Noa Garcia


2024

pdf
Can Multiple-choice Questions Really Be Useful in Detecting the Abilities of LLMs?
Wangyue Li | Liangzhi Li | Tong Xiang | Xiao Liu | Wei Deng | Noa Garcia
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)

Multiple-choice questions (MCQs) are widely used in the evaluation of large language models (LLMs) due to their simplicity and efficiency. However, there are concerns about whether MCQs can truly measure LLM’s capabilities, particularly in knowledge-intensive scenarios where long-form generation (LFG) answers are required. The misalignment between the task and the evaluation method demands a thoughtful analysis of MCQ’s efficacy, which we undertake in this paper by evaluating nine LLMs on four question-answering (QA) datasets in two languages: Chinese and English. We identify a significant issue: LLMs exhibit an order sensitivity in bilingual MCQs, favoring answers located at specific positions, i.e., the first position. We further quantify the gap between MCQs and long-form generation questions (LFGQs) by comparing their direct outputs, token logits, and embeddings. Our results reveal a relatively low correlation between answers from MCQs and LFGQs for identical questions. Additionally, we propose two methods to quantify the consistency and confidence of LLMs’ output, which can be generalized to other QA evaluation benchmarks. Notably, our analysis challenges the idea that the higher the consistency, the greater the accuracy. We also find MCQs to be less reliable than LFGQs in terms of expected calibration error. Finally, the misalignment between MCQs and LFGQs is not only reflected in the evaluation performance but also in the embedding space. Our code and models can be accessed at https://github.com/Meetyou-AI-Lab/Can-MC-Evaluate-LLMs.

2021

pdf
Attending Self-Attention: A Case Study of Visually Grounded Supervision in Vision-and-Language Transformers
Jules Samaran | Noa Garcia | Mayu Otani | Chenhui Chu | Yuta Nakashima
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: Student Research Workshop

The impressive performances of pre-trained visually grounded language models have motivated a growing body of research investigating what has been learned during the pre-training. As a lot of these models are based on Transformers, several studies on the attention mechanisms used by the models to learn to associate phrases with their visual grounding in the image have been conducted. In this work, we investigate how supervising attention directly to learn visual grounding can affect the behavior of such models. We compare three different methods on attention supervision and their impact on the performances of a state-of-the-art visually grounded language model on two popular vision-and-language tasks.