Search

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.

Emotion Recognition in Conversations (ERC) is a critical aspect of affective computing, and it has many practical applications in healthcare, education, chatbots, and social media platforms. Earlier approaches for ERC analysis involved modeling both speaker and long-term contextual information using graph neural network architectures. However, it is ideal to deploy speaker-independent models for real-world applications. Additionally, long context windows can potentially create confusion in recognizing the emotion of an utterance in a conversation. To overcome these limitations, we propose novel line conversation graph convolutional network (LineConGCN) and graph attention (LineConGAT) models for ERC analysis. These models are speaker-independent and built using a graph construction strategy for conversations -- line conversation graphs (LineConGraphs). The conversational context in LineConGraphs is short-term -- limited to one previous and future utterance, and speaker information is not part of the graph. We evaluate the performance of our proposed models on two benchmark datasets, IEMOCAP and MELD, and show that our LineConGAT model outperforms the state-of-the-art methods with an F1-score of 64.58% and 76.50%. Moreover, we demonstrate that embedding sentiment shift information into line conversation graphs further enhances the ERC performance in the case of GCN models., Comment: 13 pages, 6 figures

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., Comment: Presented at the Symposium on AI and Law (SAIL) 2023

BaTiO3 is typically a strong n-type material with tuneable optoelectronic properties via doping and controlling the synthesis conditions. It has a wide band gap that can only harness the ultraviolet region of the solar spectrum. Despite significant progress, achieving visible-light absorbing BTO with tuneable carrier concentration has been challenging, a crucial requirement for many applications. In this work, a p-type BTO with visible-light absorption is realized via iridium doping. Detailed analysis using advanced spectroscopy tools and computational electronic structure analysis is used to rationalize the n- to p-type transition after Ir doping. Results offered mechanistic insight into the interplay between the dopant site occupancy, the dopant position within the band gap, and the defect chemistry affecting the carrier concentration. A decrease in the Ti3+ donor levels concentration and the mutually correlated oxygen vacancies upon Ir doping is attributed to the p-type behavior. Due to the formation of Ir3+ or Ir4+ in-gap energy levels within the forbidden region, the optical transition can be elicited from or to such levels resulting in visible-light absorption. This newly developed Ir-doped BTO can be a promising p-type perovskite-oxide with imminent applications in solar fuel generation, spintronics and optoelectronics., Comment: 21 pages, 8 figures

During a pandemic, contact tracing is an essential tool to drive down the infection rate within a population. To accelerate the laborious manual contact tracing process, digital contact tracing (DCT) tools can track contact events transparently and privately by using the sensing and signaling capabilities of the ubiquitous cell phone. However, an effective DCT must not only preserve user privacy but also augment the existing manual contact tracing process. Indeed, not every member of a population may own a cell phone or have a DCT app installed and enabled. We present KHOVID to fulfill the combined goal of manual contact-tracing interoperability and DCT user privacy. At KHOVID's core is a privacy-friendly mechanism to encode user trajectories using geolocation data. Manual contact tracing data can be integrated through the same geolocation format. The accuracy of the geolocation data from DCT is improved using Bluetooth proximity detection, and we propose a novel method to encode Bluetooth ephemeral IDs. This contribution describes the detailed design of KHOVID; presents a prototype implementation including an app and server software; and presents a validation based on simulation and field experiments. We also compare the strengths of KHOVID with other, earlier proposals of DCT., Comment: 14 pages, 7 figures. Submitted to a conference

Existing Clinical Decision Support Systems (CDSSs) largely depend on the availability of structured patient data and Electronic Health Records (EHRs) to aid caregivers. However, in case of hospitals in developing countries, structured patient data formats are not widely adopted, where medical professionals still rely on clinical notes in the form of unstructured text. Such unstructured clinical notes recorded by medical personnel can also be a potential source of rich patient-specific information which can be leveraged to build CDSSs, even for hospitals in developing countries. If such unstructured clinical text can be used, the manual and time-consuming process of EHR generation will no longer be required, with huge person-hours and cost savings. In this paper, we propose a generic ICD9 disease group prediction CDSS built on unstructured physician notes modeled using hybrid word embeddings. These word embeddings are used to train a deep neural network for effectively predicting ICD9 disease groups. Experimental evaluation showed that the proposed approach outperformed the state-of-the-art disease group prediction model built on structured EHRs by 15% in terms of AUROC and 40% in terms of AUPRC, thus proving our hypothesis and eliminating dependency on availability of structured patient data., Comment: Submitted to the International Conference on Computational Science (ICCS) 2020

We present a theoretical description of the influence of misfit strain on mobile defects dynamics in thin strained ferroelectric films. Self-consistent solutions obtained by coupling the Poissons equation for electric potential with continuity equations for mobile donor and electron concentrations and time-dependent Landau-Ginzburg-Devonshire equations reveal that the Vegard mechanism (chemical pressure) leads to the redistribution of both charged and electro-neutral defects in order to decrease the effective stress in the film. Internal electric fields, both built-in and depolarization ones, lead to a strong accumulation of screening space charges (charged defects and electrons) near the film interfaces. Importantly, the corresponding screening length is governed by the misfit strain and Vegard coefficient. Mobile defects dynamics, kinetics of polarization and electric current reversal are defined by the complex interplay between the donor, electron and phonon relaxation times, misfit strain, finite size effect and Vegard stresses., Comment: 34 pages, 7 figures, supplementary materials

Among all the theories proposed to explain the 'anomalous' perihelion precession of Mercury's orbit announced in 1859 by Le Verrier, the general theory of relativity proposed by Einstein in November 1915, alone could calculate Mercury's 'anomalous' precession with a precision demanded by observational accuracy. Since Mercury's precession was a directly derived result of the full general theory, it was viewed by Einstein as the most critical test of general relativity, amongst the three tests proposed by him. With the advent of the space age, the observational accuracy level has improved further and it became possible to detect this precession for other planetary orbits of the solar system -- viz., Venus and the Earth. This conclusively proved that the phenomenon of 'anomalous' perihelion precession of planetary orbits is really a relativistic effect. Our previous papers presented the mathematical model and the computed value of the relativistic perihelion precession of Mercury's orbit using an alternate relativistic gravitational model, which is a remodeled form of Einstein's relativity theories, and which retained only experimentally proven principles and has been enriched by the benefits of almost a century-long relativity experimentation including the space age experiments. Using this model, we present in this paper the computed values of the relativistic precession of Venus and the Earth, which compare well with the predictions of general relativity and also are in agreement with the observed values within the range of uncertainty., Comment: 3 pages

This article provides an assessment of the causal effect of customer relationship management (CRM) applications on one-to-one marketing effectiveness. We use a potential outcomes based propensity score approach to assess this causal effect. We find that firms using CRM systems have greater levels of one-to-one marketing effectiveness. We discuss the strengths and challenges of using the propensity score approach to design and execute CRM related observational studies. We also discuss the applicability of the framework in this paper to study typical causal questions in business and electronic commerce research at the firm, individual and economy levels, and to clarify the assumptions that researchers must make to infer causality from observational data., Comment: Published at http://dx.doi.org/10.1214/088342306000000213 in the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)