← Back to all news
arXiv Computation and Language By Selen Erkan, Bastian Boll, Kristian Kersting, Bj\"orn Deiseroth, Letitia Parcalabescu

Beyond Prompt and Parser Engineering: Soft-Prompt Tuning for Automated LLM Evaluation

Read the original on arXiv Computation and Language →

The paper introduces soft‑prompt tuning as a lightweight, automated method for evaluating large language models (LLMs). By optimizing only ten soft‑prompt vectors—about 0.0006% of a 7B model’s parameters—within 150 steps, the approach adapts models to specific benchmark formats, improving format compliance while preserving knowledge accuracy. Experiments across seven models and eleven datasets show that this method matches strong evaluation‑harness baselines, enhances evaluation signals on challenging datasets, and yields cleaner outputs that align better with exact‑match scoring and independent LLM judges.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv AI
Sep 4

RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data

RECAST is a new framework that generates datasets with far more constraints per example than existing benchmarks, aiming to push large language models (LLMs) to better follow complex instructions. The authors built RECAST-30K, a 30,000‑instance dataset covering 19 constraint types extracted from real prompt‑response pairs, and showed that fine‑tuning on it improves LLMs’ ability to handle complex tasks without harming general performance. RECAST also provides rule‑based and LLM‑based validators for automatic constraint verification, enabling reward‑based reinforcement learning to further enhance model performance on challenging tasks.

By Zhengkang Guo, Wenhao Liu, Mingchen Xie, Jingwen Xu, Zisu Huang, Muzhao Tian, Jianhan Xu, Yuanzhe Shen, Qi Qian, Muling Wu, Xiaohua Wang, Changze Lv, He-Da Wang, Hu Yao, Xiaoqing Zheng, Xuanjing Huang
llmsreinforcement-learningbenchmarks
More like this →