Aligning Language Models to Explicitly Handle Ambiguity

arXiv:2404.11972v1 Announce Type: new
Abstract: In spoken languages, utterances are often shaped to be incomplete or vague for efficiency. This can lead to varying interpretations of the same input, based on different assumptions about the context. To ensure reliable user-model interactions in such scenarios, it is crucial for models to adeptly handle the inherent ambiguity in user queries. However, conversational agents built upon even the most recent large language models (LLMs) face challenges in processing ambiguous inputs, primarily due to …

abstract arxiv assumptions context cs.cl efficiency interactions language language models languages spoken type