When large language models meet personalization: Perspectives of challenges and opportunities
The advent of large language models marks a revolutionary breakthrough in artificial
intelligence. With the unprecedented scale of training and model parameters, the capability …
intelligence. With the unprecedented scale of training and model parameters, the capability …
Large language models and causal inference in collaboration: A comprehensive survey
Causal inference has shown potential in enhancing the predictive accuracy, fairness,
robustness, and explainability of Natural Language Processing (NLP) models by capturing …
robustness, and explainability of Natural Language Processing (NLP) models by capturing …
Towards automated circuit discovery for mechanistic interpretability
Through considerable effort and intuition, several recent works have reverse-engineered
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …
nontrivial behaviors oftransformer models. This paper systematizes the mechanistic …
Leace: Perfect linear concept erasure in closed form
N Belrose, D Schneider-Joseph… - Advances in …, 2024 - proceedings.neurips.cc
Abstract Concept erasure aims to remove specified features from a representation. It can
improve fairness (eg preventing a classifier from using gender or race) and interpretability …
improve fairness (eg preventing a classifier from using gender or race) and interpretability …
Radiology-llama2: Best-in-class large language model for radiology
This paper introduces Radiology-Llama2, a large language model specialized for radiology
through a process known as instruction tuning. Radiology-Llama2 is based on the Llama2 …
through a process known as instruction tuning. Radiology-Llama2 is based on the Llama2 …
Does circuit analysis interpretability scale? evidence from multiple choice capabilities in chinchilla
\emph {Circuit analysis} is a promising technique for understanding the internal mechanisms
of language models. However, existing analyses are done in small models far from the state …
of language models. However, existing analyses are done in small models far from the state …
A survey on interpretable reinforcement learning
Although deep reinforcement learning has become a promising machine learning approach
for sequential decision-making problems, it is still not mature enough for high-stake domains …
for sequential decision-making problems, it is still not mature enough for high-stake domains …
Rethinking interpretability in the era of large language models
Interpretable machine learning has exploded as an area of interest over the last decade,
sparked by the rise of increasingly large datasets and deep neural networks …
sparked by the rise of increasingly large datasets and deep neural networks …
Towards best practices of activation patching in language models: Metrics and methods
Mechanistic interpretability seeks to understand the internal mechanisms of machine
learning models, where localization--identifying the important model components--is a key …
learning models, where localization--identifying the important model components--is a key …
Evaluating language models for mathematics through interactions
There is much excitement about the opportunity to harness the power of large language
models (LLMs) when building problem-solving assistants. However, the standard …
models (LLMs) when building problem-solving assistants. However, the standard …