Papers with generation process
Exploring Controllable Text Generation Techniques (2020.coling-main)
Copied to clipboard
| Challenge: | Neural controllable text generation has a plethora of applications but there is no unifying theme. |
| Approach: | They propose a new schema for the control of attributes in the generation process by classifying it into five modules and providing an analysis on the advantages and disadvantages of these techniques. |
| Outcome: | The proposed frameworks can be used to control the attributes of natural sentences and to modulate the formality and politeness of emails. |
Text Diffusion Model with Encoder-Decoder Transformers for Sequence-to-Sequence Generation (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing diffusion models are applied to continuous feature space while texts are sequences of discrete categorical tokens. |
| Approach: | They propose to use an encoder-decoder Transformer architecture to approach sequence-to-sequence text generation. |
| Outcome: | The proposed model improves on five sequence-to-sequence generation tasks compared to other diffusion-based models regarding text quality and inference time. |
Towards Generation and Recognition of Humorous Texts in Portuguese (2023.eacl-srw)
Copied to clipboard
| Challenge: | This PhD thesis focuses on the automatic generation and recognition of verbal punning humor in Portuguese. |
| Approach: | They propose to combine natural language generation and cognitive processing to generate and recognize verbal humor in Portuguese. |
| Outcome: | The proposed methods aim to generate and recognize humor in Portuguese, an underdeveloped language compared to English. |
Non-Autoregressive Sequence Generation (2022.acl-tutorials)
Copied to clipboard
| Challenge: | Non-autoregressive sequence generation (NAR) models generate output sequences in parallel to speed up generation process. |
| Approach: | This tutorial provides a thorough introduction and review of non-autoregressive sequence generation . it aims to generate the entire or partial output sequences in parallel to speed up the generation process . |
| Outcome: | This tutorial provides a thorough introduction and review of non-autoregressive sequence generation . it aims to reduce the performance gap between state-of-the-art models due to lack of modeling power . |
DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation (2021.naacl-demos)
Copied to clipboard
| Challenge: | Recent advances in transformer-based language models and their applications to dialogue systems have succeeded to generate fluent and human-like responses. |
| Approach: | They propose to leverage conversational lines as controllable and informative content-planning elements to guide the generation model produce engaging and informative responses. |
| Outcome: | The proposed system generates engaging and informative responses using convlines as controllable and informative content-planning elements. |
Jiuge: A Human-Machine Collaborative Chinese Classical Poetry Generation System (P19-3)
Copied to clipboard
Guo Zhipeng, Xiaoyuan Yi, Maosong Sun, Wenhao Li, Cheng Yang, Jiannan Liang, Huimin Chen, Yuhui Zhang, Ruoyu Li
| Challenge: | Existing systems for automatic poetry generation are model-oriented, resulting in poor user participation. |
| Approach: | They propose a human-machine collaborative Chinese classical poetry generation system called Jiuge . Jiuge allows users to revise unsatisfied parts of a generated poem draft repeatedly . |
| Outcome: | The proposed system allows users to revise unsatisfied parts of a generated poem draft repeatedly. |
Youling: an AI-assisted Lyrics Creation System (2020.emnlp-demos)
Copied to clipboard
Rongsheng Zhang, Xiaoxi Mao, Le Li, Lin Jiang, Lin Chen, Zhiwei Hu, Yadong Xi, Changjie Fan, Minlie Huang
| Challenge: | Recent studies have focused on a single pass of lyrics generation with little human intervention. |
| Approach: | They propose an AI-assisted lyrics creation system that supports one pass full-text generation and interactive generation modes. |
| Outcome: | The proposed system supports full-text generation and interactive generation modes . it also provides a revision module which enables users to revise undesired lyrics repeatedly. |
CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity (2024.findings-emnlp)
Copied to clipboard
| Challenge: | State-of-the-art QA systems employ Large Language Models (LLMs) however, these models tend to hallucinate information in their responses. |
| Approach: | They propose an attribution-oriented Chain-of-Thought reasoning method to enhance attributions. |
| Outcome: | The proposed method outperforms existing models on context enhanced question-answering datasets and shows that it can be used to improve accuracy. |
Text-Blueprint: An Interactive Platform for Plan-based Conditional Generation (2023.eacl-demo)
Copied to clipboard
Fantine Huot, Joshua Maynez, Shashi Narayan, Reinald Kim Amplayo, Kuzman Ganchev, Annie Priyadarshini Louis, Anders Sandholm, Dipanjan Das, Mirella Lapata
| Challenge: | Recent work shows that conditional generation models can be useful to control the text generation process, leading to irrelevant, repetitive, and hallucinated content. |
| Approach: | They propose a web browser-based demonstration for query-focused summarization that uses a sequence of question-answer pairs as a blueprint plan for guiding text generation. |
| Outcome: | The proposed model can be used to generate query-focused summarization text using question-answer pairs as a blueprint plan. |
Plan-then-Seam: Towards Efficient Table-to-Text Generation (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent work explicitly decomposes the generation process into content planning and surface generation stages, employing two autoregressive networks for them respectively. |
| Approach: | They propose a non-parallelelizable table-to-text model that produces outputs in parallel with one network. |
| Outcome: | The proposed model achieves 3.0 5.6 times speedup for inference time, reducing 50% parameters, while maintaining as least comparable performance against strong two-stage table-to-text competitors. |
Enhancing Hallucination Detection via Future Context (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are widely used to generate plausible text on online platforms, without revealing the generation process. |
| Approach: | They propose a framework for detection of hallucinations in black-box generators by analyzing future contexts. |
| Outcome: | The proposed framework improves on existing methods and demonstrates that it is feasible to integrate it with other models. |
Chandler: An Explainable Sarcastic Response Generator (2021.emnlp-demo)
Copied to clipboard
| Challenge: | sarcasm generators assume intended meaning is opposite of literal meaning . sarcastically generated responses are more specific and coherent to input . |
| Approach: | They propose a system that generates sarcastic responses to a given utterance . they ground their generation process on a formal theory that unambiguously differentiates . |
| Outcome: | The proposed system generates sarcastic responses to a given utterance. |
Task-driven Layerwise Additive Activation Intervention (2025.naacl-short)
Copied to clipboard
| Challenge: | Existing approaches to task adaptation rely heavily on heuristic rules or prompt inputs. |
| Approach: | They propose a layer-wise additive activation intervention framework that steers the LMs’ generation process by identifying and manipulating the activations. |
| Outcome: | The proposed framework improves the accuracy of pretrained LMs and competing baselines on various datasets, demonstrating improvements in the accuracy and sample efficiency of the proposed framework. |
Rethinking Repetition Problems of LLMs in Code Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Recent studies have focused on content repetition, but structural repetition is a more prevalent problem in code generation. |
| Approach: | They propose a decoding approach that eliminates repetition problems in code generation by identifying grammar rules and strategically decaying the likelihood of critical tokens that contribute to repetitions. |
| Outcome: | The proposed approach outperforms baselines and humanEval benchmarks on CodeRepetEval dataset and MBPP benchmarks, effectively reducing repetitions and enhancing the quality of generated code. |
SpeechWeave: Diverse Multilingual Synthetic Text & Audio Data Generation Pipeline for Training Text to Speech Models (2025.acl-industry)
Copied to clipboard
| Challenge: | Text-to-Speech (TTS) training requires extensive and diverse text and speech data. |
| Approach: | They propose a synthetic speech data generation pipeline that generates multilingual, domain-specific datasets for TTS training. |
| Outcome: | The proposed pipeline generates data that is 10–48% more diverse than baseline across various linguistic and phonetic metrics, along with speaker-standardized speech audio while generating approximately 97% correctly normalized text. |
Neural data-to-text generation: A comparison between pipeline and end-to-end architectures (D19-1)
Copied to clipboard
| Challenge: | Traditionally, data-to-text applications have been designed using a modular pipeline architecture, in which the non-linguistic input data is converted into natural language through several intermediate transformations. |
| Approach: | They propose to use Gated-Recurrent Units and Transformer to implement neural pipelines for data-to-text generation. |
| Outcome: | The proposed models generalize better to unseen inputs and have better performance than the existing pipeline architectures. |
Cue Me In: Content-Inducing Approaches to Interactive Story Generation (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for automatic story generation focus on one-shot generation, but we focus on interactive story generation. |
| Approach: | They propose two ways to incorporate user-provided cue phrases into automatic story generation. |
| Outcome: | The proposed approach produces more topically coherent and personalized stories than baseline methods. |
De-Bias for Generative Extraction in Unified NER Task (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for Named entity recognition (NER) are not consistent with the task, which makes the model vulnerable to incorrect biases. |
| Approach: | They propose to use generative model to recognize entities from sentences . they analyze incorrect biases in the generation process from a causal perspective . |
| Outcome: | The proposed method improves the performance of the generative NER model in various datasets. |
Guided Knowledge Generation with Language Models for Commonsense Reasoning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved notable success in commonsense reasoning tasks, benefiting from extensive world knowledge acquired through extensive pretraining. |
| Approach: | They propose a method to generate knowledge explanations and to automatically assign labels based on the probability of correct answers. |
| Outcome: | The proposed method outperforms baselines on four widely-used commonsense reasoning benchmarks and shows that it can generate high quality knowledge leading to correct answers. |
Controllable Text Generation with Residual Memory Transformer (2024.findings-acl)
Copied to clipboard
| Challenge: | Large-scale Causal Language Models (CLMs) have been successful in text generation, but there is still a challenge to control the generation process. |
| Approach: | They propose a non-intrusive, lightweight control plugin to control the generation process of a CLM at arbitrary time steps. |
| Outcome: | The proposed plugin can handle any type of control conditions and cooperate with the base CLM through a residual learning paradigm. |
WaterBench: Towards Holistic Evaluation of Watermarks for Large Language Models (2024.acl-long)
Copied to clipboard
| Challenge: | Recent studies have developed watermarking algorithms which restrict the generation process to leave an invisible trace for watermark detection. |
| Approach: | They propose a benchmarking procedure that compares different methods to ensure consistent watermarking strength and jointly evaluates their generation and detection performance. |
| Outcome: | The proposed benchmark compares 4 open-source watermarks on 2 LLMs under 2 watermarking strengths and observes the common struggles for current methods on maintaining the generation quality. |
Syntax-Aware Retrieval Augmented Code Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Neural code generation models with token-level retrieval capabilities are often noisy and time-consuming. |
| Approach: | They propose a token-level retrieval augmented code generation method that leverages syntax constraints for the retrieval of datastores. |
| Outcome: | The proposed method reduces the impact of retrieve noise on code generation on two datasets. |
Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation (2021.acl-long)
Copied to clipboard
| Challenge: | Neural Machine Translation models are influenced by two types of context, source and target, but none explicitly evaluates relative contribution to generation decision. |
| Approach: | They propose to adopt a variant of Layerwise Relevance Propagation which evaluates relative contributions to the generation decision by a proportion of token influence. |
| Outcome: | The proposed model can evaluate the relative contribution of source and target to the generation decision by using a variant of Layerwise Relevance Propagation (LRP) |
Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Domain experts in engineering, healthcare, and education follow strict standards for producing quality content. |
| Approach: | They propose a retrieval-style in-context learning-based framework to guide large language models to align with expert-defined standards. |
| Outcome: | The proposed framework shows that models can gain 45% to 100% increase in precise accuracy across open and commercial LLMs evaluated. |
Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation (P18-1)
Copied to clipboard
| Challenge: | Existing encoder-decoder dialog models cannot output interpretable actions as in traditional systems. |
| Approach: | They propose an unsupervised discrete sentence representation learning method that integrates with existing encoder-decoder dialog models for interpretable response generation. |
| Outcome: | The proposed model can be integrated with existing encoder-decoder dialog models and discover interpretable semantics via either auto encoding or context predicting. |
A Semantically Consistent and Syntactically Variational Encoder-Decoder Framework for Paraphrase Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Paraphrase generation is a longstanding problem in natural language processing (NLP) Neural network-based methods have shown great progress on paraphrase generation. |
| Approach: | They propose a framework that integrates variational inference on a target-related latent variable to introduce the diversity. |
| Outcome: | The proposed framework outperforms baseline models on the metrics based on n-gram matching and semantic similarity, and it can generate multiple different paraphrases by assembling different syntactic variables. |
Generating Radiology Reports via Memory-driven Transformer (2020.emnlp-main)
Copied to clipboard
| Challenge: | Medical imaging reports are time-consuming and can be error-prone for inexperienced radiologists. |
| Approach: | They propose to generate radiology reports with memory-driven Transformer using relational memory and memory-based conditional layer normalization. |
| Outcome: | The proposed method outperforms existing models on IU X-Ray and MIMIC-CXR . it generates long reports with medical terms and meaningful image-text attention mappings . |
DYLE: Dynamic Latent Extraction for Abstractive Long-Input Summarization (2022.acl-long)
Copied to clipboard
Ziming Mao, Chen Henry Wu, Ansong Ni, Yusen Zhang, Rui Zhang, Tao Yu, Budhaditya Deb, Chenguang Zhu, Ahmed Awadallah, Dragomir Radev
| Challenge: | Existing models struggle with summarizing long text due to high memory complexity of the full self-attention. |
| Approach: | They propose a dynamic latent extraction approach for abstractive long-input summarization that treats extracted text snippets as latent variables and allows dynamic attention weights during decoding. |
| Outcome: | The proposed method outperforms existing methods on GovReport, QMSum, and arXiv while yielding strong results on arX. |
RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have focused on producing concise observations while neglecting the precise attributes that determine the severity of diseases. |
| Approach: | They propose a model that generates precise radiology reports via dynamic disease progression reasoning by combining historical and spatiotemporal information. |
| Outcome: | Experiments on two publicly available datasets show the proposed model can generate precise and accurate radiology reports with dynamic disease progression reasoning. |
Causal Intervention for Abstractive Related Work Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models ignore the inherent causality during related work generation, leading to spurious correlations which downgrade the models’ generation quality and generalizability. |
| Approach: | They propose a Causal Intervention Module for Related Work Generation (CaM) that captures causal relationships in related work generation and implements causal interventions to mitigate the negative impact of spurious correlations. |
| Outcome: | The proposed framework improves the quality and coherence of generated related work by capturing causalities in the generation process. |
Episodic Memory Retrieval from LLMs: A Neuromorphic Mechanism to Generate Commonsense Counterfactuals for Relation Extraction (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have achieved satisfactory performance in counterfactual generation, however, there are misalignments between LLMs and humans which hinder LLM from handling complex tasks like relation extraction. |
| Approach: | They propose to mimic the episodic memory retrieval mechanism of human hippocampus to align LLMs’ generation process with that of humans. |
| Outcome: | The proposed framework improves over existing methods in terms of quality of counterfactuals. |
EdiT5: Semi-Autoregressive Text Editing with T5 Warm-Start (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Pre-trained seq2seq models have established strong baselines for text-to-text transduction tasks. |
| Approach: | They propose a semi-autoregressive text-editing approach that combines the strengths of non-auto-regressively text- editing and autoregressive decoding. |
| Outcome: | The proposed model is faster at inference times than conventional models while being capable of modeling flexible input-output transformations. |
Control Image Captioning Spatially and Temporally (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods to generate image captions with user intention are still under exploration. |
| Approach: | They propose a model that connects Contrastive constraints and Attention Guidance in a loop manner and engages explicit spatial and temporal constraints to the generating process. |
| Outcome: | The proposed model improves performance on a trace-controlled image captioning task. |
A Hierarchical Latent Structure for Variational Conversation Modeling (N18-1)
Copied to clipboard
| Challenge: | Variational autoencoders suffer from the notorious degeneration problem, according to a new study . utterance drop regularization is an important feature of the hierarchical RNNs . |
| Approach: | They propose a variational hierarchical conversation RNN framework that exploits latent variables and an utterance drop regularization to exploit latent variable. |
| Outcome: | The proposed model outperforms state-of-the-art models on Cornell Movie Dialog and Ubuntu Dialog Corpus. |
Can Synthetic Text Help Clinical Named Entity Recognition? A Study of Electronic Health Records in French (2023.eacl-main)
Copied to clipboard
| Challenge: | In sensitive domains, the sharing of corpora is restricted due to confidentiality, copyrights or trade secrets. |
| Approach: | They use auto-regressive neural models to generate a clinical case corpus annotated with clinical entities and evaluate it for a named entity recognition task. |
| Outcome: | The proposed model can produce clinical case corpus annotated with clinical entities while maintaining confidentiality. |
Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches fail to generalize well to concepts that are not observed during training. |
| Approach: | They propose a framework that revolves around probing several similar image caption training instances and performing analogical reasoning over relevant entities in retrieved prototypes. |
| Outcome: | The proposed framework improves on the widely used image captioning benchmarks and on composition-related evaluation metrics. |
LatticeGen: Hiding Generated Text in a Lattice for Privacy-Aware Large Language Model Generation on Cloud (2024.findings-naacl)
Copied to clipboard
Mengke Zhang, Tianxing He, Tianle Wang, Lu Mi, Niloofar Mireshghallah, Binyi Chen, Hao Wang, Yulia Tsvetkov
| Challenge: | Currently, the server controls the generated text, but users can't keep it private . prompted generation is a common interaction paradigm for large language models on cloud . |
| Approach: | They propose a protocol where the server handles most of the computation while the client controls the sampling operation. |
| Outcome: | The proposed protocol protects both prompt and generation under strong attacks. |
Bringing Real-World Relations into Video Generation with Graph-Structured Knowledge (2026.acl-long)
Copied to clipboard
| Challenge: | Existing text-to-video models struggle to accurately simulate real-world physics and dynamic entity interactions. |
| Approach: | They propose a framework that integrates graph-structured temporal knowledge into video latent diffusion models to enhance compositional generation and interaction fidelity. |
| Outcome: | The proposed framework enhances compositional generation and interaction fidelity by integrating graph-structured temporal knowledge into video latent diffusion models. |
Modeling Complex Event Scenarios via Simple Entity-focused Questions (2023.eacl-main)
Copied to clipboard
| Challenge: | Event schemas describe a sequence of events in a particular context, but they are difficult to model with standard event language models. |
| Approach: | They propose a question-guided generation framework that generates events as answers to questions about participants. |
| Outcome: | The proposed framework provides better coverage of participants, diverse events within a domain, comparable perplexities for modeling event sequences, and more effective control for interactive schema generation. |
Attribute First, then Generate: Locally-attributable Grounded Text Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Recent efforts to address hallucinations in Large Language Models have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections. |
| Approach: | They propose a locally-attributable text generation approach prioritizing concise attributions by identifying relevant source segments and conditioning the generation process on them. |
| Outcome: | The proposed method yields more concise citations than baselines and significantly reduces time required for fact verification by human assessors. |
FACT: Examining the Effectiveness of Iterative Context Rewriting for Multi-fact Retrieval (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, but struggle with tasks requiring simultaneous retrieval of multiple facts. |
| Approach: | They propose a method that refines context through successive rounds of rewriting to address this problem by finding all Crucial Texts (FACT) |
| Outcome: | The proposed method improves multi-fact retrieval performance across tasks, though improvements are less notable in general-purpose QA scenarios. |
Disco-RAG: Discourse-Aware Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
Dongqi Liu, Hang Ding, Qiming Feng, Xurong Xie, Zhucun Xue, Chengjie Wang, Jian Li, Jiangning Zhang, Yabiao Wang
| Challenge: | Existing RAG strategies treat retrieved passages in a flat and unstructured way, which prevents the model from capturing structural cues and constrains its ability to synthesize knowledge from dispersed evidence across documents. |
| Approach: | They propose a framework that explicitly injects discourse signals into the generation process. |
| Outcome: | Experiments on question answering and long-document summarization benchmarks show the efficacy of the proposed framework. |
Retrieving Examples from Memory for Retrieval Augmented Neural Machine Translation: A Systematic Comparison (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing approaches to extract examples from memory are limited, but the upstream retrieval step is still unexplored. |
| Approach: | They propose to use a standard autoregressive model, edit-based model and a large language model with in-context learning to investigate the effect of retrieval methods on translation scores. |
| Outcome: | The proposed architectures improve translation scores and increase diversity of examples. |
A Semi-Supervised Stable Variational Network for Promoting Replier-Consistency in Dialogue Generation (D19-1)
Copied to clipboard
| Challenge: | Existing methods favor uninformative and non replier-specific responses due to lack of relevant information guidance. |
| Approach: | They propose to use a semi-supervised variable network to generate replier-specific responses . they use vMF as latent space to obtain stable KL performance . |
| Outcome: | The proposed model outperforms baseline models on two large conversation datasets and generates diverse and replier-specific responses. |
Dynamic Topic Tracker for KB-to-Text Generation (2020.coling-main)
Copied to clipboard
| Challenge: | Existing KB-to-text generation models suffer from an off-topic problem . existing models generate unrelated clauses regardless of input data . |
| Approach: | They propose a dynamic topic tracker that learns a global hidden representation for topics and recognizes the corresponding topic during each generation step. |
| Outcome: | The proposed model improves the performance of sentence generation and mitigates off-topic problem. |
SKIntern: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have high computational costs and privacy concerns due to their high computational expenses and data privacy. |
| Approach: | They propose a method that empowers SLMs to internalize symbolic knowledge and few-shot examples gradually through a progressive fine-tuning process. |
| Outcome: | The proposed approach outperforms state-of-the-art baselines by over 5% while reducing inference costs by up to 4 across a wide range of SLMs in both in-domain (ID) and out-of domain (OOD) tasks. |
Factorising AMR generation through syntax (N19-1)
Copied to clipboard
| Challenge: | Abstract Meaning Representation (AMR) is a semantic annotation framework which abstracts away from the surface form of text to capture the core 'who did what to whom' structure. |
| Approach: | They propose to decompose the generation process into two steps: first generate a syntactic structure, and then generate the surface form. |
| Outcome: | The proposed approach generates meaning-preserving syntactic paraphrases of the same graph, as judged by humans. |
MEGATRON-CNTRL: Controllable Story Generation with External Knowledge Using Large-Scale Language Models (2020.emnlp-main)
Copied to clipboard
Peng Xu, Mostofa Patwary, Mohammad Shoeybi, Raul Puri, Pascale Fung, Anima Anandkumar, Bryan Catanzaro
| Challenge: | Existing pre-trained large language models have shown unparalleled generative capabilities, but they are not controllable. |
| Approach: | They propose a framework that uses large-scale language models and adds control to text generation by incorporating an external knowledge base. |
| Outcome: | The proposed model generates more fluent, consistent, and coherent stories with less repetition and higher diversity compared to previous work on the ROC story dataset. |
Think Beyond Words: Exploring Context-Relevant Visual Commonsense for Diverse Dialogue Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to generate intelligent open-domain dialogue agents only consider auxiliary commonsense stored in pure text, ignoring grounding information from the external visual world. |
| Approach: | They propose a VIsual Commonsense enhanced dialogue generaTOR that exploits auxiliary commonsense from images related to context to generate coherent and informative responses. |
| Outcome: | The proposed method outperforms the latest competitive methods in terms of coherence and diversity on two public datasets. |
Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation (N19-1)
Copied to clipboard
| Challenge: | Modern neural generation systems conflate these two steps into a single end-to-end differentiable system. |
| Approach: | They propose to split the generation process into a symbolic text-planning stage that is faithful to the input, followed by a neural generation stage that focuses only on realization. |
| Outcome: | The proposed method improves reliability and adequacy while maintaining fluent output. |
Evaluating Rewards for Question Generation Models (N19-1)
Copied to clipboard
| Challenge: | Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. |
| Approach: | They propose to use a Seq2Seq architecture to train models to generate one-step-ahead predictions, but at test time, the model is asked to generate a whole sequence, causing errors to propagate through the generation process. |
| Outcome: | The proposed model is trained to generate a plausible question, conditioned on an input document and answer span within that document. |
Enhancing Contextual Understanding in Large Language Models through Contrastive Decoding (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models lack contextual knowledge, resulting in text with factual inconsistencies or contextually unfaithful content. |
| Approach: | They propose a method that integrates contrastive decoding with adversarial irrelevant passages as negative samples to enhance robust context grounding during generation. |
| Outcome: | The proposed method improves context grounding during generation without training. |
Solving Math Word Problems via Cooperative Reasoning induced Language Models (2023.acl-long)
Copied to clipboard
Xinyu Zhu, Junjie Wang, Lin Zhang, Yuxiang Zhang, Yongfeng Huang, Ruyi Gan, Jiaxing Zhang, Yujiu Yang
| Challenge: | Large-scale pre-trained language models (PLMs) can be used to solve math word problems, but they lack fast adaptivity as humans. |
| Approach: | They propose a cooperative reasoning-induced PLM for solving the math word problem . they use system 1 as the generator and system 2 as the verifier to generate reasoning paths . |
| Outcome: | The proposed model improves on several mathematical reasoning datasets and achieves 9.6% improvement over baselines. |
Personalized Large Language Model Assistant with Evolving Conditional Memory (2025.coling-main)
Copied to clipboard
| Challenge: | With the rapid development of large language models, personalized large language model assistants like ChatGPT are limited in personalized services. |
| Approach: | They propose a plug-and-play framework that could facilitate personalized large language model assistants with evolving conditional memory. |
| Outcome: | The proposed framework can preserve the knowledge and experience from the history dialogue with the user, which can be applied to future tailored responses that better align with the users' preferences. |
Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026.findings-acl)
Copied to clipboard
| Challenge: | 3D Vision-Language Models (VLMs) are critical cognitive backbone for spatial intelligence, but their reliance on autoregressive decoding introduces a fundamental vulnerability regarding inference efficiency. |
| Approach: | They propose a framework that triggers computational and economic exhaustion in 3D-VLMs by injecting imperceptible noise that forces the model into a state of pathological verbosity. |
| Outcome: | The proposed framework amplifies output length and energy consumption by up to 6.45, demonstrating a potent capability to drain system resources. |
RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Large language models struggle to evaluate the correctness of non-parametric knowledge when it differs from internal memorization, leading to knowledge conflicts during response generation. |
| Approach: | They propose a lightweight alignment method to leverage multi-source knowledge based on retrieval relevance. |
| Outcome: | Experiments on four datasets show that the proposed method outperforms RAG by 4-10% in accuracy without any extra component. |
LLM Knows Body Language, Too: Translating Speech Voices into Human Gestures (2024.acl-long)
Copied to clipboard
| Challenge: | despite advances in the generation of realistic human gestures, the process often includes unintended, meaningless, or non-realistic gestures. |
| Approach: | They propose a framework that leverages large language models to generate human gestures . the primary stage employs a transformer-based auto-encoder network to encode human gesture into discrete symbols . |
| Outcome: | The proposed framework has demonstrated state-of-the-art performance on public TED and TED-Expressive datasets. |
LearnDA: Learnable Knowledge-Guided Data Augmentation for Event Causality Identification (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) rely on annotated training data. |
| Approach: | They propose a method to augment training data for event causality identification by iteratively generating new examples and classifying event causalities in a dual learning framework. |
| Outcome: | The proposed method outperforms existing methods on EventStoryLine and Causal-TimeBank. |
Chunk-based Nearest Neighbor Machine Translation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Semi-parametric models augment generation with retrieval, but require expensive retrieval operation for every generated token. |
| Approach: | They propose a semi-parametric model which augments generation with retrieval by retrieving tokens from a datastore. |
| Outcome: | The proposed model can retrieve chunks of tokens from the datastore, instead of a single token, with a low decoding speed. |
CA-GAR: Context-Aware Alignment of LLM Generation for Document Retrieval (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent techniques such as Generation-Augmented Retrieval (GAR) and Generative Document Retrieleval (GDR) leverage LLMs to enhance retrieval performance but face key challenges: GAR’s generated content may not always align with the target document corpus, while GDR limits the generative capacity of LLM. |
| Approach: | They propose a Context-Aware Generation-Augmented Retrieval approach which integrates corpus information into their generation process. |
| Outcome: | Experimental results show that CA-GAR outperforms existing methods on seven tasks and four non-English languages. |
Enconter: Entity Constrained Progressive Sequence Generation via Insertion-based Transformer (2021.eacl-main)
Copied to clipboard
| Challenge: | Autoregressive language models do not perform well under hard lexical constraints as they lack fine control of content generation process. |
| Approach: | They propose a new insertion transformer that considers hard lexical constraints and imposes rules over objects in the generated text. |
| Outcome: | The proposed model outperforms baseline models in several performance metrics rendering it more suitable in practical applications. |
Think Hard Only When Needed: A Hybrid Best-of-N and Beam Search for Efficient Test-Time Compute (2026.findings-eacl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit remarkable reasoning and planning capabilities, yet their substantial inference-time cost significantly impedes deployment in resourceconstrained applications. |
| Approach: | They propose a hybrid inference pipeline that combines beam search and Best-of-N . THROW generates shorter initial trajectories and evaluates them using PRMs . |
| Outcome: | THROW achieves 1.54 and 14.38 latency speedups and 35.7% and 80.4% token reductions on average compared to Best-of-N and beam search . |
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. |
Empathetic Dialogue Generation via Sensitive Emotion Recognition and Sensible Knowledge Selection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Empathy is a key trait of everyday human conversations. |
| Approach: | They propose a serial encoding and Emotion-Knowledge interaction method for empathetic dialogue generation which is more sensitive to emotion dynamics in conversations. |
| Outcome: | The proposed method outperforms baseline evaluations on the utterance-level annotated EMPATHETICDIALOGUES. |
Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse tasks, but their deployment in high-stake domains requires consistent and coherent behavior across multiple rounds of user interaction. |
| Approach: | They propose a framework for evaluating and improving LLM response consistency, and introduce a benchmark dataset to evaluate LLM consistency. |
| Outcome: | The proposed framework improves response stability without sacrificing accuracy, and offers a practical path toward more dependable behavior in critical, real-world deployments. |
DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer (2021.emnlp-main)
Copied to clipboard
| Challenge: | Generating long passages that maintain long-range coherence is a long-standing problem in natural language generation (NLG). |
| Approach: | They propose a discourse-aware discrete variational Transformer that learns a latent variable sequence that summarizes the global structure of the text and then applies it to guide the generation process at each decoding step. |
| Outcome: | The proposed model can generate long texts with better long-range coherence by learning a latent variable sequence with each latent code. |
LET: Leveraging Error Type Information for Grammatical Error Correction (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for grammatical error correction (GEC) are mainly divided into detection-based and end-to-end generative models. |
| Approach: | They propose an end-to-end framework which Leverages Error Type (LET) information in the generation process to introduce more convincing error type information. |
| Outcome: | The proposed framework outperforms existing methods on various datasets by a clear margin. |
Prompt-Based Editing for Text Style Transfer (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Text style transfer is a type of textual prompt that generates style-transferred texts word by word . early prediction errors may affect future word predictions. |
| Approach: | They propose a prompt-based editing approach to text style transfer using a pretrained language model. |
| Outcome: | The proposed approach outperforms existing systems with 20 times more parameters on three style-transfer benchmark datasets. |
Bridging the Gap between Different Vocabularies for LLM Ensemble (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing methods to combine large language models with complete outputs have limited effectiveness . lexical gaps between different LLMs hinder dynamic correction and enhancement . |
| Approach: | They propose a method to ensemble large language models via Vocabulary Alignment (EVA) they learn mappings between vocabularies of different LLMs with overlapping tokens . |
| Outcome: | The proposed method bridges the lexical gap among various LLMs, enabling meticulous ensemble at each generation step. |
Self-Reinforcing Controllable Synthesis of Rare Relational Data via Bayesian Calibration (2026.findings-acl)
Copied to clipboard
Chongsheng Zhang, Hao Wang, Zelong Yu, Esteban Garces Arias, Julian Rodemann, Zhanshuo Zhang, Qilong Li, Gaojuan Fan, Krikamol Muandet, Christian Heumann
| Challenge: | Existing approaches to synthesis of relational/structured tabular data lack effective feedback mechanism to optimize quality of generated data. |
| Approach: | They propose a relational data generator with dynamic guidance framework that uses chain-of-thought steps to generate tabular data for enhancing downstream imbalanced classification performance. |
| Outcome: | The proposed framework outperforms existing approaches in both data fidelity and downstream imbalanced classification performance on real and synthetic datasets. |
End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems (2020.emnlp-main)
Copied to clipboard
Siamak Shakeri, Cicero Nogueira dos Santos, Henghui Zhu, Patrick Ng, Feng Nan, Zhiguo Wang, Ramesh Nallapati, Bing Xiang
| Challenge: | Existing approaches for synthetic QA data generation have limited or no success in improving the downstream Reading Comprehension task. |
| Approach: | They propose an end-to-end approach for synthetic QA data generation using a transformer-based encoder-decoder network that is trained end- to-end to generate both answers and questions. |
| Outcome: | The proposed model outperforms current state-of-the-art methods in the domain adaptation of QA models. |
ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods to generate radiology reports only rely on high-level plans, but they lack important information. |
| Approach: | They propose an Observation-guided radiology Report Generation framework which generates free-text descriptions for a set of radiographs. |
| Outcome: | The proposed framework outperforms state-of-the-art methods regarding text quality and clinical efficacy. |
Identifying Human Strategies for Generating Word-Level Adversarial Examples (2022.findings-emnlp)
Copied to clipboard
| Challenge: | a recent study shows that word-level adversarial examples are more natural and grammatical correct than automated attacks. |
| Approach: | They analyze how humans generate word-level adversarial examples against fine-tuned Transformer models that preserve naturalness and grammatical correctness. |
| Outcome: | The authors show that humans generate adversarial examples much more effortlessly than automated attacks. |
From Confidence to Collapse in LLM Factual Robustness (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation methods focus on performance-based metrics, often investigating from the perspective of prompt perturbations, which captures only the externally triggered side of knowledge robustness. |
| Approach: | They propose a method to measure factual robustness from the perspective of the generation process by analyzing token distribution entropy and temperature scaling sensitivity. |
| Outcome: | The proposed method measures factual robustness from the perspective of the generation process and entropy and temperature scaling sensitivity. |
Self-Reflective Generation at Test Time (2026.acl-long)
Copied to clipboard
| Challenge: | Existing self-reflection mechanisms are reactive and inefficient for large language models . a fundamental tension persists between the ability to execute complex multi-step reasoning and the ability of the model to generate coherent traces. |
| Approach: | They propose a test-time framework that reflects before generating at uncertain points . SRGen utilizes dynamic entropy thresholding to identify high-uncertainty tokens . |
| Outcome: | The proposed framework can significantly strengthen large language models' reasoning process. |
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) when retrieved contexts are noisy, incomplete, or heterogeneous, a single generation process often struggles to reconcile evidence effectively. |
| Approach: | They propose a multi-agent synthesis approach to retrieval-augmented generation that structures evidence processing into multiple role-specialized agents. |
| Outcome: | Experiments on four benchmarks show that MASS-RAG consistently improves performance over strong RAG baselines. |
Question Generation and Answering for exploring Digital Humanities collections (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent advances in representation learning of text have achieved impressive results on benchmark Natural Language Understanding (NLU) tasks. |
| Approach: | They propose a question answering paradigm that uses a BART Transformer based generative model to generate question data. |
| Outcome: | The proposed approach is validated on a new corpus of digitized archive collections of a French Social Science journal. |
Composing Ci with Reinforced Non-autoregressive Text Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to compose Ci are limited in handling the constraints of tune patterns . authors propose a non-autoregressive approach to generate Ci using a synchronous process . |
| Approach: | They propose to compose Ci using a non-autoregressive approach that takes into account rigid formats . they propose to apply reinforcement learning to the generation process with rigid constraints . |
| Outcome: | The proposed method outperforms baselines and previous studies on a Ci dataset . it allows the model to perform synchronous generation while maintaining the format and content requirement. |
Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for automated feature generation rely on predefined operator libraries and do not incorporate feature semantics, limiting their ability to produce high-quality features. |
| Approach: | They propose a Memory-Augmented LLM-based Multi-Agent System (MALMAS) that decomposes the generation process into agents with distinct responsibilities. |
| Outcome: | The proposed method extracts informative features from raw tabular data without manual intervention and is crucial for accurate, generalizable machine learning. |
Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies on dense video captioning and video story generation have made some progress, but in practical applications, we typically require synchronized narrations for ongoing visual scenes. |
| Approach: | They propose a task of Synchronized Video Storytelling to generate synchronized narrations for videos using a benchmark dataset with rich annotations. |
| Outcome: | The proposed framework can generate narrations with the guidance of the generated or predefined storyline and human evaluations validate the effectiveness. |
Fine-Grained Image-Text Alignment in Medical Imaging Enables Explainable Cyclic Image-Report Generation (2024.acl-long)
Copied to clipboard
| Challenge: | Fine-grained vision-language models (VLMs) have been widely used for inter-modality local alignment between fixed patches and textual words, but they provide incomplete representations of lesions. |
| Approach: | They propose an Adaptive patch-word Matching model to correlate chest X-ray (CXR) image regions with words in medical reports and apply it to CXR-report generation to provide explicit explanations. |
| Outcome: | The proposed model correlates chest X-ray image regions with words in medical reports and provides explanations for the generation process. |
Metaphor Generation with Conceptual Mappings (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models for metaphor generation lack conceptualization of meaning of the metaphors . recent neural models have led to advances in many areas of natural language generation . |
| Approach: | They propose to encode conceptual mappings between cognitive domains to generate metaphoric expressions by embedding verbs into a literal expression and deriving source/target pairs to train a controlled seq-to-seq generation model. |
| Outcome: | The proposed method outperforms existing models in automatic and human evaluations for basic metaphoricity and conceptual metaphor presence. |
A Generative Adaptive Replay Continual Learning Model for Temporal Knowledge Graph Reasoning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing Continual Learning (CL)-based Temporal Knowledge Graph Reasoning methods are incomplete and reorganize historical facts without preserving historical knowledge. |
| Approach: | They propose a method which generates and adaptively replays historical entity distributions from the whole historical context. |
| Outcome: | The proposed method outperforms baselines in reasoning and mitigating forgetting. |
Neural Response Generation with Meta-words (P19-1)
Copied to clipboard
| Challenge: | Experimental results show that meta-words can be used to generate open domain dialogues . human-machine conversation is a fundamental problem in NLP . |
| Approach: | They propose a goal-tracking memory network that formalizes meta-word expression as a target in response generation and manages the generation process with a state memory panel and a controller. |
| Outcome: | The proposed model outperforms state-of-the-art generation models in response relevance, response diversity, and accuracy. |
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. |
EvoNarrator: Modeling Scientific Evolution for Feasible Hypothesis Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Scientific discovery evolution does not occur ex nihilo but is characterized by structural deepening and reconfiguration of existing functionalities. |
| Approach: | They propose a framework for hypothesis generation based on evolutionary narratives . they extract structured P-M-L-F quadruples from citation networks and introduce a mechanism to assess their semantic compatibility. |
| Outcome: | The proposed framework reduces logical disconnects by evaluating its semantic compatibility. |
Improving Factuality with Explicit Working Memory (2025.acl-long)
Copied to clipboard
Mingda Chen, Yang Li, Karthik Padthe, Rulin Shao, Alicia Yi Sun, Luke Zettlemoyer, Gargi Ghosh, Wen-tau Yih
| Challenge: | Large language models can generate factually inaccurate content, a problem known as hallucination. |
| Approach: | They propose an approach that integrates a working memory that receives feedback from external resources. |
| Outcome: | The proposed method outperforms baselines on four fact-seeking datasets and increases the factuality metric by 2 to 6 points absolute. |
Bridging External and Parametric Knowledge: Mitigating Hallucination of LLMs with Shared-Private Semantic Synergy in Dual-Stream Knowledge (2025.emnlp-main)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) aims to mitigate the hallucination of Large Language Models (LLMs) however, external knowledge may contain noise and conflict with parametric knowledge of LLMs, leading to degraded performance. |
| Approach: | They propose a Dual-Stream Knowledge-Augmented Framework for Shared-Private Semantic Synergy that refines the traditional self-attention into a mixed-attention that distinguishes shared and private semantics for a controlled knowledge integration. |
| Outcome: | Extensive experiments show that the proposed framework achieves a superior performance over baselines. |
Hit the Sweet Spot! Span-Level Ensemble for Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | a recent study focused on sample-level and token-level ensembles, which hinder dynamic correction and enhancement of outputs during the generation process. |
| Approach: | They propose a span-level ensemble method that balances real-time adjustments and accurate ensemble decisions. |
| Outcome: | The proposed method improves performance across language generation tasks significantly. |
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Traditional methods address leaks only after content is generated, which can lead to the exposure of sensitive information. |
| Approach: | They propose a proactive approach: examining LLMs’ internal states before text generation to detect potential leaks. |
| Outcome: | The proposed framework ensures adherence to copyright and licensing requirements while enhancing data privacy and ethical standards. |
LEMMA: Learning from Errors for MatheMatical Advancement in LLMs (2025.findings-acl)
Copied to clipboard
Zhuoshi Pan, Yu Li, Honglin Lin, Qizhi Pei, Zinan Tang, Wei Wu, Chenlin Ming, H. Vicky Zhao, Conghui He, Lijun Wu
| Challenge: | Existing approaches focus on improving the quality of correct training data, neglecting the value contained in error data, thereby hindering the model’s reflective ability. |
| Approach: | They propose to improve LLM's reasoning ability by learning from error data and a grounded mistake augmentation method to collect representative errors. |
| Outcome: | The proposed model achieves significant performance improvements over other strong models with less than 90k data. |
A Synthetic Data Generation Framework for Grounded Dialogues (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to train grounded dialogues require large amounts of data. |
| Approach: | They propose a synthetic data generation framework for grounded dialogues that takes knowledge data and heuristics to determine a dialogue flow and incrementally turn it into a dialog. |
| Outcome: | The proposed framework significantly boosts model performance in training data and low-resource scenarios. |
Text Detoxification using Large Pre-trained Neural Models (2021.emnlp-main)
Copied to clipboard
David Dale, Anton Voronov, Daryna Dementieva, Varvara Logacheva, Olga Kozlova, Nikita Semenov, Alexander Panchenko
| Challenge: | Existing studies on text detoxification cast this task as style transfer . text detox requires better preservation of the original meaning, authors argue . |
| Approach: | They propose two unsupervised methods for eliminating toxicity in text . they use a paraphraser guided by style-trained language models to keep the text content . |
| Outcome: | The proposed methods yield new SOTA results. |
DPWriter: Reinforcement Learning with Diverse Planning Branching for Creative Writing (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for enhancing large language models (LLMs) lack explicit mechanisms for guiding diverse exploration and instead prioritize efficiency and performance over diversity. |
| Approach: | They propose a reinforcement learning-based framework that decomposes the generation process into explicitly planned intermediate steps and introduces divergence at the planning phase based on diversity variation. |
| Outcome: | The proposed method significantly outperforms existing baselines on creative writing benchmarks on a semi-structured long chain-of-thought (CoT) it introduces divergence at the planning phase based on diversity variation, alongside a group-aware diversity reward to encourage distinct trajectories. |
R2AG: Incorporating Retrieval Information into Retrieval Augmented Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to augment large language models with external documents are lacking in the semantic gap between LLMs and retrievers due to differences in their training objectives and architectures. |
| Approach: | They propose to integrate R2AG into R2etrieval augmented generation framework by using a R2-Former to capture retrieval information. |
| Outcome: | The proposed framework fills the semantic gap between LLMs and retrievers due to differences in their training objectives and architectures. |
POINTER: Constrained Progressive Text Generation via Insertion-based Generative Pre-training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing pre-trained language models cannot be directly employed to generate text under specified lexical constraints. |
| Approach: | They propose a method for insertion-based text generation that inserts tokens between existing tokens in a parallel manner. |
| Outcome: | The proposed method is intuitive and interpretable on Wikipedia and Yelp datasets. |
SentBS: Sentence-level Beam Search for Controllable Summarization (2022.emnlp-main)
Copied to clipboard
| Challenge: | Structure-controlled summarization is a useful and interesting research direction . current structure-controlling methods have limited effectiveness in enforcing the desired structure. |
| Approach: | They propose a sentence-level beam search generation method to select suitable sentences for subsequent generations. |
| Outcome: | The proposed method significantly reduces structural discrepancies by 68% on a structure-controlled dataset. |
From Facts to Insights: A Study on the Generation and Evaluation of Analytical Reports for Deciphering Earnings Calls (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have focused on the generation and evaluation of analytical reports derived from Earnings Calls (ECs). |
| Approach: | They propose to use Large Language Models to generate and evaluate analytical reports derived from Earnings Calls (ECs) they propose to introduce specialized agents that introduce diverse viewpoints and desirable topics into the report generation process. |
| Outcome: | The proposed model improves the quality of reports in different settings, while human-written reports remain preferred in the majority of cases. |
G2: Guided Generation for Enhanced Output Diversity in LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to enhance output diversity but compromise quality of outputs. |
| Approach: | They propose a training-free plug-and-play method that enhances output diversity while preserving generation quality. |
| Outcome: | The proposed method enhances output diversity while maintaining an optimal balance between diversity and quality. |
MobileSpeech: A Fast and High-Fidelity Framework for Mobile Zero-Shot Text-to-Speech (2024.acl-long)
Copied to clipboard
| Challenge: | Existing zero-shot text-to-speech systems require a few seconds of unseen speaker voice prompts to generate high-quality voices. |
| Approach: | They propose a zero-shot text-to-speech system based on mobile devices . they use a discrete speech codec to integrate hierarchical information from the codec . |
| Outcome: | The proposed system achieves RTF of 0.09 on a single A100 GPU and has been successfully deployed on mobile devices. |
Annotating a Fable in Italian Sign Language (LIS) (2020.lrec-1)
Copied to clipboard
| Challenge: | fables are short or medium-length stories with a moral and they generally have specific characteristics in SLs that are usually not to be found in spoken languages like Italian. |
| Approach: | They present work for automatic generation of a written text in Italian starting from glosses of fable in Italian Sign Language (LIS). |
| Outcome: | The proposed method was used to generate a written text in Italian starting from glosses of a fable in Italian Sign Language (LIS). |
Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to mitiga hallucinations rely on sampling multiple full-length generations, which introduces significant response latency and becomes ineffective when the model consistently produces hallucines. |
| Approach: | They propose a framework that dynamically monitors the generation process and selectively applies in-process interventions to revise hallucination-prone tokens. |
| Outcome: | The proposed framework outperforms self-consistency-based approaches in both effectiveness and efficiency, achieving higher factual accuracy while significantly reducing computational overhead. |
RecordTwin: Towards Creating Safe Synthetic Clinical Corpora (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to generate high-quality synthetic corpus from clinical documents require learning from the original clinical documents. |
| Approach: | They propose a method to generate synthetic corpus from clinical documents using a large language model. |
| Outcome: | The proposed method generates synthetic documents from in-hospital clinical documents. |
End-to-end Adversarial Sample Generation for Data Augmentation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating adversarial samples have deceived many neural inference models, such as text classification and machine translation. |
| Approach: | They propose an adversarial sample generator that consists of a conditioned paraphrasing model and a condition generator and introduce a pretrained discriminator to help the adversarial sample generator adapt to the data characteristics. |
| Outcome: | The proposed approach improves the performance of the trained model on several tasks and is robust for various attacking techniques. |
Controlled Text Generation for Black-box Language Models via Score-based Progressive Editor (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to control text generation are inapplicable to black-box models or suffer a trade-off between control and fluency. |
| Approach: | They propose a new approach to control text generation that modifies context at the token level during the generation process of a backbone language model and guides subsequent text to naturally include the target attributes. |
| Outcome: | The proposed method can regulate the attributes of the generated text while utilizing the capability of the backbone large language models. |
SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods of generating singable lyrics are based on a given melody, but there are two main challenges: generating the lyrics without knowing the melody and composing compatible melodies. |
| Approach: | They propose a Chinese lyric generation and editing system which rewrites lyrics of an existing song such that they are compatible with the rhythm of the existing melody. |
| Outcome: | The proposed system is based on a randomized multi-level masking strategy and can generate new lyrics or edit fragments without prior knowledge of melody composition. |
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translation (2025.acl-long)
Copied to clipboard
| Challenge: | Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. |
| Approach: | They propose to train LLMs offline and employ a test-time policy to guide simultaneous inference by extracting boundary-aware speech prompts that allow it to be better matched with text input data. |
| Outcome: | The proposed model trains speech LLMs offline and employs a test-time policy to guide simultaneous inference. |
BLM-s/lE: A structured dataset of English spray-load verb alternations for testing generalization in LLMs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Current NLP models are achieving performance comparable to human capabilities on well-established benchmarks. |
| Approach: | They propose a BLM task to identify a missing element in a linguistic pattern from a list of candidate options based on a given matrix. |
| Outcome: | The proposed framework is based on the spray-load verb alternations in English as a case study. |
Learning Fine-Grained Grounded Citations for Attributed Large Language Models (2024.findings-acl)
Copied to clipboard
Lei Huang, Xiaocheng Feng, Weitao Ma, Yuxuan Gu, Weihong Zhong, Xiachong Feng, Weijiang Yu, Weihua Peng, Duyu Tang, Dandan Tu, Bing Qin
| Challenge: | despite impressive performance, large language models still struggle with hallucinations . current approaches suffer from suboptimal citation quality due to reliance on in-context learning . |
| Approach: | They propose a framework that teaches large language models to generate fine-grained citations. |
| Outcome: | The proposed framework outperforms all baselines on the ALCE benchmark and achieves an average improvement of 14.21% in citation quality. |
Demonstration Augmentation for Zero-shot In-context Learning (2024.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated an impressive capability known as In-context Learning (ICL), which enables them to acquire knowledge from textual demonstrations without the need for parameter updates. |
| Approach: | They propose to use model’s previously predicted historical samples as demonstrations for subsequent ones to improve model’ s performance. |
| Outcome: | The proposed method significantly outperforms the previous method and its predecessors in terms of inference cost and time. |
Change Entity-guided Heterogeneous Representation Disentangling for Change Captioning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to describe differences between two images are highly challenging due to distractors such as illumination and viewpoint changes. |
| Approach: | They propose a change-entity-guided disentanglement network that explicitly learns difference representations while mitigating the impact of distractors. |
| Outcome: | The proposed method outperforms existing methods on CLEVR-Change, CLE VR-DC and Spot-the-Diff datasets and achieves state-of-the art performance. |
Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing research on multi-party dialogue generation has focused on structural information inherent in dialogues, but colloquial expressions and incomplete utterances often impede comprehension and weaken the fidelity of dialogue structure representations. |
| Approach: | They propose a framework to improve multi-party dialogue generation through dialogue context rewriting using two complementary feedback signals to construct preference data for both context & response generation. |
| Outcome: | The proposed framework improves multi-party dialogue generation through dialogue context rewriting. |
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking (2026.acl-long)
Copied to clipboard
Zechen Sun, Yuyang Sun, Zecheng Tang, Juntao Li, Wenpeng Hu, Wenliang Chen, Zhunchen Luo, Guotong Geng, Min Zhang
| Challenge: | Existing models with reasoning capabilities suffer from a severe length collapse in open-ended writing . |
| Approach: | They propose a framework that embeds a dynamic plan-write-reflect cycle into the generation process and train a model with interleaved reasoning traces. |
| Outcome: | The proposed framework achieves state-of-the-art performance on long-form benchmarks compared to other models on the same dataset. |
Segment-Based Attention Masking for GPTs (2025.acl-long)
Copied to clipboard
| Challenge: | Causal masking is a fundamental component in Generative Pre-Trained Transformers (GPT) models, playing a crucial role during training. |
| Approach: | They propose to apply causal masking to all input tokens step-by-step, mimicking the generation process. |
| Outcome: | The proposed model can process the entire user prompt at once, but it is applied to all input tokens step-by-step, mimicking the generation process. |
Structured Chain-of-Thought Prompting for Few-Shot Generation of Content-Grounded QA Conversations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Structured chain-of-thought (SCoT) prompting is used to generate content-grounded multi-turn questions and answers with a large language model. |
| Approach: | They propose a structured chain-of-thought prompting approach to generating content-grounded multi-turn question-answer conversations with a pre-trained large language model. |
| Outcome: | The proposed approach increases agent faithfulness to grounding documents by 16.8% when used as training data. |
Benchmarking Multi-National Value Alignment for Large Language Models (2025.findings-acl)
Copied to clipboard
Chengyi Ju, Weijie Shi, Chengzhong Liu, Jiaming Ji, Jipeng Zhang, Ruiyuan Zhang, Jiajie Xu, Yaodong Yang, Sirui Han, Yike Guo
| Challenge: | Existing studies on large language models focus on ethical reviews, failing to capture the diversity of national values. |
| Approach: | They propose a national value extraction pipeline to efficiently construct value assessment datasets and a model-based model with instruction tagging to process raw data sources. |
| Outcome: | The proposed benchmark evaluates the alignment of LLMs with the values of five major nations: China, the United States, the UK, France, and Germany. |
CARL: Constraint-Aware Reinforcement Learning for Planning with LLMs (2026.findings-acl)
Copied to clipboard
Qiuyi Qi, Jinjian Zhang, Mutian Bao, Tian Liang, Guocong Li, Dongnan Liu, Wei Zhou, Jie Liu, Ming Kong, Linjian Mo, Feng Zhang, Qiang Zhu
| Challenge: | Existing approaches to constraint-aware planning fail to enhance the model’s intrinsic focus on constraints. |
| Approach: | They propose a constraint-aware reinforcement learning framework that encourages constraint focus and penalizes neglect of LLMs. |
| Outcome: | The proposed framework outperforms existing frameworks and state-of-the-art reasoning models in a number of real-world applications. |
VideoRAG: Retrieval-Augmented Generation over Video Corpus (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to generating models rely on text and images, but video content is a rich source of multimodal knowledge. |
| Approach: | They propose a framework that dynamically retrieves videos based on their relevance with queries . they use large video language models to represent video content for retrieval . |
| Outcome: | The proposed framework retrieves videos based on relevance with queries and integrates both visual and textual information. |
Context Copying Modulation: The Role of Entropy Neurons in Managing Parametric and Contextual Knowledge Conflicts (2025.findings-emnlp)
Copied to clipboard
Zineddine Tighidet, Andrea Mogini, Hedi Ben younes, Jiali Mei, Patrick Gallinari, Benjamin Piwowarski
| Challenge: | Recent work has identified in autoregressive transformer models a class of neurons that produce a significant effect on the model output entropy while having an overall moderate impact on the ranking of the predicted tokens. |
| Approach: | They identify a class of neurons that produce significant effects on the model output entropy while having an overall moderate impact on the ranking of the predicted tokens. |
| Outcome: | The entropy neurons suppressed context copying behavior in autoregressive transformer models while having moderate impact on the ranking of predicted tokens. |
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. |
MERIT: Multi-Agent Collaboration for Unsupervised Time Series Representation Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to time series representation learning are time-consuming and expert-dependent, which are difficult to generalize across different tasks. |
| Approach: | They propose to use large language model agent to guide unsupervised time series representation learning and a framework to integrate three LLM agents to collaboratively generate positive views for time series data. |
| Outcome: | The proposed framework integrates large language model (LLM) agent to guide unsupervised time series representation learning and compares it with state-of-the-art baselines on multiple time series datasets. |
Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection (2025.findings-acl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) provides external knowledge for accurate and up-to-date responses, but external knowledge is vulnerable to poisoning and unauthorized injections. |
| Approach: | They propose a Gradient-based Masked Token Probability defense method to detect and filter out adversarially crafted documents by examining gradients of the retriever’s similarity function. |
| Outcome: | Experiments show that the proposed method eliminates over 90% of poisoned content while retaining relevant documents. |
TARN-VIST: Topic Aware Reinforcement Network for Visual Storytelling (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for visual storytelling ignore latent topic information. |
| Approach: | They propose a topic-aware reinforcement network for VIsual StoryTelling that takes topic information into account to generate a coherent story. |
| Outcome: | The proposed method outperforms most of the competing models across multiple evaluation metrics. |
Hierarchical Memory Organization for Wikipedia Generation (2025.acl-long)
Copied to clipboard
Eugene J. Yu, Dawei Zhu, Yifan Song, Xiangyu Wong, Jiebin Zhang, Wenxuan Shi, Xiaoguang Li, Qun Liu, Sujian Li
| Challenge: | Existing methods for generating Wikipedia articles do not utilize memory directly for outline generation. |
| Approach: | They propose a method to generate Wikipedia articles autonomously by leveraging a hierarchical memory architecture. |
| Outcome: | The proposed framework outperforms baseline methods in producing informative and reliable articles. |
Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Reasoning Models (LLMs) have demonstrated impressive performances across diverse domains, but how their safety benefits from enhanced reasoning capabilities against jailbreak queries remains unexplored. |
| Approach: | They propose a safety-aware reasoning paradigm that integrates a pivot token-based safety-based reasoning mechanism into LLMs’ generation process. |
| Outcome: | The proposed model improves the safety of large language models against jailbreak queries while minimizing attacks and maintaining the original performance. |
RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing graph-based or hybrid systems lack the ability to integrate supplementary evidence as reasoning unfolds. |
| Approach: | They propose a framework that integrates non-parametric knowledge into Large Language Models . they use a RL-based framework to optimize the entire generation process via RL . |
| Outcome: | The proposed framework outperforms existing RAG frameworks in five question answering benchmarks. |
VET: Verifiable Execution Tracing for Reliable Text-to-SQL Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for text-to-SQL generation are prone to hallucinations and grounding . authors present a novel reasoning paradigm that transforms text- to-Sql from unverifiable textual rationales into step-wise executable semantics. |
| Approach: | They propose a reasoning paradigm that transforms text-to-SQL from unverifiable textual rationales into step-wise executable semantics. |
| Outcome: | The proposed reasoning paradigm transforms text-to-SQL from unverifiable textual rationales into step-wise executable semantics. |
DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation (2026.findings-acl)
Copied to clipboard
Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
| Challenge: | Existing presentation agents rely on predefined workflows and fixed templates to generate presentations. |
| Approach: | They propose an agentic framework that adapts to diverse user intents and iterative refinement based on observation. |
| Outcome: | The proposed framework can be used to generate presentations with environmental observations. |
SeDev: Structured Semantic Exploration for LLM-Driven Code Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown remarkable capabilities in automating code generation, but they suffer from insufficient exploration of the vast solution space. |
| Approach: | They propose a large-scale LLM-driven code generation framework that efficiently finds high-quality solutions in only a few iterations. |
| Outcome: | The proposed framework outperforms baselines while maintaining reasonable time and computational costs. |
SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulas (2025.emnlp-main)
Copied to clipboard
Anjiang Wei, Yuheng Wu, Yingjia Wan, Tarun Suresh, Huanmi Tan, Zhanke Zhou, Sanmi Koyejo, Ke Wang, Alex Aiken
| Challenge: | SATBench is a benchmark for evaluating the logical reasoning capabilities of large language models (LLMs) through logical puzzles derived from Boolean satisfiability (SAT) problems. |
| Approach: | They propose a benchmark to evaluate logical reasoning capabilities of large language models (LLMs) using logical puzzles derived from Boolean satisfiability problems. |
| Outcome: | The proposed model achieves 65.0% accuracy on hard UNSAT problems, close to the baseline of 50%. |
Adaptive Backtracking for Privacy Protection in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing privacy protection methods are prone to privacy leakage, but they are not effective in ensuring the privacy of users. |
| Approach: | They propose to capture latent leakage tendency of large language models during generation process and to construct a new benchmark for personal information. |
| Outcome: | The proposed method improves privacy by up to 14% over strong baselines against adversarial attacks, avoiding the degradation of response utility. |
TRAC: Token-level Reward Assignment for Coherent Abstractive Summarization (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have achieved remarkable success in text summarization, but maintaining logical coherence and contextual consistency remains a pervasive challenge in long-form generation. |
| Approach: | They propose a framework that introduces a token-level reward function by integrating relative sentence gain, inter-sentence attention, and a Gaussian length penalty. |
| Outcome: | The proposed model outperforms the sequence-level baseline by 11.05% in fluency and 10.61% in Relevance. |
Activation Decomposition and Steering for LLM Backdoor Remediation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to defending against LLM backdoors rely on auxiliary models or safety-related datasets. |
| Approach: | They propose a method which contrasts benign and poisoned settings to decompose feature vectors for steering without auxiliary models or datasets. |
| Outcome: | The proposed method achieves better defense qualities than existing steering strategies. |
Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality (2026.findings-acl)
Copied to clipboard
Qipeng Xie, Zi Liang, Jiafei Wu, Yufei Chen, Weizheng Wang, Wenao Ma, Zhong Ming, Haiqin Yang, Kaishun Wu
| Challenge: | Existing studies on prompt engineering have focused on optimizing models for performance under stylistic perturbations. |
| Approach: | They conduct the first analysis of n-gram token-level mechanisms . they find that higher average performance is inherently associated with lower variance and greater stability. |
| Outcome: | The proposed model reduces the variance of the generated code by 40% . the proposed model is based on a large-scale dataset of 132,000 prompt variants . |
Attention Sinks in Diffusion Language Models (2026.findings-acl)
Copied to clipboard
Maximo Eduardo Rulli, Simone Petruzzi, Edoardo Michielon, Fabrizio Silvestri, Simone Scardapane, Alessio Devoto
| Challenge: | Masked Diffusion Language Models (DLMs) employ transformer encoders with bidirectional attention, enabling parallel token generation while maintaining competitive performance. |
| Approach: | They conduct an empirical analysis of DLM attention patterns focusing on the attention sinking phenomenon . they find that DLMs also exhibit attention sinks, but with distinct characteristics . |
| Outcome: | The proposed models employ transformer encoders with bidirectional attention, enabling parallel token generation while maintaining competitive performance. |