LongProc

Six procedural-generation tasks at 0.5K, 2K, and 8K output lengths that test whether long-context models can follow a procedure and emit a structured trace.

Also known as: Long Procedural Generation, LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation

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.
Categorylong-context
Subcategorysix procedural-generation tasks at 0.5K / 2K / 8K output lengths
Page statusactive
Metricmean score (task-specific exact/structured match, averaged; lm-eval group longproc uses metric score, unweighted)
Directionhigher_is_better
Unit%
Dataset size1709
Dataset licenceApache-2.0 (princeton-pli/LongProc LICENSE and Hugging Face card)
PublisherPrinceton Language and Intelligence (Princeton University) and The University of Texas at Austin

What it measures

LongProc (Long Procedural Generation) asks a model to execute a stated procedure and write a long structured output, not a short answer from a needle in a haystack. Six tasks: HTML-to-TSV extraction, line-by-line pseudocode-to-C++, path traversal on a one-out-edge city graph, theory-of-mind location/belief tracking, Countdown arithmetic search, and constrained travel planning. Difficulty is the required output length (about 500, 2K, or 8K Llama-3 tokens). English text. Rule-based scoring against a gold trace.

Task format

Prompt in, long structured generation out (TSV, C++, route listing, belief log, search trace, or itinerary). Paper evaluation uses greedy decoding and a 0.5K-1K token buffer; reasoning models may generate up to 16K tokens. lm-eval tasks are generate_until, num_fewshot 0, temperature 0, with max_gen_toks 1024 / 3072 / 9216 on the 0.5k / 2k / 8k YAML includes. `unsafe_code: true` because the pseudocode task compiles C++.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub