answerdotai/ModernBERT-base
Fill-Mask
•
Updated
•
27.6k
•
437
Oleksandr Korovii
zeusfsx
AI & ML interests
NLP field
Recent Activity
liked
a model
5 days ago
answerdotai/ModernBERT-base
new activity
9 days ago
zeusfsx/title-instruction:Adding `safetensors` variant of this model
Organizations
None yet
zeusfsx's activity
liked
a
model
5 days ago
Adding `safetensors` variant of this model
#1 opened about 1 month ago
by
SFconvertbot
liked
a
dataset
3 months ago
upvoted
a
paper
6 months ago
liked
a
dataset
8 months ago
upvoted
an
article
8 months ago
Article
SetFit: Efficient Few-Shot Learning Without Prompts
•
20
upvoted
a
collection
8 months ago
liked
2
models
8 months ago
reacted to
santiviquez's
post with ❤️
10 months ago
Post
Eigenvalues to the rescue? 🛟🤔
I found out about this paper thanks to @gsarti 's post from last week; I got curious, so I want to post my take on it. 🤗
The paper proposes a new metric called EigenScore to detect LLM hallucinations. 📄
Their idea is that given an input question, they generate K different answers, take their internal embedding states, calculate a covariance matrix with them, and use it to calculate an EigenScore.
We can think of the EigenScore as the mean of the eigenvalues of the covariance matrix of the embedding space of the K-generated answers.
❓But why eigenvalues?
Well, if the K generations have similar semantics, the sentence embeddings will be highly correlated, and most eigenvalues will be close to 0.
On the other hand, if the LLM hallucinates, the K generations will have diverse semantics, and the eigenvalues will be significantly different from 0.
The idea is pretty neat and shows better results when compared to other methods like sequence probabilities, length-normalized entropy, and other uncertainty quantification-based methods.
💭 What I'm personally missing from the paper is that they don't compare their results with other methods like LLM-Eval and SelfcheckGPT. They do mention that EigenScore is much cheaper to implement than SelfcheckGPT, but that's all on the topic.
Paper: INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection (2402.03744)
I found out about this paper thanks to @gsarti 's post from last week; I got curious, so I want to post my take on it. 🤗
The paper proposes a new metric called EigenScore to detect LLM hallucinations. 📄
Their idea is that given an input question, they generate K different answers, take their internal embedding states, calculate a covariance matrix with them, and use it to calculate an EigenScore.
We can think of the EigenScore as the mean of the eigenvalues of the covariance matrix of the embedding space of the K-generated answers.
❓But why eigenvalues?
Well, if the K generations have similar semantics, the sentence embeddings will be highly correlated, and most eigenvalues will be close to 0.
On the other hand, if the LLM hallucinates, the K generations will have diverse semantics, and the eigenvalues will be significantly different from 0.
The idea is pretty neat and shows better results when compared to other methods like sequence probabilities, length-normalized entropy, and other uncertainty quantification-based methods.
💭 What I'm personally missing from the paper is that they don't compare their results with other methods like LLM-Eval and SelfcheckGPT. They do mention that EigenScore is much cheaper to implement than SelfcheckGPT, but that's all on the topic.
Paper: INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection (2402.03744)
liked
a
dataset
12 months ago
liked
a
model
about 1 year ago
Adding `safetensors` variant of this model
#2 opened over 1 year ago
by
SFconvertbot
updated
a
model
over 1 year ago
Adding `safetensors` variant of this model
#1 opened over 1 year ago
by
SFconvertbot
updated
a
dataset
over 1 year ago
liked
a
model
over 1 year ago
liked
a
dataset
over 1 year ago
updated
a
model
over 1 year ago
updated
a
dataset
over 1 year ago