Portrait de Perouz Taslakian

Perouz Taslakian

Membre industriel associé
Professeur associé, McGill University, École d'informatique
Service Now
Sujets de recherche
Apprentissage multimodal
Apprentissage profond
Vision et langage
Site web
Google Scholar
LinkedIn

Publications

Repliqa: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
Joao Monteiro
Pierre-Andre Noel
Étienne Marcotte
Sai Rajeswar
Valentina Zantedeschi
David Vázquez
Nicolas Chapados
Christopher Pal
Perouz Taslakian
Large Language Models (LLMs) are trained on vast amounts of data, most of which is automatically scraped from the internet. This data includ… (voir plus)es encyclopedic documents that harbor a vast amount of general knowledge (e.g., Wikipedia) but also potentially overlap with benchmark datasets used for evaluating LLMs. Consequently, evaluating models on test splits that might have leaked into the training set is prone to misleading conclusions. To foster sound evaluation of language models, we introduce a new test dataset named RepLiQA, suited for question-answering and topic retrieval tasks. RepLiQA is a collection of five splits of test sets, four of which have not been released to the internet or exposed to LLM APIs prior to this publication. Each sample in RepLiQA comprises (1) a reference document crafted by a human annotator and depicting an imaginary scenario (e.g., a news article) absent from the internet; (2) a question about the document's topic; (3) a ground-truth answer derived directly from the information in the document; and (4) the paragraph extracted from the reference document containing the answer. As such, accurate answers can only be generated if a model can find relevant content within the provided document. We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting. Released splits of RepLiQA can be found here: https://huggingface.co/datasets/ServiceNow/repliqa.
2024-12-09
Advances in Neural Information Processing Systems 37 (publié)
doi.org
openreview.net
XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
Joao Monteiro
Étienne Marcotte
Pierre-Andre Noel
Valentina Zantedeschi
David Vázquez
Nicolas Chapados
Christopher Pal
Perouz Taslakian
In-context learning (ICL) approaches typically leverage prompting to condition decoder-only language model generation on reference informati… (voir plus)on. Just-in-time processing of a context is inefficient due to the quadratic cost of self-attention operations, and caching is desirable. However, caching transformer states can easily require almost as much space as the model parameters. When the right context isn't known in advance, caching ICL can be challenging. This work addresses these limitations by introducing models that, inspired by the encoder-decoder architecture, use cross-attention to condition generation on reference text without the prompt. More precisely, we leverage pre-trained decoder-only models and only train a small number of added layers. We use Question-Answering (QA) as a testbed to evaluate the ability of our models to perform conditional generation and observe that they outperform ICL, are comparable to fine-tuned prompted LLMs, and drastically reduce the space footprint relative to standard KV caching by two orders of magnitude.
2023-12-31
EMNLP (Findings) (publié)
doi.org
arxiv.org
Capture the Flag: Uncovering Data Insights with Large Language Models.
Issam H. Laradji
Perouz Taslakian
Sai Rajeswar
Valentina Zantedeschi
Alexandre Lacoste
Nicolas Chapados
David Vázquez
Christopher Pal
Alexandre Drouin
The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making. Howev… (voir plus)er, accomplishing this task requires considerable technical skills, domain expertise, and human labor. This study explores the potential of using Large Language Models (LLMs) to automate the discovery of insights in data, leveraging recent advances in reasoning and code generation techniques. We propose a new evaluation methodology based on a "capture the flag" principle, measuring the ability of such models to recognize meaningful and pertinent information (flags) in a dataset. We further propose two proof-of-concept agents, with different inner workings, and compare their ability to capture such flags in a real-world sales dataset. While the work reported here is preliminary, our results are sufficiently interesting to mandate future exploration by the community.
2023-11-06
NeurIPS.cc/2023/Workshop/FMDM (publié)
doi.org
openreview.net
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
Rim Assouel
Pau Rodríguez
Perouz Taslakian
David Vázquez
Yoshua Bengio
A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios. … (voir plus)Such capacity is not yet attained for machine learning systems. In this work, in the context of visual reasoning, we show how modularity can be leveraged to derive a compositional data augmentation framework inspired by imagination. Our method, denoted Object-centric Compositional Neural Module Network (OC-NMN), decomposes visual generative reasoning tasks into a series of primitives applied to objects without using a domain-specific language. We show that our modular architectural choices can be used to generate new training tasks that lead to better out-of-distribution generalization. We compare our model to existing and new baselines in proposed visual reasoning benchmark that consists of applying arithmetic operations to MNIST digits.
2023-10-27
ArXiv (prépublication)
doi.org
arxiv.org
Explaining Graph Neural Networks Using Interpretable Local Surrogates
Farzaneh Heidari
Perouz Taslakian
Guillaume Rabusseau
2022-12-31
TAG-ML (publié)
proceedings.mlr.press
proceedings.mlr.press
Using Graph Algorithms to Pretrain Graph Completion Transformers
Jonathan Pilault
Mikhail Galkin
Bahare Fatemi
Perouz Taslakian
David Vasquez
Christopher Pal
Recent work on Graph Neural Networks has demonstrated that self-supervised pretraining can further enhance performance on downstream graph, … (voir plus)link, and node classification tasks. However, the efficacy of pretraining tasks has not been fully investigated for downstream large knowledge graph completion tasks. Using a contextualized knowledge graph embedding approach, we investigate five different pretraining signals, constructed using several graph algorithms and no external data, as well as their combination. We leverage the versatility of our Transformer-based model to explore graph structure generation pretraining tasks (i.e. path and k-hop neighborhood generation), typically inapplicable to most graph embedding methods. We further propose a new path-finding algorithm guided by information gain and find that it is the best-performing pretraining task across three downstream knowledge graph completion datasets. While using our new path-finding algorithm as a pretraining signal provides 2-3% MRR improvements, we show that pretraining on all signals together gives the best knowledge graph completion results. In a multitask setting that combines all pretraining tasks, our method surpasses the latest and strong performing knowledge graph embedding methods on all metrics for FB15K-237, on MRR and Hit@1 for WN18RRand on MRR and hit@10 for JF17K (a knowledge hypergraph dataset).
2022-10-13
ArXiv (prépublication)
doi.org
arxiv.org
Object-centric Compositional Imagination for Visual Abstract Reasoning
Rim Assouel
Pau Rodríguez
Perouz Taslakian
David Vázquez
Yoshua Bengio
Like humans devoid of imagination, current machine learning systems lack the ability to adapt to new, unexpected situations by foreseeing th… (voir plus)em, which makes them unable to solve new tasks by analogical reasoning. In this work, we introduce a new compositional imagination framework that improves a model's ability to generalize. One of the key components of our framework is object-centric inductive biases that enables models to perceive the environment as a series of objects, properties, and transformations. By composing these key ingredients, it is possible to generate new unseen tasks that, when used to train the model, improve generalization. Experiments on a simplified version of the Abstraction and Reasoning Corpus (ARC) demonstrate the effectiveness of our framework.
2022-03-24
ICLR.cc/2022/Workshop/OSC (poster)
openreview.net
openreview.net