Papers with multi-task model
N-LTP: An Open-source Neural Language Technology Platform for Chinese (2021.emnlp-demo)
Copied to clipboard
| Challenge: | Existing tools that teach an independent model for each task are not supported in Chinese. |
| Approach: | They propose an open-source neural language platform supporting six Chinese NLP tasks . source code, documentation, and pre-trained models are available at https://github.com/hit-SCIR/ltp . |
| Outcome: | The proposed platform supports six Chinese NLP tasks. |
Generating Hypothetical Events for Abductive Inference (2021.starsem-1)
Copied to clipboard
| Challenge: | Abductive reasoning is inference to the best explanation given an incomplete set of observations about everyday situations. |
| Approach: | They propose a model that generates what could happen next from a hypothetical scenario and then proposes the most plausible explanation from varying hypothetical scenarios. |
| Outcome: | The proposed model improves over previous vanilla pre-trained models fine-tuned on Abductive NLI. |
fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP (2021.acl-demo)
Copied to clipboard
| Challenge: | Recently, the need for Chinese natural language processing (NLP) has a dramatic increase for many downstream applications. |
| Approach: | They propose to use Chinese word segmentation (CWS), Part-of-Speech (POS) tagging, named entity recognition (NER), and dependency parsing to train a multi-task model based on a pruned BERT. |
| Outcome: | The proposed model performs better than popular segmentation tools on a non-training corpus. |
Explaining the Effectiveness of Multi-Task Learning for Efficient Knowledge Extraction from Spine MRI Reports (2022.naacl-industry)
Copied to clipboard
Arijit Sehanobish, McCullen Sandora, Nabila Abraham, Jayashri Pawar, Danielle Torres, Anasuya Das, Murray Becker, Richard Herzog, Benjamin Odry, Ron Vianu
| Challenge: | Pretrained Transformer based models finetuned on domain specific corpora have changed the landscape of NLP but training or fine-tuning these models for individual tasks can be time consuming and resource intensive. |
| Approach: | They propose to use pretrained Transformer based models finetuned on domain specific corpora to train models for individual tasks. |
| Outcome: | The proposed model can match the performance of a task specific model when the task specific models show similar representations across all of their hidden layers and their gradients are aligned, i.e. their gradient follows the same direction. |
NeKo: Cross-Modality Post-Recognition Error Correction with Tasks-Guided Mixture-of-Experts Language Model (2025.acl-industry)
Copied to clipboard
Yen-Ting Lin, Zhehuai Chen, Piotr Zelasko, Zhen Wan, Xuesong Yang, Zih-Ching Chen, Krishna C Puvvada, Ke Hu, Szu-Wei Fu, Jun Wei Chiu, Jagadeesh Balam, Boris Ginsburg, Yu-Chiang Frank Wang, Chao-Han Huck Yang
| Challenge: | Existing methods to train a model on a mixture of domain datasets require separate correction language models. |
| Approach: | They propose a multi-task correction MoE that trains experts to become an "expert" of speech-to-text, language-totext and vision-to text datasets by learning to route each dataset’s tokens to its mapped expert. |
| Outcome: | The proposed model outperforms GPT-3.5 and Claude-3.5-Sonnet on the Open ASR Leaderboard and reaches an average relative 5.0% WER reduction and substantial improvements in BLEU scores. |
Transductive Auxiliary Task Self-Training for Neural Multi-Task Models (D19-61)
Copied to clipboard
| Challenge: | Multi-task learning and self-training are two common ways to improve a machine learning model’s performance in settings with limited training data. |
| Approach: | They propose a transductive auxiliary task self-training procedure that trains a model on auxiliary tasks and test instances with auxiliary labels generated by a single-task version of the model. |
| Outcome: | The proposed method improves accuracy by 9.56% over the pure multi-task model for dependency relation tagging and 13.03% for semantic taging. |
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. |
English-to-Chinese Transliteration with Phonetic Auxiliary Task (2020.aacl-main)
Copied to clipboard
| Challenge: | Several NMT techniques have been used to enhance machine transliteration models, but few focus on the linguistic features specific to the relevant languages. |
| Approach: | They propose a phonetic auxiliary task that integrates phonetic features into a model to improve generalization performance of the main transliteration task. |
| Outcome: | The proposed model achieves similar performance to the current state of the art with a much smaller size. |
STAR: Spectral Truncation and Rescale for Model Merging (2025.naacl-short)
Copied to clipboard
| Challenge: | Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning. |
| Approach: | They propose a model merging technique that aims at mitigating "merging conflicts" by truncating small components in the respective spectral spaces and then an automatic parameter rescaling scheme to retain the nuclear norm of the original matrix. |
| Outcome: | The proposed model outperforms baseline models on flan-T5 by 4.2% and is robust to hyperparamater choice. |
Measuring the Language of Self-Disclosure across Corpora (2022.findings-acl)
Copied to clipboard
| Challenge: | Existing models that estimate self-disclosure from language are poorly generalized due to variations in corpora and labeling instructions. |
| Approach: | They build single-task models on five self-disclosure corpora and use them to predict self-declaration across corpors. |
| Outcome: | The proposed model predicts self-disclosure across corpora, but the results are poor for out-of-corpora models. |
Dynamic Sampling Strategies for Multi-Task Reading Comprehension (2020.acl-main)
Copied to clipboard
| Challenge: | Prior work focused on model architecture or generalization to held out datasets and largely passed over the particulars of the multi-task learning set up. |
| Approach: | They propose a dynamic sampling strategy that selects instances proportional to the model's current performance on a dataset relative to its single task performance. |
| Outcome: | The proposed model outperforms the best model on ORB, a recent multitask reading comprehension benchmark. |
Analyzing the Effectiveness of the Underlying Reasoning Tasks in Multi-hop Question Answering (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies have utilized underlying reasoning (UR) tasks in multi-hop question answering datasets to explain the predicted answers and evaluate models' reasoning abilities. |
| Approach: | They analyze UR tasks in QA datasets to determine their effectiveness . they find that UR task is helpful in preventing reasoning shortcuts . |
| Outcome: | The proposed model improves QA performance, reasoning shortcuts, and robustness on adversarial questions. |
Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases (2022.coling-1)
Copied to clipboard
| Challenge: | Existing generation-based KBQA methods that translate natural language questions to executable logical forms are proving promising but noise introduced can lead to incorrect results. |
| Approach: | They propose a Generation-based KBQA method that uses auxiliary information to enhance logical form generation by combining unseen KB items with novel combinations. |
| Outcome: | The proposed method achieves state-of-the-art results on ComplexWebQuestions and WebQuestIONSSP datasets. |
A Practical Dialogue-Act-Driven Conversation Model for Multi-Turn Response Selection (D19-1)
Copied to clipboard
| Challenge: | Dialogue acts are important in conversation modeling, but they are rarely available for new conversations. |
| Approach: | They propose an end-to-end multi-task model that integrates dialogue acts with context and response in a crossway fashion. |
| Outcome: | The proposed model improves the accuracy of the dialogue act prediction task and the MRR for the response selection task. |
MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Model merging introduces a novel risk of unauthorized use of large language models due to the high cost of training. |
| Approach: | They propose a model merging method that embeds robust fingerprints into models . they aim to protect LLMs from misappropriation via model merg and model theft . |
| Outcome: | The proposed method enables black-box ownership verification without accessing model weights or intermediate outputs. |
Bayesian Learning for Neural Dependency Parsing (N19-1)
Copied to clipboard
| Challenge: | Several approaches for dependency parsing in the small data regime have been proposed. |
| Approach: | They propose to use stochastic gradient Langevin dynamics to generate samples from the approximated posterior to overcome the computational and statistical costs of the approximate inference step. |
| Outcome: | The proposed model outperforms the biaffine model on 6 languages with less than 5k training instances and improves across five languages. |
Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction (D18-1)
Copied to clipboard
| Challenge: | Existing relation extraction systems are designed for within-sentence relations, but extracting information from scientific articles requires relations across sentences. |
| Approach: | They propose a multi-task setup for identifying entities, relations, and coreference clusters in scientific articles . they develop a unified framework called SciIE with shared span representations to solve this problem . |
| Outcome: | The proposed model outperforms existing models without domain-specific features in scientific information extraction. |
Learning Task Sampling Policy for Multitask Learning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to train multi-task models with auxiliary tasks are limited by the number of combinations and the importance of each auxiliary task is not known a priori. |
| Approach: | They propose a search method that automatically assigns importance weights to auxiliary tasks to improve the target task quality. |
| Outcome: | The proposed method outperforms uniform sampling and the corresponding single-task baseline on XNLI and GLUE. |
STTATTS: Unified Speech-To-Text And Text-To-Speech Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a multi-task learning approach is currently available for speech recognition and speech synthesis models . |
| Approach: | They propose a parameter-efficient approach to learning ASR and TTS jointly . they use English as a resource-rich language and Arabic as 'low-resource' language . |
| Outcome: | The proposed model saves 50% of computational and memory costs while learning ASR and TTS jointly. |
Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection (2022.acl-long)
Copied to clipboard
| Challenge: | Existing ‘Stereotype Detection’ datasets adopt a diagnostic approach toward large PLMs. |
| Approach: | They propose a multi-task model that leverages the abundance of data-rich neighboring tasks such as hate speech detection, offensive language detection, misogyny detection, etc., to improve the empirical performance. |
| Outcome: | The proposed model achieves significant gains over baselines on hate speech detection, offensive language detection, misogyny detection, etc. |
BAM! Born-Again Multi-Task Networks for Natural Language Understanding (P19-1)
Copied to clipboard
| Challenge: | Existing methods to train multi-task neural networks outperform or even match their single-task counterparts are difficult to implement. |
| Approach: | They propose a method that uses knowledge distillation to train multi-task neural networks that outperform or even match their single-task counterparts. |
| Outcome: | The proposed method outperforms or matches single-task neural networks on the GLUE benchmark. |
Fisher Mask Nodes for Language Model Merging (2024.lrec-main)
Copied to clipboard
| Challenge: | Pre-trained models are ubiquitous in natural language processing, but individual fine-tuned models require significant overhead in multi-task scenarios. |
| Approach: | They propose a method for fine-tuning pre-trained models for Transformers using Fisher information. |
| Outcome: | The proposed method outperforms Fisher-weighted averaging in a fraction of the computational cost. |
Information Seeking in the Spirit of Learning: A Dataset for Conversational Curiosity (2020.emnlp-main)
Copied to clipboard
| Challenge: | Open-ended human learning and information-seeking systems often ignore the user’s pre-existing knowledge. |
| Approach: | They propose to use pre-existing user knowledge to build a model that reproduces human assistant policies and improves over a bert content model by 13 mean reciprocal rank points. |
| Outcome: | The proposed model reproduces human assistant policies and improves over a bert content model by 13 mean reciprocal rank points. |
Generating Fact Checking Explanations (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work on automated fact checking is concerned with predicting the veracity of claims based on metadata, social network spread, language used in claims, and, more recently, evidence supporting or denying claims. |
| Approach: | They propose to combine the generation of justifications for verdicts on claims with the multi-task model to optimize both objectives at the same time rather than training them separately. |
| Outcome: | The proposed model improves the informativeness, coverage and overall quality of the generated explanations, rather than training them separately. |
To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Merging (2025.emnlp-main)
Copied to clipboard
Zitao Fang, Guodong Du, Shuyang Yu, Yifei Guo, Yiwei Zhang, Yiyao Cao, Jing Li, Ho-Kin Tang, Sim Kuan Goh
| Challenge: | Existing approaches to model merging ignore the fundamental roles of neurons, connectivity and activation. |
| Approach: | They propose a framework that relies on neuronal mechanisms to mitigate task interference . they decomposed task-specific representations into two complementary subspaces . their results offer new insights into mitigating task interference and improving knowledge fusion . |
| Outcome: | The proposed framework reduces task interference within neurons and improves knowledge fusion. |
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models fail due to performance degradation . existing methods fail for models fine- tuned with low-rank adaptation . |
| Approach: | They propose to constrain the LoRA subspace prior to fine-tuning to ensure that updates relevant to one task do not adversely shift outputs for others. |
| Outcome: | The proposed method can integrate with most existing merging algorithms, reducing unintended interference among tasks. |
Why Do More Experts Fail? A Theoretical Analysis of Model Merging (2026.acl-long)
Copied to clipboard
Zijing Wang, Xingle Xu, YongKang Liu, Yiqun Zhang, Peiqin Lin, Shi Feng, Daling Wang, Xiaocui Yang, Hinrich Schuetze
| Challenge: | Existing methods for model merging struggle to maintain performance gains as the number of merged models increases. |
| Approach: | They propose a Reparameterized Heavy-Tailed method to extend the merged model’s coverage and enhance performance. |
| Outcome: | The proposed method extends the merged model’s coverage and enhances performance on 19 benchmarks, including knowledge-intensive and general-purpose tasks. |