FloatDoor uses two LoRA adapters to create the first input-independent backdoor that triggers adversary-chosen behavior only on a target platform while remaining benign elsewhere.
Smaller = weaker? bench- marking robustness of quantized llms in code generation.CoRR, abs/2506.22776, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Across 13 quantization setups on six LLMs and two APR benchmarks, memory falls sharply while time and energy rise, nearly half of configs are Pareto-dominated, and repaired bug sets drift despite similar counts.
Ditto quantizes Code LLMs with per-block K-Means codebooks and compiles GEMV into BLAS calls, claiming up to 10.5× faster, 6.4× leaner local inference with ~0.27% pass@1 loss.
citing papers explorer
-
FloatDoor: Platform-Triggered Backdoors in LLMs
FloatDoor uses two LoRA adapters to create the first input-independent backdoor that triggers adversary-chosen behavior only on a target platform while remaining benign elsewhere.
-
Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair
Across 13 quantization setups on six LLMs and two APR benchmarks, memory falls sharply while time and energy rise, nearly half of configs are Pareto-dominated, and repaired bug sets drift despite similar counts.
-
Compiling Code LLMs into Lightweight Executables
Ditto quantizes Code LLMs with per-block K-Means codebooks and compiles GEMV into BLAS calls, claiming up to 10.5× faster, 6.4× leaner local inference with ~0.27% pass@1 loss.