Year: 2025
Type: preprint
Abstract: Sentence encoders play a pivotal role in various NLP tasks; hence, an accurate evaluation of their compositional properties is paramount. However, existing evaluation methods predominantly focus on goal task-specific performance. This leaves a significant gap in understanding how well sentence embeddings demonstrate fundamental compositional properties in a task-independent context. Leveraging classical set theory, we address this gap by proposing six criteria based on three core "set-like" compositions/operations: \textit{TextOverlap}, \textit{TextDifference}, and \textit{TextUnion}. We systematically evaluate $7$ classical and $9$ Large Language Model (LLM)-based sentence encoders to assess their alignment with these criteria. Our findings show that SBERT consistently demonstrates set-like compositional properties, surpassing even the latest LLMs. Additionally, we introduce a new dataset of ~$192$K samples designed to facilitate future benchmarking efforts on set-like compositionality of sentence embeddings.
Source: arXiv (Cornell University)
Authors: Bansal, Naman, mahajan, Yash, Sinha, Sanjeev, Karmaker, Santu
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6929334240
Cites:
Cited by:
Related to: