VISLA Benchmark: Evaluating Embedding Sensitivity to Semantic and Lexical Alterations (2404.16365v1)

Abstract: Despite their remarkable successes, state-of-the-art LLMs face challenges in grasping certain important semantic details. This paper introduces the VISLA (Variance and Invariance to Semantic and Lexical Alterations) benchmark, designed to evaluate the semantic and lexical understanding of LLMs. VISLA presents a 3-way semantic (in)equivalence task with a triplet of sentences associated with an image, to evaluate both vision-LLMs (VLMs) and unimodal LLMs (ULMs). An evaluation involving 34 VLMs and 20 ULMs reveals surprising difficulties in distinguishing between lexical and semantic variations. Spatial semantics encoded by LLMs also appear to be highly sensitive to lexical information. Notably, text encoders of VLMs demonstrate greater sensitivity to semantic and lexical variations than unimodal text encoders. Our contributions include the unification of image-to-text and text-to-text retrieval tasks, an off-the-shelf evaluation without fine-tuning, and assessing LMs' semantic (in)variance in the presence of lexical alterations. The results highlight strengths and weaknesses across diverse vision and unimodal LLMs, contributing to a deeper understanding of their capabilities. % VISLA enables a rigorous evaluation, shedding light on LLMs' capabilities in handling semantic and lexical nuances. Data and code will be made available at https://github.com/Sri-Harsha/visla_benchmark.