4 citations · 4 across the 2 of their papers we have counts for
2 papers
cs.AI2026
Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight Compression
Dachi Kurtskhalia
Weight quantization largely determines the economics of serving open-weight LLMs. Its costs are usually assessed with capability benchmarks, on which 4-bit quantization of mid-size…
cs.CR2025★ 4 cited
Improving LLM Outputs Against Jailbreak Attacks with Expert Model Integration
Tatia Tsmindashvili, Ana Kolkhidashvili, Dachi Kurtskhalia +7
Using LLMs in a production environment presents security challenges that include vulnerabilities to jailbreaks and prompt injections, which can result in harmful outputs for humans…