Siva Reddy

aristides.milios@mila.quebec

Arkil Patel

Master's Research - McGill University

Principal supervisor :

arkil.patel@mila.quebec

PhD - McGill University

benno.krojer@mila.quebec

gaurav.kamath@mila.quebec

Gaurav Kamath

PhD - McGill University

Karolina Ewa Stańczak

Postdoctorate - McGill University

karolina.stanczak@mila.quebec

PhD - McGill University

laurestine.bradford@mila.quebec

Mosbach Mosbach

Postdoctorate - McGill University

marius.mosbach@mila.quebec

nicholas.meade@mila.quebec

Nicholas Meade

PhD - McGill University

Github

parishad.behnamghader@mila.quebec

Parishad BehnamGhader

Master's Research - McGill University

Collaborating researcher

spandana.gella@mila.quebec

vaibhav.adlakha@mila.quebec

Vaibhav Adlakha

PhD - McGill University

Xing Han Lu

PhD - McGill University

PhD - None

zdenek.kasner@mila.quebec

Zichao Li

PhD - McGill University

Co-supervisor :

Jackie Cheung

zichao.li@mila.quebec

Publications

LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders

Parishad BehnamGhader

Vaibhav Adlakha

Marius Mosbach

Nicolas Chapados

2024-04-09

ArXiv (preprint)

Scope Ambiguities in Large Language Models

Gaurav Kamath

Sebastian Schuster

Sowmya Vajjala

2024-04-05

ArXiv (preprint)

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Xing Han Lu

Zdeněk Kasner

We propose the problem of conversational web navigation, where a digital agent controls a web browser and follows user instructions to solve… (see more) real-world tasks in a multi-turn dialogue fashion. To support this problem, we introduce WebLINX - a large-scale benchmark of 100K interactions across 2300 expert demonstrations of conversational web navigation. Our benchmark covers a broad range of patterns on over 150 real-world websites and can be used to train and evaluate agents in diverse scenarios. Due to the magnitude of information present, Large Language Models (LLMs) cannot process entire web pages in real-time. To solve this bottleneck, we design a retrieval-inspired model that efficiently prunes HTML pages by ranking relevant elements. We use the selected elements, along with screenshots and action history, to assess a variety of models for their ability to replicate human behavior when navigating the web. Our experiments span from small text-only to proprietary multimodal LLMs. We find that smaller finetuned decoders surpass the best zero-shot LLMs (including GPT-4V), but also larger finetuned multimodal models which were explicitly pretrained on screenshots. However, all finetuned models struggle to generalize to unseen websites. Our findings highlight the need for large multimodal models that can generalize to novel settings. Our code, data and models are available for research: https://mcgill-nlp.github.io/weblinx.

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Xing Han Lu

Zdeněk Kasner

We propose the problem of conversational web navigation, where a digital agent controls a web browser and follows user instructions to solve… (see more) real-world tasks in a multi-turn dialogue fashion. To support this problem, we introduce WEBLINX - a large-scale benchmark of 100K interactions across 2300 expert demonstrations of conversational web navigation. Our benchmark covers a broad range of patterns on over 150 real-world websites and can be used to train and evaluate agents in diverse scenarios. Due to the magnitude of information present, Large Language Models (LLMs) cannot process entire web pages in real-time. To solve this bottleneck, we design a retrieval-inspired model that efficiently prunes HTML pages by ranking relevant elements. We use the selected elements, along with screenshots and action history, to assess a variety of models for their ability to replicate human behavior when navigating the web. Our experiments span from small text-only to proprietary multimodal LLMs. We find that smaller finetuned decoders surpass the best zero-shot LLMs (including GPT-4V), but also larger finetuned multimodal models which were explicitly pretrained on screenshots. However, all finetuned models struggle to generalize to unseen websites. Our findings highlight the need for large multimodal models that can generalize to novel settings. Our code, data and models are available for research: https://mcgill-nlp.github.io/weblinx

2024-03-11

ICLR.cc/2024/Workshop/LLMAgents (poster)

A Compositional Typed Semantics for Universal Dependencies

Laurestine Bradford

Timothy John O'donnell

2024-03-02

ArXiv (preprint)

When does word order matter and when doesn't it?

Xuanda Chen

Timothy John O'donnell

Language models (LMs) may appear insensitive to word order changes in natural language understanding (NLU) tasks. In this paper, we propose … (see more)that linguistic redundancy can explain this phenomenon, whereby word order and other linguistic cues such as case markers provide overlapping and thus redundant information. Our hypothesis is that models exhibit insensitivity to word order when the order provides redundant information, and the degree of insensitivity varies across tasks. We quantify how informative word order is using mutual information (MI) between unscrambled and scrambled sentences. Our results show the effect that the less informative word order is, the more consistent the model's predictions are between unscrambled and scrambled sentences. We also find that the effect varies across tasks: for some tasks, like SST-2, LMs' prediction is almost always consistent with the original one even if the Pointwise-MI (PMI) changes, while for others, like RTE, the consistency is near random when the PMI gets lower, i.e., word order is really important.

2024-02-29

ArXiv (preprint)

The Leukemoid Reaction in Severe Alcoholic Hepatitis: A Case Report

Sachin Agrawal

Sunil Kumar

Sourya Acharya

2024-02-11

Cureus (published)

Data science opportunities of large language models for neuroscience and biomedicine

Danilo Bzdok

Andrew Thieme

Oleksiy Levkovskyy

Paul Wren

Thomas Ray

2024-02-01

Neuron (published)

Sarath Chandar Anbil Parthipan

Are self-explanations from Large Language Models faithful?

Andreas Madsen

2024-01-15

ArXiv (preprint)

StarCoder: may the source be with you!

Raymond Li

Loubna Ben allal

Yangtian Zi

Niklas Muennighoff

Denis Kocetkov

Chenghao Mou

Marc Marone

Christopher Akiki

Jia LI

Jenny Chim

Qian Liu

Evgenii Zheltonozhskii

Terry Yue Zhuo

Thomas Wang

Olivier Dehaene

Mishig Davaadorj

Joel Lamy-Poirier

Joao Monteiro

Oleh Shliazhko

Ming-Ho Yee … (see 49 more)

Nicolas Gontier

Jian Zhu

Nicholas Meade

Armel Zebaze

Logesh Kumar Umapathi

Ben Lipkin

Muhtasham Oblokulov

Zhiruo Wang

Rudra Murthy

Jason T Stillerman

Siva Sankalp Patel

Dmitry Abulkhanov

Marco Zocca

Manan Dey

Zhihan Zhang

N. Fahmy

Urvashi Bhattacharyya

Wenhao Yu

Swayam Singh

Sasha Luccioni

Paulo Villegas

Jan Ebert

M. Kunakov

Fedor Zhdanov

Manuel Romero

Tony Lee

Nadav Timor

Jennifer Ding

Claire S Schlesinger

Hailey Schoelkopf

Jana Ebert

Tri Dao

Mayank Mishra

Alex Gu

Jennifer Robinson

Sean Hughes

Carolyn Jane Anderson

Brendan Dolan-Gavitt

Danish Contractor

Daniel Fried

Yacine Jernite

Carlos Muñoz Ferrandis

Sean M. Hughes

Thomas Wolf

Arjun Guha

Leandro Von Werra

Harm de Vries

The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs)… (see more), introduces StarCoder and StarCoderBase: 15.5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention. StarCoderBase is trained on 1 trillion tokens sourced from The Stack, a large collection of permissively licensed GitHub repositories with inspection tools and an opt-out process. We fine-tuned StarCoderBase on 35B Python tokens, resulting in the creation of StarCoder. We perform the most comprehensive evaluation of Code LLMs to date and show that StarCoderBase outperforms every open Code LLM that supports multiple programming languages and matches or outperforms the OpenAI code-cushman-001 model. Furthermore, StarCoder outperforms every model that is fine-tuned on Python and still retains its performance on other programming languages. We take several important steps towards a safe open-access model release, including an improved PII redaction pipeline and a novel attribution tracing tool, and make the StarCoder models publicly available under a more commercially viable version of the Open Responsible AI Model license.

2023-12-17

TMLR (accepted)

Can Retriever-Augmented Language Models Reason? The Blame Game Between the Retriever and the Language Model

Parishad BehnamGhader

Santiago Miret

Augmenting pretrained language models with retrievers to select the supporting documents has shown promise in effectively solving common NLP… (see more) problems, including language modeling and question answering, in an interpretable way. In this paper, we first study the strengths and weaknesses of different retriever-augmented language models (REALM,

2023-12-01

Findings of the Association for Computational Linguistics: EMNLP 2023 (published)

Evaluating In-Context Learning of Libraries for Code Generation

Arkil Patel

Pradeep Dasigi

2023-11-16

ArXiv (preprint)