Daiki Shirafuji

According to our database1, Daiki Shirafuji authored at least 12 papers between 2019 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of five.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
GeoSteer: Faithful Chain-of-Thought Steering via Latent Manifold Gradients.
CoRR, January, 2026

2025
A Hybrid Search for Complex Table Question Answering in Securities Report.
CoRR, November, 2025

Bridging the Modality Gap by Similarity Standardization with Pseudo-Positive Samples.
Proceedings of the 39th Pacific Asia Conference on Language, Information and Computation, 2025

An Empirical Survey of Model Merging Algorithms for Social Bias Mitigation.
Proceedings of the 39th Pacific Asia Conference on Language, Information and Computation, 2025

WhiteME at U4 Shared Task: Hybrid Retrieval withTable-Structured Clues for Economic Table QA.
Proceedings of the 18th NTCIR Conference on Evaluation of Information Access Technologies, 2025

Domain Adaptation with Medical Vocabulary-Aware Tokenizerfor Radiology Report Analysis in RadNLP at KAIYO03.
Proceedings of the 18th NTCIR Conference on Evaluation of Information Access Technologies, 2025

Bias Vector: Mitigating Biases in Language Models with Task Arithmetic Approach.
Proceedings of the 31st International Conference on Computational Linguistics, 2025

2021
Argument Extraction for Key Point Generation Using MMR-Based Methods.
IEEE Access, 2021

Limits and Challenges of Embedding-based Question Answering in Export Control Expert System.
Proceedings of the Knowledge-Based and Intelligent Information & Engineering Systems: Proceedings of the 25th International Conference KES-2021, 2021

2020
Summarizing Utterances from Japanese Assembly Minutes using Political Sentence-BERT-based Method for QA Lab-PoliInfo-2 Task of NTCIR-15.
Proceedings of the 15th NTCIR Conference on Evaluation of Information Access Technologies, 2020

2019
STARS at the NTCIR-14 QALab-PoliInfo Classification Task.
Proceedings of the 14th NTCIR Conference on Evaluation of Information Access Technologies, 2019

Debate Outcome Prediction using Automatic Persuasiveness Evaluation and Counterargument Relations.
Proceedings of the Joint Proceedings of the Workshops on Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA 2019) and on Bridging the Gap Between Human and Automated Reasoning (BtG 2019) co-located with 28th International Joint Conference on Artificial Intelligence (IJCAI 2019), 2019


  Loading...