InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain?

Recent advancements in language technology and Artificial Intelligence have resulted in numerous Language Models being proposed to perform various tasks in the legal domain ranging from predicting judgments to generating summaries. Despite their immense potential, these models have been proven to learn and exhibit societal biases and make unfair predictions. In this study, we explore the ability of Large Language Models (LLMs) to perform legal tasks in the Indian landscape when social factors are involved. We present a novel metric, $\beta$-weighted $\textit{Legal Safety Score ($LSS_{\beta}$)}$, which encapsulates both the fairness and accuracy aspects of the LLM. We assess LLMs' safety by considering its performance in the $\textit{Binary Statutory Reasoning}$ task and its fairness exhibition with respect to various axes of disparities in the Indian society. Task performance and fairness scores of LLaMA and LLaMA--2 models indicate that the proposed $LSS_{\beta}$ metric can effectively determine the readiness of a model for safe usage in the legal sector. We also propose finetuning pipelines, utilising specialised legal datasets, as a potential method to mitigate bias and improve model safety. The finetuning procedures on LLaMA and LLaMA--2 models increase the $LSS_{\beta}$, improving their usability in the Indian legal domain. Our code is publicly released.

RE-GAINS & EnCHANT: Intelligent Tool Manipulation Systems For Enhanced Query Responses

Despite the remarkable success of LLMs, they still suffer from tool invocation and tool chaining due to inadequate input queries and/or tool argument descriptions. We propose two novel frameworks, RE-GAINS and EnCHANT, enabling LLMs to tackle tool manipulation for solving complex user queries by making API calls. EnCHANT is an open-source solution that makes use of an LLM format enforcer, an LLM(OpenChat 3.5) and a retriever(ToolBench's API Retriever). RE-GAINS is based on OpenAI models and embeddings using a special prompt based on the RAP paper. Both solutions cost less than $0.01 per query with minimal latency, therefore showcasing the usefulness of the frameworks.

Identifying and examining machine learning biases on Adult dataset

This research delves into the reduction of machine learning model bias through Ensemble Learning. Our rigorous methodology comprehensively assesses bias across various categorical variables, ultimately revealing a pronounced gender attribute bias. The empirical evidence unveils a substantial gender-based wage prediction disparity: wages predicted for males, initially at \$902.91, significantly decrease to \$774.31 when the gender attribute is alternated to females. Notably, Kullback-Leibler divergence scores point to gender bias, with values exceeding 0.13, predominantly within tree-based models. Employing Ensemble Learning elucidates the quest for fairness and transparency. Intriguingly, our findings reveal that the stacked model aligns with individual models, confirming the resilience of model bias. This study underscores ethical considerations and advocates the implementation of hybrid models for a data-driven society marked by impartiality and inclusivity.

Are Models Trained on Indian Legal Data Fair?

Recent advances and applications of language technology and artificial intelligence have enabled much success across multiple domains like law, medical and mental health. AI-based Language Models, like Judgement Prediction, have recently been proposed for the legal sector. However, these models are strife with encoded social biases picked up from the training data. While bias and fairness have been studied across NLP, most studies primarily locate themselves within a Western context. In this work, we present an initial investigation of fairness from the Indian perspective in the legal domain. We highlight the propagation of learnt algorithmic biases in the bail prediction task for models trained on Hindi legal documents. We evaluate the fairness gap using demographic parity and show that a decision tree model trained for the bail prediction task has an overall fairness disparity of 0.237 between input features associated with Hindus and Muslims. Additionally, we highlight the need for further research and studies in the avenues of fairness/bias in applying AI in the legal sector with a specific focus on the Indian context.