2023/05/27 by Jason Hoelscher-Obermaier, Hoelscher-Obermaier, Jason, Julia Persson +7 · 1 voice · 2 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling #cs.AI #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2305.17553
openalex publication_date 2023/05/27 · arxiv published 2023/05/27 · openalex created_date 2023/05/31 · arxiv updated 2023/06/03 · openalex updated_date 2026/07/28
Recent model editing techniques promise to mitigate the problem of memorizing false or outdated associations during LLM training. However, we show that these techniques can introduce large unwanted side effects which are not detected by existing specificity benchmarks. We extend the existing CounterFact benchmark to include a dynamic component and dub our benchmark CounterFact+. Additionally, we extend the metrics used for measuring specificity by a principled KL divergence-based metric. We use this improved benchmark to evaluate recent model editing techniques and find that they suffer from low specificity. Our findings highlight the need for improved specificity benchmarks that identify and prevent unwanted side effects.