Papers › Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison...

Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison for Semantic Similarity

20 Feb 2025arXiv:2502.14620archive 2025-07-28

Xinghan Pan

This paper investigates the efficacy of RWKV, a novel language model architecture known for its linear attention mechanism, for generating sentence embeddings in a zero-shot setting. I conduct a layer-wise analysis to evaluate the semantic similarity captured by embeddings from different hidden layers of a pre-trained RWKV model. The performance is assessed on the Microsoft Research Paraphrase Corpus (MRPC) dataset using Spearman correlation and compared against a GloVe-based baseline. My results indicate that while RWKV embeddings capture some semantic relatedness, they underperform compared to the GloVe baseline in terms of Spearman correlation. I also analyze the inference time and GPU memory usage, highlighting the computational trade-offs associated with RWKV embeddings. The findings suggest that while RWKV offers potential advantages in terms of linear scaling, its zero-shot sentence embedding quality for semantic similarity tasks requires further investigation and potential task-specific fine-tuning to match or exceed simpler baselines.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingSemantic SimilaritySemantic Textual SimilaritySentenceSentence EmbeddingSentence EmbeddingsSentence-Embedding

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionGloVeSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections