The BrowserGym Ecosystem for Web Agent Research
Paper
•
2412.05467
•
Published
•
20
Siva Reddy
sivareddyg
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
15 days ago
The BrowserGym Ecosystem for Web Agent Research
upvoted
a
paper
15 days ago
BM25S: Orders of magnitude faster lexical search via eager sparse
scoring
liked
a Space
7 months ago
mteb/arena
Organizations
sivareddyg's activity
upvoted
2
papers
15 days ago
liked
a
Space
7 months ago
upvoted
a
paper
8 months ago
authored
a
paper
11 months ago
updated
2
collections
about 1 year ago
reacted to
gsarti's
post with 👍
about 1 year ago
Post
🔍 Today's pick in Interpretability & Analysis of LMs: Can Large Language Models Explain Themselves? by
@andreasmadsen
Sarath Chandar &
@sivareddyg
LLMs can provide wrong but convincing explanations for their behavior, and this might lead to ill-placed confidence in their predictions. This study uses self-consistency checks to measure the faithfulness of LLM explanations: if an LLM says a set of words is important for making a prediction, then it should not be able to make the same prediction without these words. Results demonstrate that LLM self-explanations faithfulness of self-explanations cannot be reliably trusted, as they prove to be very task and model dependent, with bigger model generally producing more faithful explanations.
📄 Paper: Can Large Language Models Explain Themselves? (2401.07927)
LLMs can provide wrong but convincing explanations for their behavior, and this might lead to ill-placed confidence in their predictions. This study uses self-consistency checks to measure the faithfulness of LLM explanations: if an LLM says a set of words is important for making a prediction, then it should not be able to make the same prediction without these words. Results demonstrate that LLM self-explanations faithfulness of self-explanations cannot be reliably trusted, as they prove to be very task and model dependent, with bigger model generally producing more faithful explanations.
📄 Paper: Can Large Language Models Explain Themselves? (2401.07927)
- 1 reply