Abhilasha Sancheti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Abhilasha Sancheti has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Rachel Rudinger
University of Maryland College Park USA
8 shared publications - Haozhe An
University of Maryland College Park
4 shared publications - Aparna Garimella
Adobe Research India
3 shared publications Balaji Srinivasan
Adobe Research
2 shared publicationsBalaji Vasan Srinivasan
Adobe Research
2 shared publications- Connor Baumler
University of Maryland College Park
2 shared publications
Latest Publications
- Open Access
On the Mutual Influence of Gender and Occupation in LLM Representations
We examine LLM representations of gender for first names in various occupational contexts to study how occupations and the gender perception of first names in LLMs influence each other mutually. We find that LLMs' first-name gender representations correlate with real-world gender statistics associated with the name, and are influenced by the co-occurrence of stereotypically feminine or masculine occupations. Additionally, we study the influence of first-name gender representations on LLMs in a downstream occupation prediction task and their potential as an internal metric to identify extrinsic model biases. While feminine first-name embeddings often raise the probabilities for female-dominated jobs (and vice versa for male-dominated jobs), reliably using these internal gender representations for bias detection remains challenging.
Open AccessOn the Mutual Influence of Gender and Occupation in LLM Representations
We examine LLM representations of gender for first names in various occupational contexts to study how occupations and the gender perception of first names in LLMs influence each other mutually. We find that LLMs' first-name gender representations correlate with real-world gender statistics associated with the name, and are influenced by the co-occurrence of stereotypically feminine or masculine occupations. Additionally, we study the influence of first-name gender representations on LLMs in a downstream occupation prediction task and their potential as an internal metric to identify extrinsic model biases. While feminine first-name embeddings often raise the probabilities for female-dominated jobs (and vice versa for male-dominated jobs), reliably using these internal gender representations for bias detection remains challenging.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 11680-11695
Less Mature is More Adaptable for Sentence-level Language Modeling
Abhilasha Sancheti, David Dale, Artyom Kozhevnikov, Maha Elbayad. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 11680-11695
Open AccessLess Mature is More Adaptable for Sentence-level Language Modeling
Abhilasha Sancheti, David Dale, Artyom Kozhevnikov, Maha Elbayad. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 1663-1680
On the Mutual Influence of Gender and Occupation in LLM Representations
Haozhe An, Connor Baumler, Abhilasha Sancheti, Rachel Rudinger. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 1663-1680
Open AccessOn the Mutual Influence of Gender and Occupation in LLM Representations
Haozhe An, Connor Baumler, Abhilasha Sancheti, Rachel Rudinger. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 64-82
Tracking Evolving Relationship Between Characters in Books in the Era of Large Language Models
Abhilasha Sancheti, Rachel Rudinger. Proceedings of the The 7th Workshop on Narrative Understanding. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 64-82
Open AccessTracking Evolving Relationship Between Characters in Books in the Era of Large Language Models
Abhilasha Sancheti, Rachel Rudinger. Proceedings of the The 7th Workshop on Narrative Understanding. 2025.
- Open Access
On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models
We study the presence of heteronormative biases and prejudice against interracial romantic relationships in large language models by performing controlled name-replacement experiments for the task of relationship prediction. We show that models are less likely to predict romantic relationships for (a) same-gender character pairs than different-gender pairs; and (b) intra/inter-racial character pairs involving Asian names as compared to Black, Hispanic, or White names. We examine the contextualized embeddings of first names and find that gender for Asian names is less discernible than non-Asian names. We discuss the social implications of our findings, underlining the need to prioritize the development of inclusive and equitable technology.
Open AccessOn the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models
We study the presence of heteronormative biases and prejudice against interracial romantic relationships in large language models by performing controlled name-replacement experiments for the task of relationship prediction. We show that models are less likely to predict romantic relationships for (a) same-gender character pairs than different-gender pairs; and (b) intra/inter-racial character pairs involving Asian names as compared to Black, Hispanic, or White names. We examine the contextualized embeddings of first names and find that gender for Asian names is less discernible than non-Asian names. We discuss the social implications of our findings, underlining the need to prioritize the development of inclusive and equitable technology.
- Open Access
How much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations?
In this paper, we assess the robustness (reliability) of ChatGPT under input perturbations for one of the most fundamental tasks of Information Extraction (IE) i.e. Named Entity Recognition (NER). Despite the hype, the majority of the researchers have vouched for its language understanding and generation capabilities; a little attention has been paid to understand its robustness: How the input-perturbations affect 1) the predictions, 2) the confidence of predictions and 3) the quality of rationale behind its prediction. We perform a systematic analysis of ChatGPT's robustness (under both zero-shot and few-shot setup) on two NER datasets using both automatic and human evaluation. Based on automatic evaluation metrics, we find that 1) ChatGPT is more brittle on Drug or Disease replacements (rare entities) compared to the perturbations on widely known Person or Location entities, 2) the quality of explanations for the same entity considerably differ under different types of "Entity-Specific" and "Context-Specific" perturbations and the quality can be significantly improved using in-context learning, and 3) it is overconfident for majority of the incorrect predictions, and hence it could lead to misguidance of the end-users.
Open AccessHow much reliable is ChatGPT's prediction on Information Extraction under Input Perturbations?
In this paper, we assess the robustness (reliability) of ChatGPT under input perturbations for one of the most fundamental tasks of Information Extraction (IE) i.e. Named Entity Recognition (NER). Despite the hype, the majority of the researchers have vouched for its language understanding and generation capabilities; a little attention has been paid to understand its robustness: How the input-perturbations affect 1) the predictions, 2) the confidence of predictions and 3) the quality of rationale behind its prediction. We perform a systematic analysis of ChatGPT's robustness (under both zero-shot and few-shot setup) on two NER datasets using both automatic and human evaluation. Based on automatic evaluation metrics, we find that 1) ChatGPT is more brittle on Drug or Disease replacements (rare entities) compared to the perturbations on widely known Person or Location entities, 2) the quality of explanations for the same entity considerably differ under different types of "Entity-Specific" and "Context-Specific" perturbations and the quality can be significantly improved using in-context learning, and 3) it is overconfident for majority of the incorrect predictions, and hence it could lead to misguidance of the end-users.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 479-494
On the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models
Abhilasha Sancheti, Haozhe An, Rachel Rudinger. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 479-494
Open AccessOn the Influence of Gender and Race in Romantic Relationship Prediction from Large Language Models
Abhilasha Sancheti, Haozhe An, Rachel Rudinger. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.
- Open Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 49-57
Post-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges
Abhilasha Sancheti, Koustava Goswami, Balaji Srinivasan. Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 49-57
Open AccessPost-Hoc Answer Attribution for Grounded and Trustworthy Long Document Comprehension: Task, Insights, and Challenges
Abhilasha Sancheti, Koustava Goswami, Balaji Srinivasan. Proceedings of the 13th Joint Conference on Lexical and Computational Semantics (*SEM 2024). 2024.
- Open Access
What to Read in a Contract? Party-Specific Summarization of Legal Obligations, Entitlements, and Prohibitions
Reviewing and comprehending key obligations, entitlements, and prohibitions in legal contracts can be a tedious task due to their length and domain-specificity. Furthermore, the key rights and duties requiring review vary for each contracting party. In this work, we propose a new task of party-specific extractive summarization for legal contracts to facilitate faster reviewing and improved comprehension of rights and duties. To facilitate this, we curate a dataset comprising of party-specific pairwise importance comparisons annotated by legal experts, covering ~293K sentence pairs that include obligations, entitlements, and prohibitions extracted from lease agreements. Using this dataset, we train a pairwise importance ranker and propose a pipeline-based extractive summarization system that generates a party-specific contract summary. We establish the need for incorporating domain-specific notion of importance during summarization by comparing our system against various baselines using both automatic and human evaluation methods
Open AccessWhat to Read in a Contract? Party-Specific Summarization of Legal Obligations, Entitlements, and Prohibitions
Reviewing and comprehending key obligations, entitlements, and prohibitions in legal contracts can be a tedious task due to their length and domain-specificity. Furthermore, the key rights and duties requiring review vary for each contracting party. In this work, we propose a new task of party-specific extractive summarization for legal contracts to facilitate faster reviewing and improved comprehension of rights and duties. To facilitate this, we curate a dataset comprising of party-specific pairwise importance comparisons annotated by legal experts, covering ~293K sentence pairs that include obligations, entitlements, and prohibitions extracted from lease agreements. Using this dataset, we train a pairwise importance ranker and propose a pipeline-based extractive summarization system that generates a party-specific contract summary. We establish the need for incorporating domain-specific notion of importance during summarization by comparing our system against various baselines using both automatic and human evaluation methods
- Open Access
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 14708-14725
What to Read in a Contract? Party-Specific Summarization of Legal Obligations, Entitlements, and Prohibitions
Abhilasha Sancheti, Aparna Garimella, Balaji Srinivasan, Rachel Rudinger. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.
- 1 January 2023
- Published by Association for Computational Linguistics (ACL)
- p. 14708-14725
Open AccessWhat to Read in a Contract? Party-Specific Summarization of Legal Obligations, Entitlements, and Prohibitions
Abhilasha Sancheti, Aparna Garimella, Balaji Srinivasan, Rachel Rudinger. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.