Publications

Mitigating Calibration Bias Without Fixed Attribute Grouping for Improved Fairness in Medical Imaging Analysis
Changjian Shui
Justin Szeto
Raghav Mehta
Douglas L. Arnold
Tal Arbel
2023-10-07
OpenReview (publié)
doi.org
openreview.net
SDWD: Style Diversity Weighted Distance Evaluates the Intra-Class Data Diversity of Distributed GANs
Wei Wang
Ziwen Wu
Mingwei Zhang
Yuemei Li
2023-10-07
2023 IEEE International Conference on Image Processing (ICIP) (publié)
doi.org
Crystal-GFN: sampling crystals with desirable properties and constraints
Mila AI4Science
Alex Hernández-García
Alexandre Duval
Alexandra Volokhova
Yoshua Bengio
Divya Sharma
Pierre Luc Carrier
Yasmine Benabed
Michał Koziarski
Victor Schmidt
Gian-Marco Rignanese
Pierre-Paul De Breuck
Paulette Clancy
Accelerating material discovery holds the potential to greatly help mitigate the climate crisis. Discovering new solid-state materials such … (voir plus)as electrocatalysts, super-ionic conductors or photovoltaic materials can have a crucial impact, for instance, in improving the efficiency of renewable energy production and storage. In this paper, we introduce Crystal-GFN, a generative model of crystal structures that sequentially samples structural properties of crystalline materials, namely the space group, composition and lattice parameters. This domain-inspired approach enables the flexible incorporation of physical and structural hard constraints, as well as the use of any available predictive model of a desired physicochemical property as an objective function. To design stable materials, one must target the candidates with the lowest formation energy. Here, we use as objective the formation energy per atom of a crystal structure predicted by a new proxy machine learning model trained on MatBench. The results demonstrate that Crystal-GFN is able to sample highly diverse crystals with low (median -3.1 eV/atom) predicted formation energy.
2023-10-06
arXiv (prépublication)
doi.org
arxiv.org
Driving into the Loop: Mapping Automation Bias and Liability Issues for Advanced Driver Assistance Systems
Katie Szilagyi
Jason Millar
AJung Moon
Shalaleh Rismani
2023-10-06
Digital Society (publié)
doi.org
Efficient Classification of Long Documents via State-Space Models
Peng Lu
Suyuchen Wang
Mehdi Rezagholizadeh
Bang Liu
Ivan Kobyzev
2023-10-06
EMNLP/2023/Conference (accepté)
openreview.net
openreview.net
Evaluating Dependencies in Fact Editing for Language Models: Specificity and Implication Awareness
Zichao Li
Ines Arous
Siva Reddy
Jackie C.K. Cheung
The potential of using a large language model (LLM) as a knowledge base (KB) has sparked significant interest. To maintain the knowledge acq… (voir plus)uired by LLMs, we need to ensure that the editing of learned facts respects internal logical constraints, which are known as dependency of knowledge. Existing work on editing LLMs has partially addressed the issue of dependency, when the editing of a fact should apply to its lexical variations without disrupting irrelevant ones. However, they neglect the dependency between a fact and its logical implications. We propose an evaluation protocol with an accompanying question-answering dataset, StandUp, that provides a comprehensive assessment of the editing process considering the above notions of dependency. Our protocol involves setting up a controlled environment in which we edit facts and monitor their impact on LLMs, along with their implications based on If-Then rules. Extensive experiments on StandUp show that existing knowledge editing methods are sensitive to the surface form of knowledge, and that they have limited performance in inferring the implications of edited facts.
2023-10-06
Conference on Empirical Methods in Natural Language Processing (accepté)
doi.org
openreview.net
HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
Yu Song
Santiago Miret
Huan Zhang
Bang Liu
2023-10-06
EMNLP/2023/Conference (accepté)
openreview.net
openreview.net
Investigating the Effect of Pre-finetuning BERT Models on NLI Involving Presuppositions
Jad Kabbara
Jackie CK Cheung
2023-10-06
EMNLP/2023/Conference (accepté)
openreview.net
openreview.net
MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretations
Arkil Patel
Satwik Bhattamishra
Siva Reddy
Dzmitry Bahdanau
2023-10-06
Conference on Empirical Methods in Natural Language Processing (accepté)
doi.org
openreview.net
MAPO: Boosting Large Language Model Performance with Model-Adaptive Prompt Optimization
Yuyan Chen
Zhihao Wen
Ge Fan
Zhengyu Chen
Wei Wu
Dayiheng Liu
Zhixu Li
Bang Liu
Yanghua Xiao
2023-10-06
EMNLP/2023/Conference (accepté)
openreview.net
openreview.net
MOQAGPT: Zero-Shot Multi-modal Open-domain Question Answering with Large Language Models
Le Zhang
Yihong Wu
Fengran Mo
Jian-Yun Nie
Aishwarya Agrawal
Multi-modal open-domain question answering typically requires evidence retrieval from databases across diverse modalities, such as images, t… (voir plus)ables, passages, etc. Even Large Language Models (LLMs) like GPT-4 fall short in this task. To enable LLMs to tackle the task in a zero-shot manner, we introduce MoqaGPT, a straightforward and flexible framework. Using a divide-and-conquer strategy that bypasses intricate multi-modality ranking, our framework can accommodate new modalities and seamlessly transition to new models for the task. Built upon LLMs, MoqaGPT retrieves and extracts answers from each modality separately, then fuses this multi-modal information using LLMs to produce a final answer. Our methodology boosts performance on the MMCoQA dataset, improving F1 by +37.91 points and EM by +34.07 points over the supervised baseline. On the MultiModalQA dataset, MoqaGPT surpasses the zero-shot baseline, improving F1 by 9.5 points and EM by 10.1 points, and significantly closes the gap with supervised methods. Our codebase is available at https://github.com/lezhang7/MOQAGPT.
2023-10-06
EMNLP/2023/Conference (accepté)
doi.org
openreview.net
RainProof: An Umbrella to Shield Text Generator from Out-Of-Distribution Data
Maxime Darrin
Pablo Piantanida
Pierre Colombo
Implementing effective control mechanisms to ensure the proper functioning and security of deployed NLP models, from translation to chatbots… (voir plus), is essential. A key ingredient to ensure safe system behaviour is Out-Of-Distribution (OOD) detection, which aims to detect whether an input sample is statistically far from the training distribution. Although OOD detection is a widely covered topic in classification tasks, most methods rely on hidden features output by the encoder. In this work, we focus on leveraging soft-probabilities in a black-box framework, i.e. we can access the soft-predictions but not the internal states of the model. Our contributions include: (i) RAINPROOF a Relative informAItioN Projection OOD detection framework; and (ii) a more operational evaluation setting for OOD detection. Surprisingly, we find that OOD detection is not necessarily aligned with task-specific measures. The OOD detector may filter out samples well processed by the model and keep samples that are not, leading to weaker performance. Our results show that RAINPROOF provides OOD detection methods more aligned with task-specific performance metrics than traditional OOD detectors.
2023-10-06
EMNLP/2023/Conference (accepté)
openreview.net
openreview.net