LLM Compression

Bits-per-character compression of three raw corpora, used as an unsupervised linear proxy for knowledge, coding, and math benchmarks.

Also known as: llm-compression, Compression Represents Intelligence Linearly, BPC compression corpora

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorygeneration
Subcategoryunsupervised bits-per-character on Common Crawl, GitHub Python, and arXiv-math
Page statusactive
Metricbits per character (BPC), also averaged across the three corpora
Directionlower_is_better
UnitBPC
Dataset size32344
Dataset licenceCC-BY-NC-SA-4.0
PublisherHong Kong University of Science and Technology, with Tencent

What it measures

LLM Compression does not ask questions. It scores how many bits a base language model needs, on average, to encode held-out raw text. Huang, Zhang, Shan, and He collect three external corpora aimed at three abilities: Common Crawl snapshots for knowledge and commonsense, GitHub Python for coding, and arXiv mathematics papers for math. They report bits per character (BPC) rather than bits per token so tokenizers can be compared. The claim in the COLM 2024 paper is that average BPC is almost linearly correlated with average scores on 12 downstream benchmarks. The HTML body says 30 public LLMs; the arXiv v2 abstract says 31.

Task format

No prompt and no target string. OpenCompass feeds the content field through SWCELossInferencer with a sliding window (paper reproduction: block_size 1900, stride 512), sums cross-entropy, and converts to BPC. ZeroRetriever; no in-context examples. Intended for base models, not chat-tuned models.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub