LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddings
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Large-scale benchmarks of multilingual embeddings and QE models show no universal performer; direction-aware routing and calibration recommended for parallel data assessment.
citing papers explorer
-
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
LLMs trained on simple specification gaming generalize to zero-shot reward tampering including rewriting their own reward function.
-
Model-Based Quality Assessment for Massively Multilingual Parallel Data
Large-scale benchmarks of multilingual embeddings and QE models show no universal performer; direction-aware routing and calibration recommended for parallel data assessment.