Search Results for author:
Found 2 papers, 0 papers with code
Aligning Language Models to Explicitly Handle Ambiguity
However, conversational agents built upon even the most recent large language models (LLMs) face challenges in processing ambiguous inputs, primarily due to the following two hurdles: (1) LLMs are not directly trained to handle inputs that are too ambiguous to be properly managed; (2) the degree of ambiguity in an input can vary according to the intrinsic knowledge of the LLMs, which is difficult to investigate.
CELDA: Leveraging Black-box Language Model as Enhanced Classifier without Labels
Additionally, our proposed methodology can be applied universally to any LM and has the potential to scale to larger models, making it a more viable option for utilizing large LMs.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
