no code implementations • 27 Jan 2025 • Momoka Furuhashi, Hiroaki Funayama, Yuya Iwase, Yuichiroh Matsubayashi, Yoriko Isobe, Toru Nagahama, Saku Sugawara, Kentaro Inui
We propose an "answer diagnosis graph," integrating the text's logical structure with feedback templates.
1 code implementation • 26 Aug 2024 • Hiroaki Funayama, Yuya Asazuma, Yuichiroh Matsubayashi, Tomoya Mizumoto, Kentaro Inui
Specifically, given that scoring rubrics and reference answers differ for each prompt, we utilize key phrases, or representative expressions that the answer should contain to increase scores, and train a SAS model to learn the relationship between key phrases and answers using already annotated prompts (i. e., cross-prompts).
no code implementations • 6 Mar 2024 • Naoki Miura, Hiroaki Funayama, Seiya Kikuchi, Yuichiroh Matsubayashi, Yuya Iwase, Kentaro Inui
Using this dataset, we demonstrate the performance of baselines including finetuned BERT and GPT models with few-shot in-context learning.
no code implementations • 23 Oct 2023 • Mengyu Ye, Tatsuki Kuribayashi, Jun Suzuki, Goro Kobayashi, Hiroaki Funayama
Large language models (LLMs) take advantage of step-by-step reasoning instructions, e. g., chain-of-thought (CoT) prompting.
no code implementations • 16 Jun 2022 • Hiroaki Funayama, Tasuku Sato, Yuichiroh Matsubayashi, Tomoya Mizumoto, Jun Suzuki, Kentaro Inui
Towards guaranteeing high-quality predictions, we present the first study of exploring the use of human-in-the-loop framework for minimizing the grading cost while guaranteeing the grading quality by allowing a SAS model to share the grading task with a human grader.
no code implementations • ACL 2020 • Hiroaki Funayama, Shota Sasaki, Yuichiroh Matsubayashi, Tomoya Mizumoto, Jun Suzuki, Masato Mita, Kentaro Inui
We introduce a new task formulation of SAS that matches the actual usage.