Anindita Sinha Banerjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Anindita Sinha Banerjee has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Girish Keshav Palshikar
TCS Research Tata Consultancy Services Limited India
2 shared publications - Nitin Ramrakhiyani
TCS Research, Tata Consultancy Services Limited, Pune, India
2 shared publications - Sachin Pawar
TCS Research, Tata Consultancy Services Limited, Pune, India
2 shared publications - Basit Ali
TCS Research, Tata Consultancy Services Limited, Pune, India
1 shared publication - Basit Ali
TCS Research Tata Consultancy Services Limited India
1 shared publication
Latest Publications
- 10 August 2026
- Published by Springer Nature in Artificial Intelligence and Law
- p. 1-32
Explainable Statute Prediction via Attention-based Model and LLM Prompting
- 10 August 2026
- Published by Springer Nature in Artificial Intelligence and Law
- p. 1-32
Explainable Statute Prediction via Attention-based Model and LLM Prompting
- Open Access
Explainable Statute Prediction via Attention-based Model and LLM Prompting
In this paper, we explore the problem of automatic statute prediction where for a given case description, a subset of relevant statutes are to be predicted. Here, the term "statute" refers to a section, a sub-section, or an article of any specific Act. Addressing this problem would be useful in several applications such as AI-assistant for lawyers and legal question answering system. For better user acceptance of such Legal AI systems, we believe the predictions should also be accompanied by human understandable explanations. We propose two techniques for addressing this problem of statute prediction with explanations -- (i) AoS (Attention-over-Sentences) which uses attention over sentences in a case description to predict statutes relevant for it and (ii) LLMPrompt which prompts an LLM to predict as well as explain relevance of a certain statute. AoS uses smaller language models, specifically sentence transformers and is trained in a supervised manner whereas LLMPrompt uses larger language models in a zero-shot manner and explores both standard as well as Chain-of-Thought (CoT) prompting techniques. Both these models produce explanations for their predictions in human understandable forms. We compare statute prediction performance of both the proposed techniques with each other as well as with a set of competent baselines, across two popular datasets. Also, we evaluate the quality of the generated explanations through an automated counter-factual manner as well as through human evaluation.
Open AccessExplainable Statute Prediction via Attention-based Model and LLM Prompting
In this paper, we explore the problem of automatic statute prediction where for a given case description, a subset of relevant statutes are to be predicted. Here, the term "statute" refers to a section, a sub-section, or an article of any specific Act. Addressing this problem would be useful in several applications such as AI-assistant for lawyers and legal question answering system. For better user acceptance of such Legal AI systems, we believe the predictions should also be accompanied by human understandable explanations. We propose two techniques for addressing this problem of statute prediction with explanations -- (i) AoS (Attention-over-Sentences) which uses attention over sentences in a case description to predict statutes relevant for it and (ii) LLMPrompt which prompts an LLM to predict as well as explain relevance of a certain statute. AoS uses smaller language models, specifically sentence transformers and is trained in a supervised manner whereas LLMPrompt uses larger language models in a zero-shot manner and explores both standard as well as Chain-of-Thought (CoT) prompting techniques. Both these models produce explanations for their predictions in human understandable forms. We compare statute prediction performance of both the proposed techniques with each other as well as with a set of competent baselines, across two popular datasets. Also, we evaluate the quality of the generated explanations through an automated counter-factual manner as well as through human evaluation.