Abstract:Despite the state-of-the-art performance of Large Language Models (LLMs) achieved on many tasks, their massive scale often leads to high computational and environmental costs, limiting their accessibility. Parameter-Efficient Fine-Tuning (PEFT) methods address this challenge by reducing the number of trainable parameters while maintaining strong downstream performance. Despite the advances in PEFT methods, current evaluations remain limited (in terms of evaluated models and datasets) and difficult to reproduce. To bridge this gap, we introduce PEFT-Bench, a unified end-to-end benchmark for evaluating diverse PEFT methods on autoregressive LLMs. We demonstrate its usage across 27 NLP datasets and 7 PEFT methods. To account for different PEFT training and inference factors, we also introduce the PEFT Soft Cost Penalties (PSCP) metric, which takes trainable parameters, inference speed, and training memory usage into account.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2511.21285 [cs.CL] |
| (or arXiv:2511.21285v3 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2511.21285 arXiv-issued DOI via DataCite |
|
| Related DOI: | https://doi.org/10.18653/v1/2026.eacl-long.140
DOI(s) linking to related resources |
Submission history
From: Robert Belanec [view email]
[v1]
Wed, 26 Nov 2025 11:18:06 UTC (287 KB)
[v2]
Sun, 22 Feb 2026 16:12:41 UTC (291 KB)
[v3]
Tue, 12 May 2026 18:52:26 UTC (291 KB)