@inproceedings{sundar-heck-2023-ctbls,
    title = "c{TBLS}: Augmenting Large Language Models with Conversational Tables",
    author = "Sundar, Anirudh S.  and
      Heck, Larry",
    editor = "Chen, Yun-Nung  and
      Rastogi, Abhinav",
    booktitle = "Proceedings of the 5th Workshop on NLP for Conversational AI (NLP4ConvAI 2023)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.nlp4convai-1.6/",
    doi = "10.18653/v1/2023.nlp4convai-1.6",
    pages = "59--70",
    abstract = "Optimizing accuracy and performance while eliminating hallucinations of open-domain conversational large language models (LLMs) is an open research challenge. A particularly promising direction is to augment and ground LLMs with information from structured sources. This paper introduces Conversational Tables cTBLS, a three-step architecture to retrieve and generate dialogue responses grounded on retrieved tabular information. cTBLS uses Transformer encoder embeddings for Dense Table Retrieval and obtains up to 125{\%} relative improvement over the retriever in the previous state-of-the-art system on the HyrbiDialogue dataset. cTBLS then uses a shared process between encoder and decoder models to perform a coarse+fine tabular knowledge (e.g., cell) ranking combined with a GPT-3.5 LLM response generator to yield a 2x relative improvement in ROUGE scores. Finally, human evaluators prefer cTBLs +80{\%} of the time (coherency, fluency) and judge informativeness to be 4x better than the previous state-of-the-art."
}