Publication

Augmenting large language models with chemistry tools

Related publications (44)

Stochastic pairwise preference convergence in Bayesian agents

Beliefs inform the behaviour of forward-thinking agents in complex environments. Recently, sequential Bayesian inference has emerged as a mechanism to study belief formation among agents adapting to dynamical conditions. However, we lack critical theory to ...

2024

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Pierre Vandergheynst, Milos Vasic, Francesco Craighero, Renata Khasanova

Under resource constraints, LLMs are usually fine- tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new ...

2024

Beyond fine-tuning: LoRA modules boost near-OOD detection and LLM security

Pierre Vandergheynst, Milos Vasic, Francesco Craighero, Renata Khasanova

Under resource constraints, LLMs are usually fine-tuned with additional knowledge using Parameter Efficient Fine-Tuning (PEFT), using Low-Rank Adaptation (LoRA) modules. In fact, LoRA injects a new set of small trainable matrices to adapt an LLM to a new t ...

2024

Nanomole-scale photochemical thiol-ene chemistry for high-throughput late-stage diversification of peptide macrocycles

Alexander Lund Nielsen, Mischa Schüttel, Mark Daniel Nolan

The photochemical thiol-ene reaction is an efficient method for rapid and chemoselective formation of thioether linkages under mild conditions. It has found widespread use in small-molecule synthesis as well as peptide and protein chemistry. While high-thr ...

WILEY2023

Improving Generalization of Pretrained Language Models

Rabeeh Karimi Mahabadi

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

EPFL2023

Yes but.. Can ChatGPT Identify Entities in Historical Documents?

Emanuela Boros, Ahmed Hamdi

Large language models (LLMs) have been leveraged for several years now, obtaining state-of-the-art performance in recognizing entities from modern documents. For the last few months, the conversational agent ChatGPT has "prompted" a lot of interest in the ...

New York2023

SKILL: Structured Knowledge Infusion for Large Language Models

Martin Jaggi, Fedor Moiseev

Large language models (LLMs) have demonstrated human-level performance on a vast spectrum of natural language tasks. However, it is largely unexplored whether they can better internalize knowledge from a structured data, such as a knowledge graph, or from ...

ASSOC COMPUTATIONAL LINGUISTICS-ACL2022

Go to the Board: A Journey through the Life of Professor David A. Evans

Yimon Aye

By taking a journey through the events that happened during Professor David A. Evans' lifetime in the context of chemical synthesis and drug discovery, this in-focus article reflects upon Professor Evans' lifelong scientific and padegogical impacts on the ...

AMER CHEMICAL SOC2022

Multiple Surface Site Three-Dimensional Structure Determination of a Supported Molecular Catalyst

Moreno Lelli, Pierrick Berruyer, David Benjamin Roger Antoine Gajan, Zhuoran Wang

The structural characterization of supported molecular catalysts is challenging due to the low density of active sites and the presence of several organic/organometallic surface groups resulting from the often complex surface chemistry associated with supp ...

AMER CHEMICAL SOC2022

Horizontal Healing

Anja Fröhlich

A Concideration of Typologies for Housing the Sick as a Spatial Manifestation of knowledge. ...

EPFL Press2022

Graph Chatbot

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.