Papers with generation task
From Lazy to Prolific: Tackling Missing Labels in Open Vocabulary Extreme Classification by Positive-Unlabeled Sequence Learning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Extreme multi-label classification (OXMC) is a challenging and critical task in natural language processing. |
| Approach: | They propose to use PUSL to reframe OXMC as an infinite keyphrase generation task . they propose to adopt evaluation metrics to reliably assess OXML models with incomplete ground truths. |
| Outcome: | The proposed approach improves on a highly imbalanced e-commerce dataset with missing labels . it generates 30% more unique labels and 72% of its predictions align with actual user queries . |
Bi-Directional Multi-Granularity Generation Framework for Knowledge Graph-to-Text with Large Language Model (2024.acl-short)
Copied to clipboard
| Challenge: | Existing methods generate whole text based on all KG triples at once and may incorporate incorrect KG Triples for each sentence. |
| Approach: | They propose a bi-directional multi-granularity generation framework that generates graph-level sentences based on KG triples instead of the whole text at a time. |
| Outcome: | The proposed framework achieves state-of-the-art in benchmark dataset WebNLG and further analysis shows the efficiency of different modules. |
TaKG: A New Dataset for Paragraph-level Table-to-Text Generation Enhanced with Knowledge Graphs (2022.findings-aacl)
Copied to clipboard
| Challenge: | Existing table-to-text generation benchmarks have some limitations, such as E2E and ToTTo focusing on singlesentence generation tasks. |
| Approach: | They propose a new table-to-text generation dataset called TaKG that uses a set of knowledge graphs to enhance table input. |
| Outcome: | The proposed model outperforms existing models for short-text generation tasks and shows reliable performance on long-text generated across a variety of metrics. |
Efficient Continual Pre-training of LLMs for Low-resource Languages (2025.naacl-industry)
Copied to clipboard
| Challenge: | Open-source large language models (LLMs) are a promising tool for low-resource languages . however, there is still a substantial performance gap between high-resourced languages and LRLs . |
| Approach: | They develop an algorithm to select a subset of texts from a larger corpus and use it to select tokens for LLMs. |
| Outcome: | The proposed algorithm reduces the cost of continual pre-training (CPT) with large amounts of language-specific data. |
Review-based Question Generation with Adaptive Instance Transfer and Augmentation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to generate questions for verbose reviews are inefficient for potential consumers . lack of training data hinders efficient review digestion, authors say . |
| Approach: | They propose to generate questions that can be answered by corresponding review sentences . they propose an iterative learning framework with adaptive instance transfer and augmentation . |
| Outcome: | The proposed model can generate questions that can be answered by review sentences . it is easier to find critical review parts that are important for potential consumers . |
Compositional Structured Explanation Generation with Dynamic Modularized Reasoning (2024.starsem-1)
Copied to clipboard
| Challenge: | Large-scale language models have shown remarkable performance on reasoning tasks such as reading comprehension, natural language inference, story generation, etc. |
| Approach: | They propose a compositional structured explanation generation task to test a model's ability to generalize from generating entailment trees to more steps, focusing on the length and shapes of engorgement trees. |
| Outcome: | The proposed model shows competitive compositional generalization abilities in a generation setting. |
Selecting, Planning, and Rewriting: A Modular Approach for Data-to-Document Generation and Translation (D19-56)
Copied to clipboard
| Challenge: | Existing systems for document-level generation and translation are too complex to capture the complexity of the problem. |
| Approach: | They propose to adapt a large scale system trained on WMT data to a document in a different language. |
| Outcome: | The proposed system generates a textual document from structured data or a document in a different language. |
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. |
A Question-Answer Driven Approach to Reveal Affirmative Interpretations from Verbal Negations (2022.findings-naacl)
Copied to clipboard
Md Mosharaf Hossain, Luke Holman, Anusha Kakileti, Tiffany Kao, Nathan Brito, Aaron Mathews, Eduardo Blanco
| Challenge: | Negations carry affirmative meanings, which are difficult to process and understand by humans. |
| Approach: | They propose a question-answer driven approach to reveal affirmative interpretations from verbal negations. |
| Outcome: | The proposed approach is based on a natural language inference task . it shows that state-of-the-art transformers are insufficient to reveal affirmative interpretations . |
“When Words Fail, Emojis Prevail”: A Novel Architecture for Generating Sarcastic Sentences With Emoji Using Valence Reversal and Semantic Incongruity (2023.acl-srw)
Copied to clipboard
Faria Binte Kader, Nafisa Hossain Nujat, Tasmia Binte Sogir, Mohsinul Kabir, Hasan Mahmud, Md Kamrul Hasan
| Challenge: | Existing sarcasm generation tasks focus on textual sarcasm, but people often use emojis to express their emotions. |
| Approach: | They propose a novel architecture for sarcasm generation with emojis from a non-sarcastic input sentence in English. |
| Outcome: | The proposed architecture generates sarcastic outputs with emojis from a non-sarcastic input sentence in english. |
SchAman: Spell-Checking Resources and Benchmark for Endangered Languages from Amazonia (2022.aacl-short)
Copied to clipboard
Arturo Oncevay, Gerardo Cardoso, Carlo Alva, César Lara Ávila, Jovita Vásquez Balarezo, Saúl Escobar Rodríguez, Delio Siticonatzi Camaiteri, Esaú Zumaeta Rojas, Didier López Francis, Juan López Bautista, Nimia Acho Rios, Remigio Zapata Cesareo, Héctor Erasmo Gómez Montoya, Roberto Zariquiey
| Challenge: | Spell-checking as a generation task requires large amount of data, which is not feasible for endangered languages such as the languages spoken in Peru. |
| Approach: | They propose to use augmented misspelling data to train neural spell-checking models for four endangered languages of Peru: Shipibo-Koniba, Asháninka, Yánesha, yine . |
| Outcome: | The proposed model achieves better scores in most of the errors and languages in the four indigenous languages of Peru: Shipibo-Koniba, Asháninka, Yánesha, yine. |
Video2Commonsense: Generating Commonsense Descriptions to Enrich Video Captioning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Observable changes in the scene are reflected in captions, but actions are also linked to social aspects such as intentions, effects, and attributes that describe the agent. |
| Approach: | They propose to generate captions from videos that describe latent aspects of the human agent's actions. |
| Outcome: | The proposed model can be used to describe latent aspects of human actions in video clips and answer questions about videos. |
BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work adopts separate modules for retrieval and generation, which may be suboptimal since the retrieval task and generation task cannot benefit from each other to improve performance. |
| Approach: | They propose a backbone-shared RAG framework that uses a domain-specific corpus to continuously pre-train a model and then trains two plug-and-play Low-Rank Adaptation modules based on the shared backbone to minimize retrieval and generation losses respectively. |
| Outcome: | The proposed framework outperforms baseline models by 5% and 13% in Hit@3 upon two datasets in retrieval evaluation and by 23% in terms of BLEU-3 in generation evaluation. |
Acrostic Poem Generation (2020.emnlp-main)
Copied to clipboard
| Challenge: | Acrostic poems contain a hidden message; typically, the first letter of each line spells out a word or short phrase. |
| Approach: | They propose a task for acrostic poem generation in English with multiple constraints . they define the task as a generation task with multiple constraint constraints based on a conditional neural language model and a neural rhyming model . |
| Outcome: | The proposed task is based on a baseline model and a neural rhyming model. |
Cluster-Guided Label Generation in Extreme Multi-Label Classification (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing classification-based models are poorly per-form for tail labels and ignore semantic relations among labels. |
| Approach: | They propose to guide label generation using label cluster information to hierarchically generate lower-level labels. |
| Outcome: | The proposed model outperforms classification and generation baselines on tail labels and improves in four popular XMC benchmarks. |
Tagging-Assisted Generation Model with Encoder and Decoder Supervision for Aspect Sentiment Triplet Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in the ASTE task have been driven by Natural Language Generation-based approaches, but most NLG methods overlook the supervision of the encoder-decoder hidden representations and fail to fully utilize the semantic information provided by the labels. |
| Approach: | They propose a tagging-assisted generation model with encoder and decoder supervision that enhances the supervision of the encoder-decoder through multiple-perspective tabbing assistance and label semantic representations. |
| Outcome: | The proposed model enhances the supervision of the encoder and decoder through multiple-perspective tagging assistance and label semantic representations. |
A Hybrid Model of Classification and Generation for Spatial Relation Extraction (2022.coling-1)
Copied to clipboard
| Challenge: | Existing studies only focus on spatial relations extraction as a classification task . spatial information is one kind of critical information for natural language understanding . |
| Approach: | They propose a hybrid model that generates null-role relations and extracts non-null-rol . they propose varying kinds of schemes to represent spatial relation . |
| Outcome: | The proposed model outperforms the baselines on the spatial relation extraction task on SpaceEval. |
StoryWars: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation (2023.acl-long)
Copied to clipboard
| Challenge: | Understanding and generating collaborative stories remains an underexplored area due to the lack of open-domain corpora. |
| Approach: | They propose to use a dataset of 40,000 collaborative stories written by 9,400 different authors from an online platform to generate a multi-task benchmark. |
| Outcome: | The proposed model achieves the best performance on fully-supervised, few-shot, and zero-shot scenarios while achieving the best results on the fully-supervised tasks. |
Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods of implicit discourse relation recognition (IDRR) focus on three aspects: enhancing discourse units representation, enhancing semantic interaction, and joint learning with other tasks. |
| Approach: | They propose a joint model to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. |
| Outcome: | The proposed model achieves the best performance against several state-of-the-art systems on Chinese and English datasets. |
Generate & Rank: A Multi-task Framework for Math Word Problems (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies formalize MWP as a generation task but mathematical expressions are prone to minor mistakes. |
| Approach: | They propose a ranking task for math word problem (MWP) that learns from its own mistakes and distinguishes between correct and incorrect expressions. |
| Outcome: | The proposed model outperforms baselines on the classical Math23k dataset and is 7% higher than the state-of-the-art. |
Knowledge Enhanced Reflection Generation for Counseling Dialogues (2022.acl-long)
Copied to clipboard
| Challenge: | Using retrieval and generative methods, we generate responses using commonsense and domain knowledge. |
| Approach: | They propose a pipeline that collects domain knowledge through web mining and a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. |
| Outcome: | The proposed pipeline collects domain knowledge through web mining and incorporates knowledge generated by COMET using soft positional encoding and masked self-attention. |
GPT-NER: Named Entity Recognition via Large Language Models (2025.findings-naacl)
Copied to clipboard
Shuhe Wang, Xiaofei Sun, Xiaoya Li, Rongbin Ouyang, Fei Wu, Tianwei Zhang, Jiwei Li, Guoyin Wang, Chen Guo
| Challenge: | Large-scale language models (LLMs) have shown impressive ability for in-context learning with limited training data. |
| Approach: | They propose a novel sequence labeling task that transforms a sequence labeled as a text-generation task into a self-verification task that LLMs can adapt to. |
| Outcome: | The proposed model performs better on NER than supervised models on a variety of tasks . the proposed model can be easily adapted by LLMs to generate a text sequence . |
Can Factual Statements Be Deceptive? The DeFaBel Corpus of Belief-based Deception (2024.lrec-main)
Copied to clipboard
| Challenge: | if a person firmly believes in a non-factual statement, there is no inherent intention to deceive. |
| Approach: | They propose to use the DeFaBel corpus to study the relationship between deception and factuality based on belief to generate arguments supporting statements . |
| Outcome: | The DeFaBel corpus contains 1031 texts in german, out of which 643 are deceptive and 388 are non-deceptive. |
CEPT: A Contrast-Enhanced Prompt-Tuning Framework for Emotion Recognition in Conversation (2024.lrec-main)
Copied to clipboard
| Challenge: | Emotion recognition in conversation research suffers from data imbalance and the presence of similar linguistic expressions for different emotions. |
| Approach: | They propose a Contrast-Enhanced Prompt-Tuning framework that transforms an ERC task into a Masked Language Modeling task and generates the emotion for each utterance in the conversation. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on all three benchmark datasets and excels in recognizing minority emotions. |
FRUIT: Faithfully Reflecting Updated Information in Text (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing work on generating edits grounded in external knowledge has focused on correcting grammar and reducing repetitive typing. |
| Approach: | They propose a novel task where the goal is to update an existing article given new evidence by using a dataset of 170K distantly supervised data produced from Wikipedia snapshots. |
| Outcome: | The proposed model can update Wikipedia articles faithfully with new capabilities and opens doors to many new applications. |
Instruction Tuning with Retrieval-based Examples Ranking for Aspect-based Sentiment Analysis (2024.findings-acl)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects . previous studies have proposed using fixed examples for instruction tuning . |
| Approach: | They propose an instruction learning method with retrieval-based example ranking for ABSA tasks. |
| Outcome: | The proposed method is superior to existing models on three ABSA subtasks. |
MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding (2021.naacl-main)
Copied to clipboard
| Challenge: | a new method for generating metaphors is proposed to generate literal sentences . human evaluations show that our best model generates metaphors better than three well-crafted baselines 66% of the time on average. |
| Approach: | They propose a method to automatically construct a parallel corpus by transforming literal sentences to metaphorical ones using commonsense inference and masked language modeling. |
| Outcome: | The proposed method generates metaphors better than baselines 66% of the time on average. |
Pre-Trained Language-Meaning Models for Multilingual Parsing and Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) have been used for tasks in computational semantics but meaning representations are not included in PLMs. |
| Approach: | They propose to include meaning representations besides natural language texts in the same model . they propose to use DRSs to improve performance of non-English tasks . |
| Outcome: | The proposed approach achieves the best performance on multilingual parsing and DRS-to-text generation tasks. |
Personalized Transformer for Explainable Recommendation (2021.acl-long)
Copied to clipboard
| Challenge: | Recent years have witnessed the successful application of natural language generation. |
| Approach: | They propose a model that uses user and item IDs to predict the words in the target explanation to make personalized Transformer. |
| Outcome: | The proposed model outperforms BERT on the explainable recommendation task in terms of effectiveness and efficiency. |
Thinking Like a Skeptic: Defeasible Inference in Natural Language (2020.findings-emnlp)
Copied to clipboard
Rachel Rudinger, Vered Shwartz, Jena D. Hwang, Chandra Bhagavatula, Maxwell Forbes, Ronan Le Bras, Noah A. Smith, Yejin Choi
| Challenge: | Defeasible inference is a mode of reasoning in which an inference may be weakened or overturned in light of new evidence. |
| Approach: | They propose a dataset for defeasible inference in natural language that includes extensions to existing inference datasets. |
| Outcome: | Defeasible NLI extends existing datasets for defeaasibility inference in natural language . generative models can weaken or strengthen inferences up to 68% of the time, it shows . |
SciReviewGen: A Large-scale Dataset for Automatic Literature Review Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing literature review models have addressed literature review generation, but lack of large-scale datasets has been a stumbling block. |
| Approach: | They propose to use a large-scale dataset to evaluate automatic literature review generation models. |
| Outcome: | The proposed model can generate summaries comparable to human-written reviews while lacking detailed information. |
Evaluation of African American Language Bias in Natural Language Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have shown that large language generation models disadvantaging African American Language (AAL) can be biased for certain language varieties, but there is little research on the impact of these biases on other languages. |
| Approach: | They evaluate how well LLMs understand African American Language (AAL) in comparison to white Mainstream English (WME) using a dataset of AAL texts from a variety of regions and contexts, they find dialectal bias in six pre-trained LLM. |
| Outcome: | The proposed models understand African American language in comparison to white mainstream English (WME) the proposed models have performance gaps on two tasks that are not matched by the model. |
Cogito: A Cognitive Agentic Framework Driven by Dynamic Graph of Thoughts for Financial Report Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to financial report generation are insufficient to handle dynamic uncertainties of real-world financial environments. |
| Approach: | They propose a cognitively grounded agentic framework for professional financial report generation that is driven by Dynamic Graph of Thoughts and a social collaboration mechanism to facilitate coordinated agent interaction. |
| Outcome: | The proposed framework is based on a dynamic reasoning model and social collaboration mechanism. |
Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation (2021.acl-long)
Copied to clipboard
| Challenge: | Existing related work generation models are inflexible and extract sentences from multiple papers to form a related work discussion. |
| Approach: | They propose a Relation-aware Related work generator which generates an abstractive related work from the given multiple scientific papers in the same research area. |
| Outcome: | The proposed model improves over existing models and can be used to familiarize researchers with the state of the art in the field. |
CodeReviewQA: The Code Review Comprehension Assessment for Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | State-of-the-art large language models (LLMs) have demonstrated impressive code generation capabilities but struggle with real-world software engineering tasks such as revising source code to address code reviews. |
| Approach: | They propose a benchmark to evaluate large language models' ability to bridge both technical and conversational contexts by decomposing the generation task of code refinement into three essential reasoning steps. |
| Outcome: | The proposed benchmark exposes specific model weaknesses in code review comprehension disentangled from their generative automated code refinement results. |
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. |
Generating Hashtags for Short-form Videos with Guided Signals (2023.acl-long)
Copied to clipboard
Tiezheng Yu, Hanchao Yu, Davis Liang, Yuning Mao, Shaoliang Nie, Po-Yao Huang, Madian Khabsa, Pascale Fung, Yi-Chia Wang
| Challenge: | Short-form video hashtag recommendation (SVHR) is a classification or ranking problem that selects hashtags from a set of limited candidates. |
| Approach: | They propose a short-form video hashtag recommendation task that better represents how hashtags are created naturally by retrieving relevant hashtags from a large-scale hashtag pool as extra guidance signals. |
| Outcome: | The proposed model outperforms strong classification baselines on two short-form video datasets and the guidance signals boost the performance by 8.11 and 2.17 absolute ROUGE-1 scores on average. |
Structure-aware Knowledge Graph-to-text Generation with Planning Selection and Similarity Distinction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to generate knowledge graph-to-text (KG-to) text rely on pre-trained language models to bridge the gap between the different structures of the input KG and the target text. |
| Approach: | They propose a method that integrates graph structure-aware modules with pre-trained language models to capture the intricate topology information present in the KG. |
| Outcome: | The proposed model captures the topology information present in the knowledge graph and distinguishes similar input KGs through contrastive learning techniques. |
A Model-agnostic Data Manipulation Method for Persona-based Dialogue Generation (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models for introducing explicit personas are expensive due to their expensive collection costs. |
| Approach: | They propose a data manipulation method which is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance. |
| Outcome: | The proposed method is model-agnostic to be packed with any persona-based dialogue generation model to improve their performance. |
From Discrimination to Generation: Low-Resource Intent Detection with Language Model Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies fine-tune discriminative models on specific defined intent classes, preventing them from being directly adopted to new intent domains. |
| Approach: | They propose to use a pre-trained generative intent model to detect new intents from different domains with no parameter updates. |
| Outcome: | The proposed model outperforms baselines that need further fine-tuning or domain-specific samples. |
ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Currently, legal claims are not being used by non-professionals. |
| Approach: | They construct a dataset for Chinese legal claim generation task and then use it to evaluate the generated claims. |
| Outcome: | The proposed dataset is the first for the Chinese legal claim generation task and will be made publicly available. |
Analysis of Plan-based Retrieval for Grounded Text Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large, parametric language models (LLMs) produce fluent text for many applications . hallucinations are generation of text that is factually correct and semantically plausible . |
| Approach: | They propose to use learning-tuned LLMs to infuse models with retrieval mechanisms to reduce hallucinations. |
| Outcome: | The proposed approach reduces the frequency of hallucinations by reducing the coverage of relevant facts and generating more informative responses while providing higher attribution rates. |
Partially-Aligned Data-to-Text Generation with Distant Supervision (2020.emnlp-main)
Copied to clipboard
| Challenge: | Using partially-aligned data is an alternative way of solving the dataset scarcity problem. |
| Approach: | They propose a task to generate human-readable text for describing some given structured data enabling more interpretability. |
| Outcome: | The proposed framework outperforms baseline models and validates the feasibility of using partially-aligned data. |
Semantic Space Grounded Weighted Decoding for Multi-Attribute Controllable Dialogue Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Controlling chatbot utterance generation with multiple attributes is a useful but under-studied problem. |
| Approach: | They propose a framework that possesses strong controllability with a weighted decoding paradigm and improves generation quality with an attribute semantics space. |
| Outcome: | The proposed framework achieves high control accuracy with simultaneous control of 3 aspects while producing interesting and sensible responses even in an out-of-distribution robustness test. |
LLM as a metric critic for low resource relation identification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies show that small language models (SLMs) overfit in low resource situations . however, the gap between pre-training and fine-tuning leads to performance decay . |
| Approach: | They propose to combine large language models and LLM for relation identification by co-evolution . they propose to use a masked language model prompt to generate a relation identification task . |
| Outcome: | The proposed model can handle low resource relation identification tasks with minimal overfitting . the proposed model provides essential background knowledge to assist training process . |
Efficient Layer-wise LLM Fine-tuning for Revision Intention Prediction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models have shown extraordinary success across text generation tasks . however, their potential for simple yet essential text classification remains underexplored . |
| Approach: | a plug-and-play layer-wise parameter-efficient fine-tuning framework is proposed . it fine- tunes a subset of important LLM layers while freezing redundant ones . |
| Outcome: | a plug-and-play framework fine-tunes a subset of important LLM layers while freezing redundant layers. |
SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing automated layout models are ill-suited for spreadsheets, authors say . existing layout models treat components as rectangles with continuous coordinates . authors: spreadsheets are powerful tools for organizing and analyzing data . |
| Approach: | They formalize a spreadsheet layout generation task and introduce a framework for spreadsheet layouts . they use multimodal large language models to combine rule and vision reflection . |
| Outcome: | The proposed framework outperforms baselines in a spreadsheet layout generation task by 22.6%. |
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Jailbreak attacks, where harmful prompts bypass generative models’ built-in safety, raise serious concerns about model vulnerability. |
| Approach: | They propose to reframe the standard generation task as a binary classification problem to assess model refusal tendencies for both harmful and benign queries. |
| Outcome: | The proposed defenses improve model safety or optimize the trade-off between safety and helpfulness. |
Perspective-driven Preference Optimization with Entropy Maximization for Diverse Argument Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Argument generation with diverse perspectives is essential for fostering balanced discourse and mitigating bias. |
| Approach: | They propose a Perspective-aware Preference Optimization with Entropy Maximization framework for diverse argument generation. |
| Outcome: | The proposed framework enhances perspective diversity through preference optimization based on the constructed preference dataset . |
so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Despite popularity of poetry as both an art form and a generation task for large language models, whitespace has not received sufficient attention from the NLP community. |
| Approach: | They examine how 4k poets have used whitespace in their works . they compare it to 51k LLM-generated poems and 12k unpublished poems posted online . |
| Outcome: | The proposed dataset compares 4k poetry poems with 51k LLM-generated poems and 12k unpublished poems posted in an online community. |
Multimodal Dual-Path Decoding for Medical Report Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Current methods for radiology report generation rely on encoder-decoder based frameworks that fail to integrate multimodal clinical evidence with domain-specific knowledge. |
| Approach: | They propose a multimodal dual-path framework that synergistically integrates large vision-language models and large language models for radiology report generation. |
| Outcome: | The proposed framework improves on the public MIMIC-CXR benchmark and shows that it is superior to state-of-the-art models. |