Papers by Kyosuke Nishida

11 papers
Let’s Put Ourselves in Sally’s Shoes: Shoes-of-Others Prefilling Improves Theory of Mind in Large Language Models (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods for Theory of Mind (ToM) are specialized for inferring beliefs from contexts involving changes in the world state.
Approach: They propose a method which makes fewer assumptions about contexts and is applicable to broader scenarios.
Outcome: The proposed method makes fewer assumptions about contexts and is applicable to broader scenarios.
Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions (2022.findings-naacl)

Copied to clipboard

Challenge: Humans can efficiently learn about new concepts from language descriptions, and we propose a new machine learning model, LIDE, which has a text decoder to generate the descriptions and a decoded text encoder to obtain the text representations of machine-generated descriptions.
Approach: They propose a model with a text decoder to generate the descriptions and a corresponding text encoder to obtain the text representations of machine- or user-generated descriptions.
Outcome: The proposed model outperforms baseline models with machine-generated descriptions and with high-quality user-generated models with high quality explanations.
Multi-style Generative Reading Comprehension (P19-1)

Copied to clipboard

Challenge: Current studies on generative reading comprehension (RC) focus on extracting an answer span from textual evidence and natural language generation (NLG).
Approach: They propose a multi-style abstractive summarization model for question answering called Masque.
Outcome: The proposed model achieves state-of-the-art performance on the Q&A and Q& A + NLG tasks of MS MARCO and NarrativeQA.
Initialization of Large Language Models via Reparameterization to Mitigate Loss Spikes (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to train large language models that require a non-uniform model norm are not effective.
Approach: They propose a technique that allows for uniformity of the norm of the model parameters . they propose 'weight scaling as reparameterization' to adjust the norm to the parameter .
Outcome: The proposed technique outperforms existing methods and stabilizes training with the transformer decoders.
Task-adaptive Pre-training of Language Models with Word Embedding Regularization (2021.findings-acl)

Copied to clipboard

Challenge: Pre-trained language models acquire domain-independent knowledge through pre-training with massive textual resources.
Approach: They propose a task-adaptive pre-training process that makes static embeddings close to the word embedds obtained in the target domain.
Outcome: The proposed process improves on BioASQ and SQuAD when the pre-training corpora were not dominated by indomain data.
Answering while Summarizing: Multi-task Learning for Multi-hop QA with Evidence Extraction (P19-1)

Copied to clipboard

Challenge: Question answering (QA) using textual sources for purposes such as reading comprehension has attracted much attention.
Approach: They propose a Query Focused Extractor model for evidence extraction and multi-task learning with the QA model.
Outcome: The proposed model achieves state-of-the-art evidence extraction score on hotpotQA and FEVER, which is a recognizing textual entailment task on a large textual database.
Debiasing Reward Models via Causally Motivated Inference-Time Intervention (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches for mitigating spurious features in RMs focus on response length . Existing methods focus on RM activation, resulting in performance trade-offs .
Approach: They propose a method that uses neurons to suppress spurious features in RMs at inference time.
Outcome: The proposed method reduces sensitivity to spurious features without inducing performance trade-offs on RM benchmarks.
Self-Adaptive Named Entity Recognition by Retrieving Unstructured Knowledge (2023.eacl-main)

Copied to clipboard

Challenge: Named entity recognition (NER) is costly because of lack of training data and domain experts.
Approach: They propose a self-adaptive neural model that retrieves external knowledge from unstructured text to learn the usages of entities that have not been learned well.
Outcome: The proposed model outperforms strong baselines on cross-neuro-ner datasets by 2.35 points in F1 metric.
Unsupervised Domain Adaptation of Language Models for Reading Comprehension (2020.lrec-1)

Copied to clipboard

Challenge: State-of-the-art reading comprehension models do not have general linguistic intelligence . accuracy of out-domain datasets is affected by the distribution of data .
Approach: They propose to use supervised RC training data in the source domain and unlabeled passages in the target domain to adapt models.
Outcome: The proposed model outperforms the model without domain adaptation with five datasets in different domains.
Scene-Text Aware Image and Text Retrieval with Dual-Encoder (2022.acl-srw)

Copied to clipboard

Challenge: Existing studies on image and text retrieval using a dual-encoder model have not shown their effectiveness for fast inferences.
Approach: They propose a dual-encoder model that connects vision and language in the same semantic space and integrates scene-text and visual information into a model.
Outcome: The proposed model can interpret scene-text and surrounding visual information better than cross-encoder models.
DueT: Image-Text Contrastive Transfer Learning with Dual-adapter Tuning (2023.emnlp-main)

Copied to clipboard

Challenge: Comparative learning models for vision and language models are gaining popularity . dueT trains only adapters inserted into pre-trained image and text encoders .
Approach: They propose a transfer learning method for vision and language models built by contrastive learning that trains only adapters inserted into the frozen image and text encoders.
Outcome: The proposed method outperforms fine-tuning, and the LoRA-based adapter method in English and Japanese domains.

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