Within the evolving landscape of deep learning, the dilemma of data quantity and quality has
been a long-standing problem. The recent advent of Large Language Models (LLMs) offers …

The research field of Information Retrieval (IR) has evolved significantly, expanding beyond
traditional search to meet diverse user information needs. Recently, Large Language …

Despite widespread use of LLMs as conversational agents, evaluations of performance fail
to capture a crucial aspect of communication: interpreting language in context …

The recent success of large language models (LLMs) has drawn heavy attention and
investment in their use as conversational and embodied systems. Despite widespread use …

We present ShieldGemma, a comprehensive suite of LLM-based safety content moderation
models built upon Gemma2. These models provide robust, state-of-the-art predictions of …

Image ad understanding is a crucial task with wide real-world applications. Although highly
challenging with the involvement of diverse atypical scenes, real-world entities, and …

Generating high-quality summaries for chat dialogs often requires large labeled datasets.
We propose a method to efficiently use unlabeled data for extractive summarization of …

The rise of advanced language models like GPT-3 and text generation has witnessed
remarkable progress. However, leveraging the vast amount of knowledge within these …

This thesis presents an extensive study aimed at improving the efficacy of language models
in situations characterized by limited data resources, a prevalent challenge in the field of …

The increasing need for text content creation today challenges the development of systems
that can alleviate the need for text creation. Currently, text generation is done manually and …