CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Gaifan, Zhou, Yi, Bollegala, Danushka
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915767795056640
author Zhang, Gaifan
Zhou, Yi
Bollegala, Danushka
author_facet Zhang, Gaifan
Zhou, Yi
Bollegala, Danushka
contents The meaning conveyed by a sentence often depends on the context in which it appears. Despite the progress of sentence embedding methods, it remains unclear as how to best modify a sentence embedding conditioned on its context. To address this problem, we propose Condition-Aware Sentence Embeddings (CASE), an efficient and accurate method to create an embedding for a sentence under a given condition. First, CASE creates an embedding for the condition using a Large Language Model (LLM) encoder, where the sentence influences the attention scores computed for the tokens in the condition during pooling. Next, a supervised method is learnt to align the LLM-based text embeddings with the Conditional Semantic Textual Similarity (C-STS) task. We find that subtracting the condition embedding consistently improves the C-STS performance of LLM-based text embeddings by improving the isotropy of the embedding space. Moreover, our supervised projection method significantly improves the performance of LLM-based embeddings despite requiring a small number of embedding dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2503_17279
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement
Zhang, Gaifan
Zhou, Yi
Bollegala, Danushka
Computation and Language
The meaning conveyed by a sentence often depends on the context in which it appears. Despite the progress of sentence embedding methods, it remains unclear as how to best modify a sentence embedding conditioned on its context. To address this problem, we propose Condition-Aware Sentence Embeddings (CASE), an efficient and accurate method to create an embedding for a sentence under a given condition. First, CASE creates an embedding for the condition using a Large Language Model (LLM) encoder, where the sentence influences the attention scores computed for the tokens in the condition during pooling. Next, a supervised method is learnt to align the LLM-based text embeddings with the Conditional Semantic Textual Similarity (C-STS) task. We find that subtracting the condition embedding consistently improves the C-STS performance of LLM-based text embeddings by improving the isotropy of the embedding space. Moreover, our supervised projection method significantly improves the performance of LLM-based embeddings despite requiring a small number of embedding dimensions.
title CASE -- Condition-Aware Sentence Embeddings for Conditional Semantic Textual Similarity Measurement
topic Computation and Language
url https://arxiv.org/abs/2503.17279