Papers by Masaki Asada

7 papers
ProMQA: Question Answering Dataset for Multimodal Procedural Activity Understanding (2025.naacl-long)

Copied to clipboard

Challenge: Existing studies typically provide traditional, but less practical evaluation testbeds for multimodal systems.
Approach: They propose a novel evaluation dataset, ProMQA, to measure the advancement of systems in application-oriented scenarios.
Outcome: The proposed evaluation dataset reveals a significant gap between human and competitive multimodal models.
Assessing the Belief Consistency of Large Language Models on the Logical Conversation Process (2026.acl-long)

Copied to clipboard

Challenge: Large language models have been shown remarkable ability to understand given contexts.
Approach: They propose a method to evaluate whether beliefs held by LLMs remain consistent . they propose to use multiple choice question answering format to assess belief consistency .
Outcome: The proposed method evaluates the consistency of LLMs in a multiple-choice question answering format.
Principled Self-Correction in Discrete Diffusion: A UCB-Guided Framework for Text Generation (2026.eacl-long)

Copied to clipboard

Challenge: Existing diffusion models are trained on corrupted ground-truth tokens, but at inference time they must denoise inputs corruptes from their own predictions.
Approach: They propose a framework that denoises inputs corrupted from their own predictions at inference time.
Outcome: The proposed framework achieves higher faithfulness and coherence over existing diffusion baselines.
Improving Relation Extraction by Sequence-to-sequence-based Dependency Parsing Pre-training (2025.coling-main)

Copied to clipboard

Challenge: Existing studies show that dependency information is used only for encoder-only-based relation extraction tasks.
Approach: They propose a syntax-aware seq2seq pre-trained model for relation extraction that incorporates dependency information into a seq2-trained language model by continual pre-training with a dependency parsing task.
Outcome: The proposed model incorporates dependency information into a seq2seq pre-trained language model by continual pre-training with a generative sequence-to-sequence (sequ2sq)-based dependency parsing task.
Addressing the Training-Inference Discrepancy in Discrete Diffusion for Text Generation (2025.coling-main)

Copied to clipboard

Challenge: Existing discrete diffusion models for text generation have a discrepancy between training and inference.
Approach: They propose a training schema that considers two-step diffusion processes and a scheduling technique that gradually increases the probability of using self-generated text as training progresses.
Outcome: The proposed training schema and scheduling technique improve diffusion models on four widely used datasets.
ELAINE-medLLM: Lightweight English Japanese Chinese Trilingual Large Language Model for Bio-medical Domain (2025.coling-main)

Copied to clipboard

Challenge: Existing bilingual or multilingual medical LLMs are limited in multilingual data and therefore perform poorly in non-English languages such as Japanese and Chinese.
Approach: They propose to use a trilingual (English, Japanese, Chinese) large language model adapted for the bio-medical domain to harness the knowledge and abilities of the base model.
Outcome: The proposed model can support English, Japanese, and Chinese and is adapted for a bio-medical domain.
Enhancing Drug-Drug Interaction Extraction from Texts by Molecular Structure Information (P18-2)

Copied to clipboard

Challenge: Graph Convolutional Networks (GCNs) can extract drug-drug interactions (DDIs) from texts using external drug molecular structure information.
Approach: They propose a novel neural method to extract drug-drug interactions (DDIs) from texts using external drug molecular structure information.
Outcome: The proposed model can extract drug-drug interactions (DDIs) from texts with high accuracy and the molecular information can enhance text-based extraction by 2.39 percent points in the F-score on the DDIExtraction 2013 shared task data set.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations