Anubrata Das @ NAACL 2025
@anubrata.bsky.social
Ah that makes sense! Thanks, yeah I am on that slack, hhh!
August 27, 2025 at 2:06 PM
Ah that makes sense! Thanks, yeah I am on that slack, hhh!
How can I get an invite for the XAI discord?
August 27, 2025 at 1:12 PM
How can I get an invite for the XAI discord?
Thank you for making the list, could you please add me?
July 29, 2025 at 1:31 PM
Thank you for making the list, could you please add me?
McCombs article: news.mccombs.utexas.edu/research/to-...
Paper url: doi.org/10.47989/ir3...
@utaustin.bsky.social
@texasscience.bsky.social
@engagingnews.bsky.social
@utischool.bsky.social
#TexasAI
#YearofAI
Paper url: doi.org/10.47989/ir3...
@utaustin.bsky.social
@texasscience.bsky.social
@engagingnews.bsky.social
@utischool.bsky.social
#TexasAI
#YearofAI
To Spot Toxic Speech Online, Try AI - McCombs News and Magazine
A new tool helps balance accuracy with fairness toward all groups in social media
news.mccombs.utexas.edu
June 6, 2025 at 3:10 PM
Session detail:
Poster Session 5 - IAM: Interpretability and Analysis of Models for NLP, Hall 3
Poster Session 5 - IAM: Interpretability and Analysis of Models for NLP, Hall 3
May 1, 2025 at 5:27 AM
Session detail:
Poster Session 5 - IAM: Interpretability and Analysis of Models for NLP, Hall 3
Poster Session 5 - IAM: Interpretability and Analysis of Models for NLP, Hall 3
This is a collaborative work with Manoj Kumar, Ninareh Mehrabi, Anil Ramakrishna, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Morteza Ziyadi, Rahul Gupta
May 1, 2025 at 5:26 AM
This is a collaborative work with Manoj Kumar, Ninareh Mehrabi, Anil Ramakrishna, Anna Rumshisky, Kai-Wei Chang, Aram Galstyan, Morteza Ziyadi, Rahul Gupta
Causal tracing informed edits provide a better detoxification-degeneration trade-off.
May 1, 2025 at 5:25 AM
Causal tracing informed edits provide a better detoxification-degeneration trade-off.
Model editing helps reduce toxicity. High detoxification can be achieved by simply editing random MLP layers. However, this leads to degeneration and increased perplexity.
May 1, 2025 at 5:25 AM
Model editing helps reduce toxicity. High detoxification can be achieved by simply editing random MLP layers. However, this leads to degeneration and increased perplexity.
We find evidence of toxic memory in the early layer of GPT-2 XL for innocuous-looking adversarial prompts.
May 1, 2025 at 5:25 AM
We find evidence of toxic memory in the early layer of GPT-2 XL for innocuous-looking adversarial prompts.
Paper: On Localizing and Deleting Toxic Memories in Large Language Models
Anthology URL: aclanthology.org/2025.finding...
Anthology URL: aclanthology.org/2025.finding...
aclanthology.org
May 1, 2025 at 5:24 AM
Paper: On Localizing and Deleting Toxic Memories in Large Language Models
Anthology URL: aclanthology.org/2025.finding...
Anthology URL: aclanthology.org/2025.finding...
Right, sorry for being unclear. I saw your comment sharing the Qualtrics integration tutorial with a video. bsky.app/profile/dggo...
Tom Costello ( @tomcostello.bsky.social ) has made freely available tools that let you build LLM interaction into Qualtrics
publish.obsidian.md/qualtrics-do...
publish.obsidian.md/qualtrics-do...
Home - Obsidian Publish
Request If you use our template (.QSF) to set up your research, we would appreciate it if you cite our paper when describing your method: Durably reducing conspiracy beliefs through dialogues with AI…
publish.obsidian.md
November 25, 2024 at 9:33 PM
Right, sorry for being unclear. I saw your comment sharing the Qualtrics integration tutorial with a video. bsky.app/profile/dggo...