Angana Borah
@AnganaBorah2
Followers
191
Following
647
Media
24
Statuses
118
2nd year Ph.D. @UMichCSE 〽️ advised by @radamihalcea. LLMs, Agents, Culture, Bias& Misinfo | Intern @AmazonAlexa. Prev @GeorgiaTech, @UTAustin, @DFKI, @LstSaar
Joined June 2022
Do LLMs exhibit belief-based biases like humans do?. We examine the presence of belief congruence in multi-agent systems and find that LLMs exhibit even stronger belief congruence than humans. Paper: Code: .🧵(1/n)
1
9
36
RT @ZhijingJin: 🏛️Can we trust #LLMs to value democracy? 🎉Check our paper "Democratic or Authoritarian? Probing a New Dimension of Politica….
0
11
0
RT @zkjzou: 🔥 Excited to introduce ManyICLBench (ACL 2025).🧐 Do many-shot ICL tasks evaluate LCLMs' ability to retrieve the most similar ex….
0
17
0
RT @JieRuan75: 🔍LLMs now give medical diagnoses, legal advice, and even tackle scientific problems. ❓Your LLM sounds smart. But what if it….
0
19
0
RT @ZhijingJin: Really excited about our recent large collaboration work on NLP for Social Good. The work stems from our discussions at the….
0
23
0
RT @radamihalcea: Those of you in Ann Arbor: why not do “AI & dinner” tonight? With the flurry of AI tools coming out any day, chances are….
0
1
0
RT @radamihalcea: Very proud of all of Do June’s accomplishments, all the way to his successful PhD defense this week! 🎓👏 He not only devel….
0
3
0
0
0
4
RT @Elenal3ai: 🚨 New paper alert 🚨. Ever asked an LLM-as-Marilyn Monroe who the US president was in 2000? 🤔 Should the LLM answer at all? W….
0
10
0
1
0
4
🗣️I will discuss the following papers: .Cross-Cultural Awareness - Implicit biases - Persuasion and Misinformation -
1
0
6
Excited to present some of our work on “Agentic AI ecosystems: Navigating cross-cultural awareness, biases and misinformation in multi-agent LLM and human-LLM interactions” tomorrow 8am ET at MSR Africa and AI4Good seminar! 🤗🌍.More details here:
1
8
28
RT @michigan_AI: 🎙️WEDNESDAY at #AAMAS2025, don't miss Prof. @radamihalcea's keynote, focused on exploring the evolving relationship betwee….
0
1
0
RT @OanaIgnatRo: Check out the BRIGHTER dataset -- Human-Annotated Textual Emotion Recognition for 28 Languages. I hope to see all the amaz….
0
3
0
It was also great to be a part of the selected authors panel to discuss several open questions around cultural alignment, biases, and LLMs. Thank you so much to the organizers. I had a great time learning from so many amazing keynotes and participants!
0
0
9
So honored to have won the Outstanding Paper award at @c3_nlp today. ❤️.Many thanks to my wonderful collaborators @AparnaGarimell2 and @radamihalcea! What an amazing way to end #NAACL2025! 😊
Excited to present our paper on cross-cultural bias evaluation at @c3_nlp 🌎 co-located with #NAACL2025. I am presenting today (4/5) orally at 2:15pm MT (Pecos) and at the poster session at 3:30pm MT. Paper link: .Workshop page:
5
9
44
RT @OanaIgnatRo: Super excited to win the Best Paper Award @c3_nlp #NAACL2025 with @GGaneshL and @radamihalcea! Cross-cultural AI is a rese….
0
10
0
RT @OanaIgnatRo: Presenting this at @c3_nlp today #NAACL2025 in a short talk (2:15) and poster (4:15). Come say hi 😊.
0
3
0
Excited to present our paper on cross-cultural bias evaluation at @c3_nlp 🌎 co-located with #NAACL2025. I am presenting today (4/5) orally at 2:15pm MT (Pecos) and at the poster session at 3:30pm MT. Paper link: .Workshop page:
Current gender bias evaluation metrics like WEAT assume bias dimensions such as “family-career” hold universally. But do they? .In our recent work “Towards Region-aware Bias Evaluation Metrics”, we explore cross-cultural differences in gender bias metrics.
0
7
29
RT @radamihalcea: 🌎Really honored to give one of the keynote talks at #NAACL2025, and speak about the power of learning from many cultures….
0
16
0
RT @radamihalcea: Very proud of my lab’s work to be presented at #NAACL2025, all aligned with this year’s special theme on NLP in a multicu….
0
7
0