AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing

Anxin Guo, Jingwei Li

ICML 2026 · Learning theory and algorithms › Sample complexity · approach: Computational thresholds in graphs and structure · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
increase fact weight lambda_F in the training lossfrom-scratch Transformer · Random strings (from scratch, 2-layer Transformer, n=15145)hallucination rate on non-factsHurt
increase fact weight lambda_F in the training lossfrom-scratch Transformer · Random strings (from scratch, 2-layer Transformer, n=15145)information per keyImproved
start from a pretrained LLM prior (ISBN) instead of structure-free IDsLoRA-tuned Qwen3.5-2B · LoRA fine-tuning (Synthetic IDs and ISBN, 12 runs)KL overhead vs lower bound: 14-22%No clear effect
fine-tune a pretrained model instead of training from scratchQwen3.5-2B · LoRA vs scratchconvergence speedImproved
lower LoRA rank from 4 to 2LoRA-tuned Qwen3.5-2B · ISBNKL per trainable parameter (bits): 0.17 -> 0.27Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy