12 citations · 16 across the 9 of their papers we have counts for
9 papers
Debiasing Reward Models via Causally Motivated Inference-Time Intervention
Kazutoshi Shinoda, Kosuke Nishida, Kyosuke Nishida
Reward models (RMs) play a central role in aligning large language models (LLMs) with human preferences. However, RMs are often sensitive to spurious features such as response leng…
Relative Density Ratio Optimization for Stable and Statistically Consistent Model Alignment
Hiroshi Takahashi, Tomoharu Iwata, Atsutoshi Kumagai +4
Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models su…
Which Shortcut Solution Do Question Answering Models Prefer to Learn?
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Question answering (QA) models for reading comprehension tend to learn shortcut solutions rather than the solutions intended by QA datasets. QA models that have learned shortcut so…
Penalizing Confident Predictions on Largely Perturbed Inputs Does Not Improve Out-of-Distribution Generalization in Question Answering
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Question answering (QA) models are shown to be insensitive to large perturbations to inputs; that is, they make correct and confident predictions even when given largely perturbed…
Look to the Right: Mitigating Relative Position Bias in Extractive Question Answering
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Extractive question answering (QA) models tend to exploit spurious correlations to make predictions when a training set has unintended biases. This tendency results in models not b…
Improving the Robustness to Variations of Objects and Instructions with a Neuro-Symbolic Approach for Interactive Instruction Following
Kazutoshi Shinoda, Yuki Takezawa, Masahiro Suzuki +2
An interactive instruction following task has been proposed as a benchmark for learning to map natural language instructions and first-person vision into sequences of actions to in…
Can Question Generation Debias Question Answering Models? A Case Study on Question-Context Lexical Overlap
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Question answering (QA) models for reading comprehension have been demonstrated to exploit unintended dataset biases such as question-context lexical overlap. This hinders QA model…
Improving the Robustness of QA Models to Challenge Sets with Variational Question-Answer Pair Generation
Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa
Question answering (QA) models for reading comprehension have achieved human-level accuracy on in-distribution test sets. However, they have been demonstrated to lack robustness to…
Multi-style Generative Reading Comprehension
Kyosuke Nishida, Itsumi Saito, Kosuke Nishida +4
This study tackles generative reading comprehension (RC), which consists of answering questions based on textual evidence and natural language generation (NLG). We propose a multi-…