#LLM

Six entries on this site carry the LLM tag: two papers and four posts, dated 2026.

Papers

Test-Input Generation for Tensor Programs: What Actually Finds Kernel Bugs
Paper · 2026 · arXiv · cited by 0 Companion paper to the Correctness Illusion. We study what kinds of test inputs actually find bugs in LLM-generated GPU kernels. Existing benchmarks (KernelBench) use uniformly-sampled inputs.
The Correctness Illusion in LLM-Generated GPU Kernels
Paper · 2026 · arXiv · cited by 0 LLM-generated GPU kernels pass the standard correctness test and are still wrong. We present the Correctness Illusion: the standard test bed for LLM-generated GPU kernels (KernelBench) under-specifies the input distribution, leading to kernels that pass the.

Automated Prompt Optimization: From AutoPrompt (2020) to TextGrad (2024)
Post · 2026 A chronological survey of automated prompt optimization 2020–2025: AutoPrompt, APE, OPRO, EvoPrompt, DSPy, TextGrad, PromptAgent, and how to choose between them.
LLM Prompt Compression: LLMLingua, GIST Tokens, and the Path to 480x Compression
Post · 2026 A practitioner's guide to LLM prompt compression: LLMLingua, GIST Tokens, 500xCompressor, KV-cache methods, and the rate-distortion limits of compressing context.
Prompt Structuring Techniques: From Chain-of-Thought to the Instruction Hierarchy
Post · 2026 A chronological survey of LLM prompt structuring: chain-of-thought, the instruction hierarchy, system prompt design, evaluation frameworks, and the theoretical foundations behind why prompts work.
LLM Safety Techniques: Constitutional AI, Harmony, SAIF, and Llama Guard Compared
Post · 2026 A practitioner's survey of LLM safety techniques across OpenAI Harmony, Anthropic Constitutional AI, Google SAIF, Meta Llama Guard, and open-source RLHF frameworks.