Papers with multi-task
Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods to facilitate distantly supervised relation extraction are noisy instances, long-tail relations and unbalanced bag sizes. |
| Approach: | They propose a multi-task approach to facilitate distantly supervised relation extraction by bringing closer the representations of sentences that contain the same Knowledge Base pairs. |
| Outcome: | The proposed approach improves performance on two datasets created via distant supervision. |
A Web Scale Entity Extraction System (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing systems for large-scale entity extraction are limited by the scale and variety of data available on internet platforms. |
| Approach: | They propose to build an entity extraction system for multiple document types at large scale using multi-modal Transformers. |
| Outcome: | The proposed system extracts multiple types of entities from multiple document types at large scale using multi-modal Transformers. |
In-BoXBART: Get Instructions into Biomedical Multi-Task Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Experimental results show that the proposed model outperforms single-task baseline by 3% and multi-task (without instruction) baseline by 18% on an average. |
| Approach: | They propose a unified model that can learn all 32 instruction tasks of the BoX without any task-specific modules. |
| Outcome: | The proposed model outperforms single-task baseline by 3% and multi-task (without instruction) baseline by 18% on an average. |
Multilingual Universal Sentence Encoder for Semantic Retrieval (2020.acl-demos)
Copied to clipboard
Yinfei Yang, Daniel Cer, Amin Ahmad, Mandy Guo, Jax Law, Noah Constant, Gustavo Hernandez Abrego, Steve Yuan, Chris Tar, Yun-hsuan Sung, Brian Strope, Ray Kurzweil
| Challenge: | Using a multi-task trained dual-encoder, our models embed text from 16 languages into a shared semantic space. |
| Approach: | They propose retrieval focused multilingual sentence embedding models on TensorFlow Hub. |
| Outcome: | The models achieve state-of-the-art on monolingual and cross-lingual retrieval (SR) and retrieval question answering (ReQA) competitive performance is obtained on related tasks of translation pair bitext retrieval and retrieving question answering. |
Geolocation with Attention-Based Multitask Learning Models (D19-55)
Copied to clipboard
| Challenge: | predicting the location of a social media post requires discretization of the coordinates, but results in poor performance. |
| Approach: | They propose to combine two approaches to predict location using supervised models . they evaluate a multitask convolutional neural network that predicts both discrete locations and continuous coordinates . |
| Outcome: | The proposed model outperforms singletask models and prior work on one dataset and shows that correlation between labels and coordinates has a marked impact on the effectiveness of a regression task. |
All-in-One: A Deep Attentive Multi-task Learning Framework for Humour, Sarcasm, Offensive, Motivation, and Sentiment on Memes (2020.aacl-main)
Copied to clipboard
| Challenge: | Empirical results show the efficacy of our proposed multi-task framework over existing state-of-the-art systems. |
| Approach: | They propose a multi-task, multi-modal deep learning framework to solve multiple tasks simultaneously. |
| Outcome: | The proposed framework performs better than existing state-of-the-art systems on a complicated form of information, i.e., memes. |
Fine-grained Fallacy Detection with Human Label Variation (2025.naacl-long)
Copied to clipboard
| Challenge: | Fallacy detection is an open challenge in NLP and has shown to be intrinsically difficult for both humans and machines. |
| Approach: | They propose a framework that minimizes annotation errors whilst keeping signals of human label variation. |
| Outcome: | The proposed framework minimizes annotation errors while keeping signals of human label variation. |
Comparatives, Quantifiers, Proportions: a Multi-Task Model for the Learning of Quantities from Vision (N18-1)
Copied to clipboard
| Challenge: | Comparatives, vague quantification, and proportional estimation are not learned at the same time nor governed by the same rules during language acquisition. |
| Approach: | They propose to combine sets comparison, vague quantification, and proportional estimation to learn them together from visual scenes. |
| Outcome: | The proposed model can generalize to unseen combinations of target/non-target objects. |
SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks (2024.eacl-short)
Copied to clipboard
Gourab Dey, Adithya V Ganesan, Yash Kumar Lal, Manal Shah, Shreyashee Sinha, Matthew Matero, Salvatore Giorgi, Vivek Kulkarni, H. Schwartz
| Challenge: | Social science NLP tasks require large data to capture semantics and implicit pragmatics. |
| Approach: | They propose an open-source instruction tuning tool for social science NLP tasks that captures implicit pragmatic cues from text. |
| Outcome: | The proposed model matches or improves on a state-of-the-art, multi-task finetuned model on 80% of social tasks. |
Adversarial Training for Multi-task and Multi-lingual Joint Modeling of Utterance Intent Classification (D18-1)
Copied to clipboard
| Challenge: | In multi-task and multi-lingual joint modeling, common knowledge can be efficiently utilized among multiple tasks or multiple languages. |
| Approach: | They propose to introduce language-specific adversarial networks and task-specific language adversarials to purge the task or language dependencies of shared networks. |
| Outcome: | The proposed method is demonstrated using Japanese and English data sets for three different utterance intent classification tasks. |
Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning (D18-1)
Copied to clipboard
| Challenge: | Pre-trained word embeddings provide significant improvements over untrained embeddables . Feature analysis reveals structural patterns of headline popularity . |
| Approach: | They use a multi-task GRU network to model headline popularity . they find that pre-trained word embeddings provide significant improvements over untrained embeddables . |
| Outcome: | The proposed model improves on pre-trained word embeddings and untrained embeddables . it also improves with the combination of two auxiliary tasks, news-section prediction and part-of-speech tagging . |
Multi-task Active Learning for Pre-trained Transformer-based Models (2022.tacl-1)
Copied to clipboard
| Challenge: | Multi-task learning requires annotating the same text with multiple annotation schemes, which can be costly and laborious. |
| Approach: | They propose to use multi-task active learning paradigm to optimize annotation processes by iteratively selecting unlabeled examples whose annotation is most valuable for the NLP model. |
| Outcome: | The proposed model minimizes annotation efforts for multi-task NLP models by iterating on the most valuable examples. |
What Does Your Smile Mean? Jointly Detecting Multi-Modal Sarcasm and Sentiment Using Quantum Probability (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to model multi-modal sarcasm and sentiment are based on quantum probability . sarcasm and feelings embody intrinsic uncertainty of human cognition . |
| Approach: | They propose a quantum probability-driven multi-task learning framework for sarcasm and sentiment recognition using quantum superpositions and quantum interference. |
| Outcome: | The proposed model achieves state-of-the-art in multi-modal sarcasm and sentiment recognition. |
Multi-Task Retrieval for Knowledge-Intensive Tasks (2021.acl-long)
Copied to clipboard
Jean Maillard, Vladimir Karpukhin, Fabio Petroni, Wen-tau Yih, Barlas Oguz, Veselin Stoyanov, Gargi Ghosh
| Challenge: | Knowledge-intensive tasks require large amounts of knowledge about the world . recent neural retrieval models achieve better results by learning directly from task-specific training data. |
| Approach: | They propose a multi-task trained neural retrieval model that can be universally trained on a wide variety of problems. |
| Outcome: | The proposed model outperforms specialised retrievers on a few-shot setting and matches or improves state-of-the-art on multiple benchmarks. |
Beyond Emotion: A Multi-Modal Dataset for Human Desire Understanding (2022.naacl-main)
Copied to clipboard
| Challenge: | Desire is a primitive instinct and a need for strongly expressing human desires to get or possess something. |
| Approach: | They propose to use MSED to model and understand human desire . they propose to provide a benchmark for human desire analysis . |
| Outcome: | The proposed dataset contains 9,190 text-image pairs with English text. |
RBPtool: A Deep Language Model Framework for Multi-Resolution RBP-RNA Binding Prediction and RNA Molecule Design (2025.emnlp-main)
Copied to clipboard
Jiyue Jiang, Yitao Xu, Zikang Wang, Yihan Ye, Yanruisheng Shao, Yuheng Shan, Jiuming Wang, Xiaodan Fan, Jiao Yuan, Yu Li
| Challenge: | RNA-binding proteins play key roles in post-transcriptional gene regulation . existing methods focus on shallow sequence features or coarse structural representations . large language models allow for precise modeling and biologically informed de novo RNA design . |
| Approach: | They extend RPI15223 into a multi-resolution, structure-level RBP-RNA dataset and introduce RBPtool, a framework that fuses sequence and structural information. |
| Outcome: | The proposed framework achieves state-of-the-art performance on public benchmarks and the RPI15223 dataset while supporting fine-grained level predictions. |
KLEJ: Comprehensive Benchmark for Polish Language Understanding (2020.acl-main)
Copied to clipboard
| Challenge: | Recent introduction of robust, general-purpose models for fine-tuning has enabled improvements in general natural language understanding (NLU) but such benchmarks are only available for a handful of languages. |
| Approach: | They propose a multi-task benchmark for the Polish language understanding with an online leaderboard . they also propose GLUE, a task for named entity recognition and sentiment analysis . |
| Outcome: | The proposed model performs best on three out of nine tasks in the Polish language . the proposed model is also used in an e-commerce domain to analyze the sentiments of users . |
From TextBlob to LLM Agents: Sentiment Model Selection for B2B Technical Support with CSAT Ground Truth (2026.acl-industry)
Copied to clipboard
| Challenge: | a dedicated single-task LLM agent reduces neutral bias from 69% to 22%, improving MCC from -0.018 to 0.347 . only 4.88% of tickets receive negative satisfaction ratings . |
| Approach: | They evaluate sentiment models for customer satisfaction prediction in B2B technical support . they use a complete population of CSAT-rated tickets from 100+ organizations . |
| Outcome: | The proposed model performs better than the most expensive model, with a lower neutrality and lower recall than the budget model. |
Intent-Driven Semantic ID Generation for Grounded Conversational News Recommendation (2026.acl-industry)
Copied to clipboard
| Challenge: | a new approach to news recommendation grounds each suggestion in a rapidly evolving article corpus while addressing implicit user intents that lack explicit retrievable keywords. |
| Approach: | They propose an intent-driven Semantic ID generation paradigm to address these challenges . they map diverse intents to hierarchical SID prefixes and then fuzzy-match them to current news pool . |
| Outcome: | The proposed model achieves 0% hallucination and 12.4% L1 match on a mainstream Chinese news platform. |
Issue Framing in Online Discussion Fora (N19-1)
Copied to clipboard
| Challenge: | In online discussion fora, speakers often make arguments by highlighting certain aspects of the topic. |
| Approach: | They propose to use a newswire and social media annotated corpus to detect issue frames in online discussions. |
| Outcome: | The proposed model can be applied to the domain of discussion fora using multi-task and adversarial training. |
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. |
Do Text-to-Text Multi-Task Learners Suffer from Task Conflict? (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing multi-task learning architectures learn a single model across multiple tasks through a shared encoder followed by task-specific decoders. |
| Approach: | They propose to use a shared encoder and language model decoder to learn a single model across multiple tasks. |
| Outcome: | The proposed architecture does surprisingly well across a range of diverse tasks. |
CEM: Machine-Human Chatting Handoff via Causal-Enhance Module (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to predict chatbot failure ignore causal variables, resulting in cost increasement and prediction bias. |
| Approach: | They propose a machine-human chatting handoff module that predicts chatbot failure . they use user state and labor cost to correct the prediction bias . |
| Outcome: | The proposed method improves the performance of existing methods without any elaborate model crafting. |
DESED: Dialogue-based Explanation for Sentence-level Event Detection (2022.coling-1)
Copied to clipboard
Yinyi Wei, Shuaipeng Liu, Jianwei Lv, Xiangyu Xi, Hailei Yan, Wei Ye, Tong Mo, Fan Yang, Guanglu Wan
| Challenge: | Existing methods for sentence-level event detection depend on manual annotations or domain expertise to design sophisticated templates and rules. |
| Approach: | They propose a dialogue-based explanation paradigm to enhance sentence semantics for event detection. |
| Outcome: | The proposed method can be applied to two event detection datasets. |
SEE-Few: Seed, Expand and Entail for Few-shot Named Entity Recognition (2022.coling-1)
Copied to clipboard
| Challenge: | Existing few-shot named entity recognition methods focus on leveraging existing datasets in the rich-resource domains which might fail in training-from-scratch setting. |
| Approach: | They propose a multi-task learning framework for Few-shot named entity recognition without using source domain data. |
| Outcome: | The proposed framework outperforms state-of-the-art few-shot named entity recognition methods on a training-from-scratch dataset. |
MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction (2023.acl-long)
Copied to clipboard
| Challenge: | Existing studies predict sentiment elements in a fixed order, which ignores the interdependence of the elements and the diversity of language expression. |
| Approach: | They propose a multi-view process that aggregates sentiment elements generated in different order . they use element order prompts to guide the language model to generate multiple tuples with different element order based on a given text . |
| Outcome: | The proposed method outperforms existing methods on 10 datasets of 4 benchmark tasks and is highly flexible and transferable across tasks. |
CLoSE: Contrastive Learning of Subframe Embeddings for Political Bias Classification of News Media (2022.coling-1)
Copied to clipboard
| Challenge: | Framing is a political strategy in which journalists and politicians emphasize certain aspects of an issue to influence and sway public opinion. |
| Approach: | They propose a BERT-based model which embeds indicators of frames from news articles in order to predict political bias. |
| Outcome: | The proposed model performs on subframes and political bias classification tasks and is able to detect political bias on both zero-shot and few-shot learning tasks. |
NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks (2022.acl-long)
Copied to clipboard
Swaroop Mishra, Arindam Mitra, Neeraj Varshney, Bhavdeep Sachdeva, Peter Clark, Chitta Baral, Ashwin Kalyan
| Challenge: | Existing AI systems fail to perform basic mathematical reasoning when presented in a slightly different manner. |
| Approach: | They propose a multi-task benchmark that evaluates the performance of AI systems on eight different tasks that at their core require simple arithmetic understanding. |
| Outcome: | The proposed benchmark compares the performance of AI systems on eight different tasks. |
Multi-task and Multi-lingual Joint Learning of Neural Lexical Utterance Classification based on Partially-shared Modeling (C18-1)
Copied to clipboard
| Challenge: | Existing studies on multitask and multilingual joint learning focus on cross-task or cross-lingual knowledge transfer. |
| Approach: | They propose to divide state-of-the-art neural lexical utterance classification into language-specific components that can be shared between different tasks and different languages. |
| Outcome: | The proposed method is able to support multi-task and multi-lingual learning using Japanese and English data sets with three different lexical utterance classification tasks. |
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can be fine-tuned to new tasks, but in multi-task scenarios, training imbalance and seesaw effect often arise. |
| Approach: | They propose a flexible fine-tuning framework that leverages asymmetric optimization among LoRA experts to reduce training imbalance and improve performance. |
| Outcome: | The proposed framework outperforms baseline methods in inter- and intra-task learning scenarios. |
Legal Judgment Prediction based on Knowledge-enhanced Multi-Task and Multi-Label Text Classification (2025.naacl-long)
Copied to clipboard
| Challenge: | Legal judgment prediction (LJP) is an essential task for legal AI, aiming at predicting judgments based on the facts of a case. |
| Approach: | They propose a knowledge-enhanced approach that incorporates 'label-level knowledge' to enhance the representation of case facts for each task and 'task-level' knowledge to improve synergy. |
| Outcome: | The proposed method is effective in comparison to state-of-the-art (SOTA) baselines. |
ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts (2022.emnlp-main)
Copied to clipboard
| Challenge: | a new multi-task, parameter-efficient language model tuning method learns to transfer knowledge across different tasks via a mixture of soft prompts. |
| Approach: | They propose a multi-task, parameter-efficient language model tuning method that uses soft prompts to learn to transfer knowledge across different tasks. |
| Outcome: | The proposed method outperforms prompt tuning and outperfies or matches fully fine-tuned tuning approaches that use 10 times more parameters. |
FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs’ Responsiveness to Human Feedback (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing research focuses on benchmarking LLMs in single-turn dialogues, neglecting the nuanced nature of human feedback within real-world usage scenarios. |
| Approach: | They propose a fine-grained, multi-task benchmark designed to evaluate LLMs’ responsiveness to human feedback under real-world usage scenarios in Chinese. |
| Outcome: | The proposed benchmarks show that human feedback can significantly impact LLMs’ responsiveness in real-world usage scenarios. |
MedINST: Meta Dataset of Biomedical Instructions (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Medical data and tasks require extensive preprocessing and standardization for effective use in training LLMs. |
| Approach: | They propose to use MedINST as a meta-dataset to evaluate LLMs' generalization ability. |
| Outcome: | The meta-dataset of biomedical instruction measures the generalization ability of LLMs across multiple open-domain tasks. |
Tree LSTMs with Convolution Units to Predict Stance and Rumor Veracity in Social Media Conversations (P19-1)
Copied to clipboard
| Challenge: | Existing approaches to learn from social-media conversations have been proposed to identify and contain fake news shared on social media platforms. |
| Approach: | They propose to represent social-media conversations as binarized constituency trees that allows comparing features in source-posts and their replies effectively. |
| Outcome: | The proposed models outperform the current best model by 12% and 15% on F1-macro for rumor-veracity classification and stance classification tasks respectively. |
Superlim: A Swedish Language Understanding Evaluation Benchmark (2023.emnlp-main)
Copied to clipboard
Aleksandrs Berdicevskis, Gerlof Bouma, Robin Kurtz, Felix Morger, Joey Öhman, Yvonne Adesam, Lars Borin, Dana Dannélls, Markus Forsberg, Tim Isbister, Anna Lindahl, Martin Malmsten, Faton Rekathati, Magnus Sahlgren, Elena Volodina, Love Börjeson, Simon Hengchen, Nina Tahmasebi
| Challenge: | In this paper, we present a multi-task benchmark for Swedish language models . we address methodological challenges, such as mitigating the Anglocentric bias when creating datasets for a less-resourced language . |
| Approach: | They propose a multi-task NLP benchmark for Swedish language models . they propose to use superlim to evaluate Swedish language model performance . |
| Outcome: | The proposed benchmark does not approach ceiling performance on any of the tasks, suggesting it is difficult to implement. |
Using Eye-tracking Data to Predict the Readability of Brazilian Portuguese Sentences in Single-task, Multi-task and Sequential Transfer Learning Approaches (2020.coling-main)
Copied to clipboard
Sidney Evaldo Leal, João Marcos Munguba Vieira, Erica dos Santos Rodrigues, Elisângela Nogueira Teixeira, Sandra Aluísio
| Challenge: | Sentence complexity assessment is a relatively new task in Natural Language Processing. |
| Approach: | They propose to use Brazilian Portuguese to evaluate sentences with linguistic features to improve readability. |
| Outcome: | The proposed model reaches the state-of-the-art for Brazilian Portuguese with 97.8% accuracy with linguistic features. |
PoliSe: Reinforcing Politeness Using User Sentiment for Customer Care Response Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Human-machine interactions have increased rapidly assisting humans in their everyday lives. |
| Approach: | They propose to automatically identify the sentiment of the user and transform the neutral responses into polite responses conforming to the sentiment and the conversational history. |
| Outcome: | The proposed approach achieves superior performance compared to baseline models. |
MedEval: A Multi-Level, Multi-Task, and Multi-Domain Medical Benchmark for Language Model Evaluation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing medical datasets require high quality domain-specific datasets. |
| Approach: | They propose a multi-level, multi-task, and multi-domain medical benchmark to facilitate the development of language models for healthcare. |
| Outcome: | The proposed model provides granular potential usage and supports a wide range of tasks. |
Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing multilingual models cannot fully leverage training data when it is available in different task-language combinations. |
| Approach: | They propose a single hypernetwork that unifies multi-task and multilingual learning with efficient adaptation. |
| Outcome: | The proposed model achieves the best or competitive gain when a mixture of multiple resources is available while being significantly more efficient than existing models. |
CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent efforts in natural language processing (NLP) commonsense reasoning research have produced a number of new datasets and benchmarks. |
| Approach: | They propose a manually-curated, multi-task benchmark that evaluates models' ability to apply commonsense reasoning in the context of six real-world NLP tasks. |
| Outcome: | The proposed benchmark evaluates the ability of models to apply commonsense reasoning in the context of six real-world NLP tasks. |
Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for large language models use parameter-efficient techniques such as Low-Rank Adaptation (LoRA) prior studies suggest that the inner A matrices are highly similar during training and therefore suitable for sharing. |
| Approach: | They propose an asymmetric multi-LoRA design with multiple A matrices and a single shared B in multi-task fine-tuning. |
| Outcome: | The proposed methods achieve more balanced performance across tasks with comparable or superior average accuracy relative to existing methods. |
Discourse Structure-Aware Prefix for Generation-Based End-to-End Argumentation Mining (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent advances in AM models overlook the integration of supplementary discourse structure information, resulting in suboptimal outcomes. |
| Approach: | They propose a framework which generates discourse structure-aware prefixes for each layer of the generation model. |
| Outcome: | The proposed framework achieves state-of-the-art performance on two AM benchmarks. |
IberoBench: A Benchmark for LLM Evaluation in Iberian Languages (2025.coling-main)
Copied to clipboard
Irene Baucells, Javier Aula-Blasco, Iria de-Dios-Flores, Silvia Paniagua Suárez, Naiara Perez, Anna Salles, Susana Sotelo Docio, Júlia Falcão, Jose Javier Saiz, Robiert Sepulveda Torres, Jeremy Barnes, Pablo Gamallo, Aitor Gonzalez-Agirre, German Rigau, Marta Villegas
| Challenge: | Existing multi-task benchmarks for Large Language Models are limited to English . a new benchmark is needed to evaluate models on a range of tasks . |
| Approach: | They propose a multilingual, multi-task benchmark for Iberian languages built on the LM Evaluation Harness framework. |
| Outcome: | The proposed benchmark covers 62 tasks divided into 179 subtasks and is available in Iberian, Basque, Catalan, Galician, European Spanish and European Portuguese. |
No Train but Gain: Language Arithmetic for training-free Language Adapters enhancement (2025.coling-main)
Copied to clipboard
| Challenge: | Modular deep learning is the most effective way to lift the curse of multilinguality. |
| Approach: | They propose a method which enables training-free post-processing to address this limitation by adding learning to the language adapters and transitioning the framework from a multi-task to a multiple language setup. |
| Outcome: | The proposed method consistently improves baselines with significant gains, especially in the most challenging case of zero-shot application. |
A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multi-modal intent recognition (MIR) requires integrating non-verbal cues from real-world contexts to enhance human intention understanding. |
| Approach: | They present a comprehensive review of multi-modal intent recognition . they provide a survey of the field covering textual, visual, and acoustic signals . |
| Outcome: | The present survey summarises the current state of multi-modal intent recognition . it includes a comprehensive taxonomy and advanced methods . |
Can You Really Trust Code Copilot? Evaluating Large Language Models from a Code Security Perspective (2025.acl-long)
Copied to clipboard
| Challenge: | Existing code security benchmarks focus on one task and paradigm, such as code completion and generation, without comprehensive assessment across dimensions like secure code generation, vulnerability repair and discrimination. |
| Approach: | They propose a multi-task benchmark for comprehensive evaluation of LLM code security . they also propose VC-Judge, an improved judgment model that aligns closely with human experts . |
| Outcome: | The proposed model can evaluate LLM-generated programs for vulnerabilities in a more efficient and reliable way. |
3MVRD: Multimodal Multi-task Multi-teacher Visually-Rich Form Document Understanding (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing models for visually rich document understanding do not account for the diverse carriers of document versions and their associated noises. |
| Approach: | They propose a multimodal, multi-task, multiteacher joint-grained knowledge distillation model for visually-rich form document understanding. |
| Outcome: | The proposed model outperforms baselines on a comprehensive evaluation of public datasets showing it can handle complex structures and content of visually-rich forms. |
Dynamic Expert Specialization: Towards Catastrophic Forgetting-Free Multi-Domain MoE Adaptation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to adapt Mixture-of-Experts models to multiple domains are prohibitive computation, cross-domain interference or require separate runs per domain. |
| Approach: | They propose a dynamic expert specialization framework for multi-domain adaptation of Mixture-of-Experts models. |
| Outcome: | The proposed framework reduces forgetting by 89% compared to full fine-tuning as domains scale from 2 to 6 and achieves faster convergence than conventional methods. |
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Models (2025.emnlp-main)
Copied to clipboard
Zhen Zhang, Yifan Yang, Kai Zhen, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann, Zheng Zhang
| Challenge: | Large language models (LLMs) have demonstrated exceptional capabilities across diverse tasks, but their fine-tuning requires significant memory, posing challenges for resource-constrained environments. |
| Approach: | They propose a ZO-based framework that eliminates the need for backpropagation and provides a memory-efficient alternative to backprograming. |
| Outcome: | The proposed framework surpasses first-order methods in performance and accuracy. |
Argument Relation Classification through Discourse Markers and Adversarial Training (2024.emnlp-main)
Copied to clipboard
| Challenge: | Argument relation classification (ARC) identifies supportive, contrasting and neutral relations between argumentative units. |
| Approach: | They propose an argument relation classifier that integrates knowledge of discourse markers into a pre-trained RoBERTa model. |
| Outcome: | The proposed model outperforms existing methods and learns discriminative sentence embeddings supporting the task. |
NormAL LoRA: What is the perfect size? (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are crucial for enabling intelligent experiences across applications. |
| Approach: | They propose a low-rank adaptive localization method that uses rank-norm regularization to determine the optimal rank for each weight matrix. |
| Outcome: | NormAL LoRA reduces adapter parameters by 37% while preserving full fine-tuning performance. |
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification (2025.findings-acl)
Copied to clipboard
xu Zhao Pan, Pengfei Zhou, Jiaxin Ai, Wangbo Zhao, Kai Wang, Xiaojiang Peng, Wenqi Shao, Hongxun Yao, Kaipeng Zhang
| Challenge: | Existing benchmarks of large language models focus on error detection, neglecting other scenarios like reasoning search. |
| Approach: | et al. propose a multi-task, multimodal benchmark to assess effectiveness of PRMs . step correctness, answers aggregation and reasoning process search are evaluated . ethical principles of MPBench are based on a set of evaluation paradigms based in a text-based benchmark . |
| Outcome: | a new benchmark assesses the effectiveness of large language models (LLMs) in multiple scenarios . it uses three evaluation paradigms to assess the effectiveness and compares them with existing models . a the proposed model improves reasoning accuracy by providing stepwise feedback for multi-step reasoning results . |
RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models (2025.findings-emnlp)
Copied to clipboard
Jingjing Liu, Zeming Liu, Zihao Cheng, Mengliang He, Xiaoming Shi, Yuhang Guo, Xiangrong Zhu, Yuanfang Guo, Yunhong Wang, Haifeng Wang
| Challenge: | Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair. |
| Approach: | They propose a repository-level code debugging dataset with 22 subtypes of errors that supports 8 commonly used programming languages and 3 debug tasks. |
| Outcome: | The proposed dataset supports 8 commonly used programming languages and 3 debugging tasks. |
Reusable Experiences: Latent Routing and Modular Composition in LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches represent accumulated experience as explicit textual artifacts in prompts or implicitly within model weights via fine-tuning. Existing methods are limited by context windows and cannot internalize knowledge. |
| Approach: | They propose a framework that treats latent experiences as fundamental units for LLM specialization. |
| Outcome: | Experiments on multi-task NLP benchmarks show that this approach outperforms standard fine-tuning, yielding improved generalization through flexible skill reuse. |
AV-Dialog: Spoken Dialogue Models with Audio-Visual Input (2026.acl-long)
Copied to clipboard
| Challenge: | AV-Dialog uses audio and visual cues to track the target speaker, predict turn-taking, and generate coherent responses. |
| Approach: | They propose a multimodal dialog framework that uses both audio and visual cues to track the target speaker. |
| Outcome: | AV-Dialog outperforms audio-only models under interference, reducing transcription errors, improving turn-taking prediction and human-rated dialogue quality. |
Skill Weaving: Efficient LLM Improvement via Modular Skillpacks (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can specialize under fixed memory and inference budgets, but they struggle to achieve high performance across heterogeneous domains. |
| Approach: | They propose a modular improvement framework that partitions full capabilities of a general-purpose model into domain-specific delta modules that reorganize and refine the model's internal knowledge. |
| Outcome: | The proposed framework outperforms monolithic models on multi-task and agentic benchmarks and achieves up to 4 speedup. |