Angana Borah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Angana Borah has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Rada Mihalcea
University of Michigan, Ann Arbor, MI, USA
3 shared publications - Amit Awekar
Indian Institute of Technology Guwahati INDIA
1 shared publication - Aparna Garimella
Adobe Research India
1 shared publication - Marwa Houalla
University of Michigan Ann Arbor USA
1 shared publication Rada Mihalcea
University of Michigan Ann Arbor USA
1 shared publication- Rohit Raj Rai
Indian Institute of Technology Guwahati INDIA
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18441-18463
Mind the (Belief) Gap: Group Identity in the World of LLMs
Angana Borah, Marwa Houalla, Rada Mihalcea. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 18441-18463
Open AccessMind the (Belief) Gap: Group Identity in the World of LLMs
Angana Borah, Marwa Houalla, Rada Mihalcea. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 108-131
Towards Region-aware Bias Evaluation Metrics
Angana Borah, Aparna Garimella, Rada Mihalcea. Proceedings of the 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP 2025). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 108-131
Open AccessTowards Region-aware Bias Evaluation Metrics
Angana Borah, Aparna Garimella, Rada Mihalcea. Proceedings of the 3rd Workshop on Cross-Cultural Considerations in NLP (C3NLP 2025). 2025.
- Open Access
Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions
As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to human-generated data. Given that LLMs are being used to gain insights into various societal aspects, it is essential to mitigate these biases. To that end, our study investigates the presence of implicit gender biases in multi-agent LLM interactions and proposes two strategies to mitigate these biases. We begin by creating a dataset of scenarios where implicit gender biases might arise, and subsequently develop a metric to assess the presence of biases. Our empirical analysis reveals that LLMs generate outputs characterized by strong implicit bias associations (>= 50\% of the time). Furthermore, these biases tend to escalate following multi-agent interactions. To mitigate them, we propose two strategies: self-reflection with in-context examples (ICE); and supervised fine-tuning. Our research demonstrates that both methods effectively mitigate implicit biases, with the ensemble of fine-tuning and self-reflection proving to be the most successful.
Open AccessTowards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions
As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs are susceptible to societal biases due to their exposure to human-generated data. Given that LLMs are being used to gain insights into various societal aspects, it is essential to mitigate these biases. To that end, our study investigates the presence of implicit gender biases in multi-agent LLM interactions and proposes two strategies to mitigate these biases. We begin by creating a dataset of scenarios where implicit gender biases might arise, and subsequently develop a metric to assess the presence of biases. Our empirical analysis reveals that LLMs generate outputs characterized by strong implicit bias associations (>= 50\% of the time). Furthermore, these biases tend to escalate following multi-agent interactions. To mitigate them, we propose two strategies: self-reflection with in-context examples (ICE); and supervised fine-tuning. Our research demonstrates that both methods effectively mitigate implicit biases, with the ensemble of fine-tuning and self-reflection proving to be the most successful.
- Open Access
Application Specific Compression of Deep Learning Models
Large Deep Learning models are compressed and deployed for specific applications. However, current Deep Learning model compression methods do not utilize the information about the target application. As a result, the compressed models are application agnostic. Our goal is to customize the model compression process to create a compressed model that will perform better for the target application. Our method, Application Specific Compression (ASC), identifies and prunes components of the large Deep Learning model that are redundant specifically for the given target application. The intuition of our work is to prune the parts of the network that do not contribute significantly to updating the data representation for the given application. We have experimented with the BERT family of models for three applications: Extractive QA, Natural Language Inference, and Paraphrase Identification. We observe that customized compressed models created using ASC method perform better than existing model compression methods and off-the-shelf compressed models.
Open AccessApplication Specific Compression of Deep Learning Models
Large Deep Learning models are compressed and deployed for specific applications. However, current Deep Learning model compression methods do not utilize the information about the target application. As a result, the compressed models are application agnostic. Our goal is to customize the model compression process to create a compressed model that will perform better for the target application. Our method, Application Specific Compression (ASC), identifies and prunes components of the large Deep Learning model that are redundant specifically for the given target application. The intuition of our work is to prune the parts of the network that do not contribute significantly to updating the data representation for the given application. We have experimented with the BERT family of models for three applications: Extractive QA, Natural Language Inference, and Paraphrase Identification. We observe that customized compressed models created using ASC method perform better than existing model compression methods and off-the-shelf compressed models.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 9306-9326
Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions
Angana Borah, Rada Mihalcea. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 9306-9326
Open AccessTowards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions
Angana Borah, Rada Mihalcea. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.