Although the rise of Large Language Models (LLMs) in enterprise settings brings new opportunities and capabilities, it also brings challenges, such as the risk of generating inappropriate, biased, or misleading content that violates regulations and can have legal concerns. To alleviate this, we present "LLMGuard", a tool that monitors user interactions with an LLM application and flags content against specific behaviours or conversation topics. To do this robustly, LLMGuard employs an ensemble of detectors.

Machine learning and deep learning-based decision making has become part of today's software. The goal of this work is to ensure that machine learning and deep learning-based systems are as trusted as traditional software. Traditional software is made dependable by following rigorous practice like static analysis, testing, debugging, verifying, and repairing throughout the development and maintenance life-cycle. Similarly for machine learning systems, we need to keep these models up to date so that their performance is not compromised. For this, current systems rely on scheduled re-training of these models as new data kicks in. In this work, we propose DetAIL, a tool to measure the data drift that takes place when new data kicks in so that one can adaptively re-train the models whenever re-training is actually required irrespective of schedules. In addition to that, we generate various explanations at sentence level and dataset level to capture why a given payload text has drifted.

Machine Learning has seen tremendous growth recently, which has led to a larger adaptation of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. The trustworthiness of ML and NLP systems is a crucial aspect and requires a guarantee that the decisions they make are fair and robust. Aligned with this, we propose a novel framework GYC, to generate a set of exhaustive counterfactual text, which are crucial for testing these ML systems. Our main contributions include a) We introduce GYC, a framework to generate counterfactual samples such that the generation is plausible, diverse, goal-oriented, and effective, b) We generate counterfactual samples, that can direct the generation towards a corresponding \texttt{condition} such as named-entity tag, semantic role label, or sentiment. Our experimental results on various domains show that GYC generates counterfactual text samples exhibiting the above four properties. GYC generates counterfactuals that can act as test cases to evaluate a model and any text debiasing algorithm.

The advancements in the field of Information Communication Technology have engendered revolutionary changes in the journalism industry, not only on the part of the journalists and the media personnel, but also on the people consuming these news stories, who today, are only a click away from all the updates they need. However, these advances have also exposed the prevailing venality, wearying off the trust of the public in news media. How then, does an individual discern that which, out of the countless news stories for an incident, should be trusted? This work introduces a system that presents the user a multidimensional analysis for trust in news from various media sources based on the textual content of the articles, assessment of the journalists' perspectives and the temporal diversity of the issues being covered by the media houses publishing the news articles. Our experiments on a self-collected dataset confirm that the system aids in a comprehensive analysis of trust.

IT service providers differentiate themselves through offering after-sales support for hardware and software products. Thus, businesses, including large corporations, have intricate work-flows for servicing such support requests while reducing man-hours needed. These work-flows generally operate through a ticketing system for resolving customer issues. A lot of man-hours are spent in searching old tickets for correct problem and resolution for such issues. Support requests pertaining to enterprise hardware are more challenging than desktop support for end-user products. Enterprise hardware requires deeper diagnosis involving several systems and expertise of multiple agents. In this work we propose a cognitive agent, Neev, which helps in mitigating the problem in a three-fold fashion (1) retrieving a summary of relevant ticket text (2) Tagging the relevant parts as a part-of-the-problem or a part-of-the-solution (3) Focusing on the precise problem and solution. We evaluate the performance of our system using a rank-based metric where a ticket extraction is successful if the problem or solution occur in the top-n suggestions. We report the results for varying top-n values for both problem and solution on varying severity of the tickets. We find that the accuracy for problem extraction in top-1 is 62% and it reaches 86% and 94% for top-3 and top-5 cases, respectively. Furthermore, the accuracy for solution extraction reaches 62% and 88% for top-3 and top-8 cases, respectively.