Krithika Ramesh

Kabir Ahuja, Harshita Diddee, Rishav Hada et al. · microsoft-research

Generative AI models have shown impressive performance on many Natural Language Processing tasks such as language understanding, reasoning, and language generation. An important question being asked by the AI community today is about the capabilities and limits of these models, and it is clear that evaluating generative AI is very challenging. Most studies on generative LLMs have been restricted to English and it is unclear how capable these models are at understanding and generating text in other languages. We present the first comprehensive benchmarking of generative LLMs - MEGA, which evaluates models on standard NLP benchmarks, covering 16 NLP datasets across 70 typologically diverse languages. We compare the performance of generative LLMs including Chat-GPT and GPT-4 to State of the Art (SOTA) non-autoregressive models on these tasks to determine how well generative models perform compared to the previous generation of LLMs. We present a thorough analysis of the performance of models across languages and tasks and discuss challenges in improving the performance of generative LLMs on low-resource languages. We create a framework for evaluating generative LLMs in the multilingual setting and provide directions for future progress in the field.

Krithika Ramesh, Sunayana Sitaram, Monojit Choudhury

With language models becoming increasingly ubiquitous, it has become essential to address their inequitable treatment of diverse demographic groups and factors. Most research on evaluating and mitigating fairness harms has been concentrated on English, while multilingual models and non-English languages have received comparatively little attention. This paper presents a survey of fairness in multilingual and non-English contexts, highlighting the shortcomings of current research and the difficulties faced by methods designed for English. We contend that the multitude of diverse cultures and languages across the world makes it infeasible to achieve comprehensive coverage in terms of constructing fairness datasets. Thus, the measurement and mitigation of biases must evolve beyond the current dataset-driven practices that are narrowly focused on specific dimensions and types of biases and, therefore, impossible to scale across languages and cultures.

Yaxuan Ren, Krithika Ramesh, Yaxing Yao et al.

In this work, we aim to clarify and reconcile metrics for evaluating privacy protection in text through a systematic survey. Although text anonymization is essential for enabling NLP research and model development in domains with sensitive data, evaluating whether anonymization methods sufficiently protect privacy remains an open challenge. In manually reviewing 47 papers that report privacy metrics, we identify and compare six distinct privacy notions, and analyze how the associated metrics capture different aspects of privacy risk. We then assess how well these notions align with legal privacy standards (HIPAA and GDPR), as well as user-centered expectations grounded in HCI studies. Our analysis offers practical guidance on navigating the landscape of privacy evaluation approaches further and highlights gaps in current practices. Ultimately, we aim to facilitate more robust, comparable, and legally aware privacy evaluations in text anonymization.

Krithika Ramesh, Daniel Smolyak, Zihao Zhao et al.

We present SynthTextEval, a toolkit for conducting comprehensive evaluations of synthetic text. The fluency of large language model (LLM) outputs has made synthetic text potentially viable for numerous applications, such as reducing the risks of privacy violations in the development and deployment of AI systems in high-stakes domains. Realizing this potential, however, requires principled consistent evaluations of synthetic data across multiple dimensions: its utility in downstream systems, the fairness of these systems, the risk of privacy leakage, general distributional differences from the source text, and qualitative feedback from domain experts. SynthTextEval allows users to conduct evaluations along all of these dimensions over synthetic data that they upload or generate using the toolkit's generation module. While our toolkit can be run over any data, we highlight its functionality and effectiveness over datasets from two high-stakes domains: healthcare and law. By consolidating and standardizing evaluation metrics, we aim to improve the viability of synthetic text, and in-turn, privacy-preservation in AI development.

Krithika Ramesh, Ashiqur R. KhudaBukhsh, Sumeet Kumar

Over the last few years, YouTube Kids has emerged as one of the highly competitive alternatives to television for children's entertainment. Consequently, YouTube Kids' content should receive an additional level of scrutiny to ensure children's safety. While research on detecting offensive or inappropriate content for kids is gaining momentum, little or no current work exists that investigates to what extent AI applications can (accidentally) introduce content that is inappropriate for kids. In this paper, we present a novel (and troubling) finding that well-known automatic speech recognition (ASR) systems may produce text content highly inappropriate for kids while transcribing YouTube Kids' videos. We dub this phenomenon as \emph{inappropriate content hallucination}. Our analyses suggest that such hallucinations are far from occasional, and the ASR systems often produce them with high confidence. We release a first-of-its-kind data set of audios for which the existing state-of-the-art ASR systems hallucinate inappropriate content for kids. In addition, we demonstrate that some of these errors can be fixed using language models.

Mirza Yusuf, Praatibh Surana, Gauri Gupta et al.

In recent times, there has been definitive progress in the field of NLP, with its applications growing as the utility of our language models increases with advances in their performance. However, these models require a large amount of computational power and data to train, consequently leading to large carbon footprints. Therefore, it is imperative that we study the carbon efficiency and look for alternatives to reduce the overall environmental impact of training models, in particular large language models. In our work, we assess the performance of models for machine translation, across multiple language pairs to assess the difference in computational power required to train these models for each of these language pairs and examine the various components of these models to analyze aspects of our pipeline that can be optimized to reduce these carbon emissions.

Rakshit Naidu, Harshita Diddee, Ajinkya Mulay et al.

In recent years, machine learning techniques utilizing large-scale datasets have achieved remarkable performance. Differential privacy, by means of adding noise, provides strong privacy guarantees for such learning algorithms. The cost of differential privacy is often a reduced model accuracy and a lowered convergence speed. This paper investigates the impact of differential privacy on learning algorithms in terms of their carbon footprint due to either longer run-times or failed experiments. Through extensive experiments, further guidance is provided on choosing the noise levels which can strike a balance between desired privacy levels and reduced carbon emissions.

Gauri Gupta, Krithika Ramesh, Sanjay Singh

With language models being deployed increasingly in the real world, it is essential to address the issue of the fairness of their outputs. The word embedding representations of these language models often implicitly draw unwanted associations that form a social bias within the model. The nature of gendered languages like Hindi, poses an additional problem to the quantification and mitigation of bias, owing to the change in the form of the words in the sentence, based on the gender of the subject. Additionally, there is sparse work done in the realm of measuring and debiasing systems for Indic languages. In our work, we attempt to evaluate and quantify the gender bias within a Hindi-English machine translation system. We implement a modified version of the existing TGBI metric based on the grammatical considerations for Hindi. We also compare and contrast the resulting bias measurements across multiple metrics for pre-trained embeddings and the ones learned by our machine translation model.