Valentin Liévin
YOU?
Author Swipe
View article: Towards physician-centered oversight of conversational diagnostic AI
Towards physician-centered oversight of conversational diagnostic AI Open
Recent work has demonstrated the promise of conversational AI systems for diagnostic dialogue. However, real-world assurance of patient safety means that providing individual diagnoses and treatment plans is considered a regulated activity…
View article: Advancing Conversational Diagnostic AI with Multimodal Reasoning
Advancing Conversational Diagnostic AI with Multimodal Reasoning Open
AI systems based on Large Language Models (LLMs) have demonstrated great potential for conducting diagnostic conversations but evaluation has been largely limited to language-only interactions, deviating from the real-world requirements of…
View article: Advancing Conversational Diagnostic AI with Multimodal Reasoning
Advancing Conversational Diagnostic AI with Multimodal Reasoning Open
Large Language Models (LLMs) have demonstrated great potential for conducting diagnostic conversations but evaluation has been largely limited to language-only interactions, deviating from the real-world requirements of remote care deliver…
View article: Can large language models reason about medical questions?
Can large language models reason about medical questions? Open
Although large language models often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert domain knowledge. We set out to investigate whether closed- and open-…
View article: ThoughtSource: A central hub for large language model reasoning data
ThoughtSource: A central hub for large language model reasoning data Open
Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail at complex reasoning, their reasoning processes are opaque…
View article: ThoughtSource: A central hub for large language model reasoning data (dataset snapshot)
ThoughtSource: A central hub for large language model reasoning data (dataset snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the openly available ThoughtSource datasets.
View article: ThoughtSource: A central hub for large language model reasoning data (dataset snapshot)
ThoughtSource: A central hub for large language model reasoning data (dataset snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the openly available ThoughtSource datasets.
View article: ThoughtSource: A central hub for large language model reasoning data (code snapshot)
ThoughtSource: A central hub for large language model reasoning data (code snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the associated GitHub repository.
View article: ThoughtSource: A central hub for large language model reasoning data (code snapshot)
ThoughtSource: A central hub for large language model reasoning data (code snapshot) Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs). This repository contains a snapshot of the associated GitHub repository.
View article: ThoughtSource: A central hub for large language model reasoning data
ThoughtSource: A central hub for large language model reasoning data Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs).
View article: FindZebra online search delving into rare disease case reports using natural language processing
FindZebra online search delving into rare disease case reports using natural language processing Open
Early diagnosis is crucial for well-being and life quality of the rare disease patient. Access to the most complete knowledge about diseases through intelligent user interfaces can play an important role in supporting the physician reachin…
View article: ThoughtSource: A central hub for large language model reasoning data
ThoughtSource: A central hub for large language model reasoning data Open
ThoughtSource is a meta-dataset and software library for chain-of-thought reasoning in large language models (LLMs).
View article: ThoughtSource: A central hub for large language model reasoning data
ThoughtSource: A central hub for large language model reasoning data Open
Large language models (LLMs) such as GPT-4 have recently demonstrated impressive results across a wide range of tasks. LLMs are still limited, however, in that they frequently fail at complex reasoning, their reasoning processes are opaque…
View article: Variational Open-Domain Question Answering
Variational Open-Domain Question Answering Open
Retrieval-augmented models have proven to be effective in natural language processing tasks, yet there remains a lack of research on their optimization using variational inference. We introduce the Variational Open-Domain (VOD) framework f…
View article: Can large language models reason about medical questions?
Can large language models reason about medical questions? Open
Although large language models (LLMs) often produce impressive outputs, it remains unclear how they perform in real-world scenarios requiring strong reasoning skills and expert domain knowledge. We set out to investigate whether close- and…
View article: Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds.
Optimal Variance Control of the Score-Function Gradient Estimator for Importance-Weighted Bounds. Open
This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE). We prove that in the limit of large K (number of importance samples) one can choose the control variate such…
View article: Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds
Optimal Variance Control of the Score Function Gradient Estimator for Importance Weighted Bounds Open
This paper introduces novel results for the score function gradient estimator of the importance weighted variational bound (IWAE). We prove that in the limit of large $K$ (number of importance samples) one can choose the control variate su…
View article: BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling Open
With the introduction of the variational autoencoder (VAE), probabilistic latent variable models have received renewed attention as powerful generative models. However, their performance in terms of test likelihood and quality of generated…
View article: BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling
BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modeling Open
With the introduction of the variational autoencoder (VAE), probabilistic latent variable models have received renewed attention as powerful generative models. However, their performance in terms of test likelihood and quality of generated…