The Inefficiency of Language Models in Scholarly Retrieval: An Experimental Walk-through
This highlights inefficiencies in AI-powered scientific information retrieval systems, which is an incremental finding for researchers and developers in the field.
The paper evaluated scientific language models for scholarly retrieval, finding they fail to retrieve relevant documents for short queries even under relaxed conditions and that retrieval performance is more influenced by surface form than semantics.
Language models are increasingly becoming popular in AI-powered scientific IR systems. This paper evaluates popular scientific language models in handling (i) short-query texts and (ii) textual neighbors. Our experiments showcase the inability to retrieve relevant documents for a short-query text even under the most relaxed conditions. Additionally, we leverage textual neighbors, generated by small perturbations to the original text, to demonstrate that not all perturbations lead to close neighbors in the embedding space. Further, an exhaustive categorization yields several classes of orthographically and semantically related, partially related, and completely unrelated neighbors. Retrieval performance turns out to be more influenced by the surface form rather than the semantics of the text.