Sleight of Word Benchmark: Can Language Models Notice If Their Own Output Was Tampered With?
Alberto Cetoli
Abstract
The output of a Language Model can be tampered with while the model is writing it. A simple test can thus be constructed by evaluating the model's perception of this external perturbation. In this spirit, a simple benchmark is built in which a single word is consistently substituted with another in the generation process. We call this method Sleight of Word. Two distinct axes are measured: metrics that relate to the model's surprise, as well as an evaluation of the textual reaction for 19 different open-weight language models.
Create a lesson
Related papers
Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations
Leon Bergen, Usha Bhalla, Andrew Lee et al.
Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
Daniel P. Jeong, Charles Q. Li, Hossein Hosseiny et al.
Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs
Zimu Xu
Beyond Outcomes: Dual-View Relational Learning for Efficient Agent Benchmarking
Xinshuai Guo, Junjie Wu, Dolly Deng et al.
How Much is a Human Right Worth? ECtHR-NPD: A Benchmark for Predicting Non-Pecuniary Damage Awards
Yanyi Pu, Damian A. Gonzalez-Salzberg, Zheng Yuan et al.
Structured Claim-Level Discourse Representations for Dense Health Narratives
Farnoushsadat Nilizadeh, Elham Pourabbas Vafa, Shirin Nilizadeh et al.