-
2025Retrieval-augmented generation (RAG) can enhance the generation quality of large language models (LLMs) by incorporating external token databases. However, retrievals from large databases can constitute a substantial portion of the overall generation time, particularly when retrievals are periodically performed to align the retrieved content with the latest states of generation. In this paper, we introduce
-
2025Existing automatic prompt engineering methods are typically designed for discriminative tasks, where new task prompts are iteratively refined with limited feedback from a single metric reflecting a single aspect. However, these approaches are suboptimal for generative tasks, which require more nuanced guidance beyond a single numeric metric to improve the prompt and optimize multiple aspects of the generated
-
Knowledge distillation is used, in generative language modeling, to train a smaller student model using the help of a larger teacher model, resulting in improved capabilities for the student model. In this paper, we formulate a more general framework for knowledge distillation where the student learns from the teacher during training, and also learns to ask for the teacher’s help at test-time following
-
2025Text-to-SQL simplifies database interactions by enabling non-experts to convert their natural language (NL) questions to Structured Query Language (SQL) queries. With advancements in Large Language Models (LLM), in-context learning (ICL) has emerged as a popular choice for building Text-to-SQL systems. Real world, industry-scale databases, often comprise thousands of tables and hundreds of columns, and
-
COLING 2025 Workshop on Evaluation of Multi-Modal Generation2025Multimodal generative AI usually involves generating image or text responses given inputs in another modality. The evaluation of image-text relevancy is essential for measuring response quality or ranking candidate responses. In particular, binary relevancy evaluation, i.e., “Relevant” vs. “Not Relevant”, is a fundamental problem. However, this is a challenging task considering that texts have diverse formats
Related content
-
September 06, 2022Speech recognition and text-to-speech predominate, but other topics include audio watermarking, automatic dubbing, and compression.
-
September 02, 2022Method would enable customers to evaluate supporting evidence for tip reliability.
-
August 23, 2022New speech representations and self-supervised learning are two of the recent trends that most intrigue him.
-
August 15, 2022Data augmentation and post-editing strategies lift Amazon’s submission above competitors.
-
August 02, 2022With an encoder-decoder architecture — rather than decoder only — the Alexa Teacher Model excels other large language models on few-shot tasks such as summarization and machine translation.
-
August 01, 2022McKeown awarded IEEE Innovation in Societal Infrastructure Award and named a member of the American Philosophical Society.