Publications

Crystal-GFN: sampling crystals with desirable properties and constraints
Alex Hernandez-Garcia
Alexandre AGM Duval
Alexandra Volokhova
Divya Sharma
pierre luc carrier
Michał Koziarski
Victor Schmidt
Accelerating material discovery holds the potential to greatly help mitigate the climate crisis. Discovering new solid-state materials such … (see more)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.
Efficient Classification of Long Documents via State-Space Models
Peng Lu
Suyuchen Wang
Mehdi Rezagholizadeh
Ivan Kobyzev
EpiK-Eval: Evaluation for Language Models as Epistemic Models
Gabriele Prato
Jerry Huang
Prasanna Parthasarathi
Shagun Sodhani
In the age of artificial intelligence, the role of large language models (LLMs) is becoming increasingly central. Despite their growing prev… (see more)alence, their capacity to consolidate knowledge from different training documents—a crucial ability in numerous applications—remains unexplored. This paper presents the first study examining the capability of LLMs to effectively combine such information within their parameter space. We introduce EpiK-Eval, a novel question-answering benchmark tailored to evaluate LLMs' proficiency in formulating a coherent and consistent knowledge representation from segmented narratives. Evaluations across various LLMs reveal significant weaknesses in this domain. We contend that these shortcomings stem from the intrinsic nature of prevailing training objectives. Consequently, we advocate for refining the approach towards knowledge consolidation, as it harbors the potential to dramatically improve their overall effectiveness and performance. The findings from this study offer insights for developing more robust and reliable LLMs. Our code and benchmark are available at https://github.com/chandar-lab/EpiK-Eval
HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
Yu Song
Santiago Miret
Huan Zhang
Investigating the Effect of Pre-finetuning BERT Models on NLI Involving Presuppositions
Jad Kabbara
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
Yanghua Xiao
MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Model
Le Zhang
Yihong Wu
Fengran Mo
Jian-Yun Nie
Multi-modal open-domain question answering typically requires evidence retrieval from databases across diverse modalities, such as images, t… (see more)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.
RainProof: An Umbrella to Shield Text Generator from Out-Of-Distribution Data
Maxime Darrin
Pierre Colombo
Implementing effective control mechanisms to ensure the proper functioning and security of deployed NLP models, from translation to chatbots… (see more), 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.
Responsible AI Considerations in Text Summarization Research: A Review of Current Practices
Yu Lu Liu
Meng Cao
Su Lin Blodgett
Adam Trischler
AI and NLP publication venues have increasingly encouraged researchers to reflect on possible ethical considerations, adverse impacts, and o… (see more)ther responsible AI issues their work might engender. However, for specific NLP tasks our understanding of how prevalent such issues are, or when and why these issues are likely to arise, remains limited. Focusing on text summarization—a common NLP task largely overlooked by the responsible AI community—we examine research and reporting practices in the current literature. We conduct a multi-round qualitative analysis of 333 summarization papers from the ACL Anthology published between 2020–2022. We focus on how, which, and when responsible AI issues are covered, which relevant stakeholders are considered, and mismatches between stated and realized research goals. We also discuss current evaluation practices and consider how authors discuss the limitations of both prior work and their own work. Overall, we find that relatively few papers engage with possible stakeholders or contexts of use, which limits their consideration of potential downstream adverse impacts or other responsible AI issues. Based on our findings, we make recommendations on concrete practices and research directions.
Sparse Universal Transformer
Shawn Tan
Yikang Shen
Zhenfang Chen
Chuang Gan
The Universal Transformer (UT) is a variant of the Transformer that shares parameters across its layers and is Turing-complete under certain… (see more) assumptions. Empirical evidence also shows that UTs have better compositional generalization than Vanilla Transformers (VTs) in formal language tasks. The parameter-sharing also affords it better parameter efficiency than VTs. Despite its many advantages, most state-of-the-art NLP systems use VTs as their backbone model instead of UTs. This is mainly because scaling UT parameters is more compute and memory intensive than scaling up a VT. This paper proposes the Sparse Universal Transformer (SUT), which leverages Sparse Mixture of Experts (SMoE) to reduce UT's computation complexity while retaining its parameter efficiency and generalization ability. Experiments show that SUT combines the best of both worlds, achieving strong generalization results on formal language tasks (Logical inference and CFQ) and impressive parameter and computation efficiency on standard natural language benchmarks like WMT'14.
The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning
Tian Jin
Nolan Clement
Xin Dong
Vaishnavh Nagarajan
Michael Carbin
Jonathan Ragan-Kelley
How does scaling the number of parameters in large language models (LLMs) affect their core capabilities? We study two natural scaling techn… (see more)iques -- weight pruning and simply training a smaller or larger model, which we refer to as dense scaling -- and their effects on two core capabilities of LLMs: (a) recalling facts presented during pre-training and (b) processing information presented in-context during inference. By curating a suite of tasks that help disentangle these two capabilities, we find a striking difference in how these two abilities evolve due to scaling. Reducing the model size by more than 30\% (via either scaling approach) significantly decreases the ability to recall facts seen in pre-training. Yet, a 60--70\% reduction largely preserves the various ways the model can process in-context information, ranging from retrieving answers from a long context to learning parameterized functions from in-context exemplars. The fact that both dense scaling and weight pruning exhibit this behavior suggests that scaling model size has an inherently disparate effect on fact recall and in-context learning.
Towards Reliable Misinformation Mitigation: Generalization, Uncertainty, and GPT-4
Kellin Pelrine
Anne Imouza
Meilina Reksoprodjo
Camille Thibault
Caleb Gupta
Joel Christoph
Jean-François Godbout
Misinformation poses a critical societal challenge, and current approaches have yet to produce an effective solution. We propose focusing on… (see more) generalization, uncertainty, and how to leverage recent large language models, in order to create more practical tools to evaluate information veracity in contexts where perfect classification is impossible. We first demonstrate that GPT-4 can outperform prior methods in multiple settings and languages. Next, we explore generalization, revealing that GPT-4 and RoBERTa-large exhibit differences in failure modes. Third, we propose techniques to handle uncertainty that can detect impossible examples and strongly improve outcomes. We also discuss results on other language models, temperature, prompting, versioning, explainability, and web retrieval, each one providing practical insights and directions for future research. Finally, we publish the LIAR-New dataset with novel paired English and French misinformation data and Possibility labels that indicate if there is sufficient context for veracity evaluation. Overall, this research lays the groundwork for future tools that can drive real-world progress to combat misinformation.