• Sign in
  • Sign up
Elektrine
EN
Log in Register
Modes
Overview Chat Timeline Communities Gallery Lists Friends Email Vault DNS VPN
Back to Timeline
  • Open on mastodon.social

Nazneen Rajani

@nazneenrajani@mastodon.social
mastodon 4.6.0-nightly.2026-04-17

Research Lead @huggingface@mastodon.social

https://www.nazneenrajani.com/

0 Followers
0 Following
Joined October 28, 2022

Posts

Open post
nazneenrajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
Nazneen Rajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
@nazneenrajani@mastodon.social · Jan 24, 2023

Did you know there are other dialog agents like ChatGPT?

And what if I told you the secret sauce is IFT, RLHF, CoT, and SFT.

Wait, what? 😱

We explain each of these terms and why they are relevant to ChatGPT by comparing with 4 other dialog agents.

We discuss what's been done and what remains to be shown as next steps for these dialog agents.

So if you are curious, check out our blog: https://huggingface.co/blog/dialog-agents

Work done with the dream team Nathan Lambert Victor Sanh and Thomas Wolf 🤗

View on mastodon.social
What Makes a Dialog Agent Useful?
huggingface.co

What Makes a Dialog Agent Useful?

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

2
1
2
0
Open post
In reply to
nazneenrajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
Nazneen Rajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
@nazneenrajani@mastodon.social · Nov 11, 2022
@lasha_nlp we are using in-context learning for labeling, so I'd imagine that linguistic phenomena would not be straightforward for LLMs to label. But I think maybe chain-of-thought could possibly help here? 🤔
View full thread on mastodon.social
1
0
0
0
Open post
In reply to
nazneenrajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
Nazneen Rajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
@nazneenrajani@mastodon.social · Nov 10, 2022
Joint work with @liang_weixin , Lingjiao Chen, @mmitchell_ai and @james_y_zou
View full thread on mastodon.social
0
0
0
0
Open post
In reply to
nazneenrajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
Nazneen Rajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
@nazneenrajani@mastodon.social · Nov 10, 2022
3 & 4: use LLMs for generating semantic labels and visual features. 🦭Interface showing high-error groups for distilbert evaluated on the yelp dataset. (a) ex from the dataset in the high-error groups (sorted by loss), (b) tokens in high-error groups relative to the entire eval set, (c) 2d viz of model embeddings showing groups of errors in color. Paper: https://arxiv.org/abs/2210.05839 Space: https://huggingface.co/spaces/nazneen/seal Screencast: https://vimeo.com/736659216
View full thread on mastodon.social
0
1
2
0
Open post
nazneenrajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
Nazneen Rajani
Nazneen Rajani
@nazneenrajani@mastodon.social

Research Lead @ huggingface https://www. nazneenrajani.com/

mastodon.social
@nazneenrajani@mastodon.social · Nov 10, 2022

Our paper on Systematic Error Analysis and Labeling (SEAL) 🦭 has been accepted at EMNLP demo track 🎉

Problem: How can we help users find systematic bugs in their models?

Eg: Image classification model on low light images, sentiment classifier on gym reviews

Intuition: There are patterns to model failures. Can we extract those and give them natural language descriptions?

1 & 2: extract the model embeddings and cluster points with high-loss.

View on mastodon.social
3
2
2
0

Media

313k7r1n3

Company

  • About
  • Contact
  • FAQ

Legal

  • Terms of Service
  • Privacy Policy
  • VPN Policy

Email Settings

IMAP: mail.elektrine.com:993

POP3: pop3.elektrine.com:995

SMTP: mail.elektrine.com:465

SSL/TLS required

Support

  • support@elektrine.com
  • Report Security Issue

Connect

Tor Hidden Service

khav7sdajxu6om3arvglevskg2vwuy7luyjcwfwg6xnkd7qtskr2vhad.onion
© 2026 Elektrine. All rights reserved. • Server: 18:34:37 UTC