallucination detection. |
MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection (2025.acl-long)
Copied to clipboard
| Challenge: | MaCP is a new adaptation method for large foundation models that requires minimal parameters and memory for fine-tuning. |
| Approach: | They propose a method that exploits the superior energy compaction and decorrelation properties of cosine projection to improve model efficiency and accuracy. |
| Outcome: | The proposed method improves model efficiency and accuracy across a wide range of single-modality tasks including natural language understanding, natural language generation, text summarization, and multi-modalities such as image classification and video understanding. |
Prompt-based Generation of Natural Language Explanations of Synthetic Lethality for Cancer Drug Discovery (2024.lrec-main)
Copied to clipboard
| Challenge: | Synthetic lethality (SL) is a genetic interaction where a single gene mutation allows cell survival, but simultaneous mutations in two genes lead to cell death. |
| Approach: | They propose a prompt-based pipeline for generating natural language explanations using a dataset derived from New Bing . |
| Outcome: | The proposed pipeline improves on existing biomedical language models in terms of text quality and explainability. |
Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in large language models have led to optimism that they can serve as reliable evaluators of natural language outputs. |
| Approach: | They propose to use factuality metrics to evaluate natural language outputs . they find they misestimate the factual accuracy of NLG systems . |
| Outcome: | The proposed metrics are inconsistent with each other and often misestimate the factual accuracy of NLG systems, causing biases against paraphrased outputs and outputs that draw upon faraway parts of the source documents. |
Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing decoding strategies for language models are based on heuristics and are difficult to improve. |
| Approach: | They propose a theory of decoding strategies for language models by expressing popular decoding algorithms as equilibrium states and stating objective functions they optimize. |
| Outcome: | The proposed method is based on ergodic theory and is difficult to improve . it shows that local normalization distortion is a fundamental defect of decoding strategies . |
Are LLMs Rational Investors? A Study on the Financial Bias in LLMs (2025.findings-acl)
Copied to clipboard
Yuhang Zhou, Yuchen Ni, Zhiheng Xi, Zhangyue Yin, Yu He, Gan Yunhui, Xiang Liu, Zhang Jian, Sen Liu, Xipeng Qiu, Yixin Cao, Guangnan Ye, Hongfeng Chai
| Challenge: | Existing studies on biases within specific domains, such as finance, remain limited. |
| Approach: | They propose a framework to detect, detect, analyze and mitigate financial biases in large language models. |
| Outcome: | The proposed framework reduces bias by 68% for the most biased model, according to key metrics. |
Step-by-Step: Controlling Arbitrary Style in Text with Large Language Models (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for autoregressive text generation have low controllability and accumulating errors. |
| Approach: | They propose a three-stage prompt-based approach to express autoregressive text in a specific region editing task using a word frequency-based strategy. |
| Outcome: | Experiments on publicly competitive datasets confirm that the proposed approach achieves state-of-the-art performance. |
Would You Like to Make a Donation? A Dialogue System to Persuade You to Donate (2024.lrec-main)
Copied to clipboard
| Challenge: | Persuasive automated dialogue systems are a popular way to influence people's behavior and decision making. |
| Approach: | They propose to use a context-aware persuasion strategy selection module to persult users . they also propose a persuasiveness prediction model to automatically evaluate the persuasiveness of generated text. |
| Outcome: | The proposed system can achieve better performance on several automated evaluation metrics than baseline models. |
PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claims (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing natural language generation (NLG) metrics fail to capture domain-specific nuances . patent claims require precise assessment of structural elements such as antecedent consistency and claim dependency. |
| Approach: | They propose a multi-dimensional evaluation framework specifically designed for patent claims . PatentScore integrates hierarchical decomposition of claim elements, validation patterns and scoring across structural, semantic, and legal dimensions. |
| Outcome: | The proposed evaluation framework outperforms existing evaluation frameworks on patent claims . patentScore achieved highest correlation with expert annotations on 400 patent claims dataset . |
Astra: Activation-Space Tail-Eigenvector Low-Rank Adaptation of Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained models are limited due to suboptimal activation subspaces. |
| Approach: | They propose a method that leverages tail eigenvectors of model output activations to construct low-rank adapters. |
| Outcome: | The proposed method outperforms existing methods across 16 benchmarks and surpasses full fine-tuning in certain scenarios. |
SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models can generate highquality, human-like content, but they also pose risks such as infringement of proprietary interests, misuse of outputs, and spread harmful misinformation. |
| Approach: | They propose a method that partitions the vocabulary into two logit-balanced subsets and lifts the lower bound of watermark strength for each token prediction. |
| Outcome: | The proposed method lifts the lower bound of watermark strength for each token prediction, thereby improving watermark detectability. |
HypoEval: Hypothesis-Guided Evaluation for Natural Language Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing frameworks for LLM-as-a-judge use zero-shot setting without consulting any human input, which leads to low alignment, or fine-tune LLMs on labeled data, which requires a non-trivial number of samples. |
| Approach: | They propose a hypothesis-guided evaluation framework that uses a small corpus of human evaluations to generate more detailed rubrics for human judgments and incorporates a checklist-like approach to combine LLM’s assigned scores on each decomposed dimension to acquire overall scores. |
| Outcome: | The proposed framework outperforms existing frameworks in both human rankings and human scores with 30 human evaluations and fine-tunes LLMs on labeled data with 3 times more human evaluation by 11.95%. |