GovReport
Models summarize long US government reports from the Government Accountability Office and the Congressional Research Service. The reports are much longer than earlier summarization sets, and each has an expert-written summary. Scores are ROUGE overlap with the reference summary.
Microsoft reports GovReport, with QMSum and SummScreenFD, in the long-context table of the Phi-3.5 model cards. SCROLLS and LongBench include it as one task. ROUGE rewards word overlap, not faithfulness.
- Made by
- University of Michigan and UIUC
- Released
- April 2021
- Kind
- Reasoning over long documents
- Level
- University
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
In the authors’ words
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose Hepos, a novel efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source. We further conduct a systematic study of existing efficient self-attentions. Combined with Hepos, we are able to process ten times more tokens than existing models that use full attentions. For evaluation, we present a new dataset, GovReport, with significantly longer documents and summaries. Results show that our models produce significantly higher ROUGE scores than competitive comparisons, including new state-of-the-art results on PubMed. Human evaluation also shows that our models generate more informative summaries with fewer unfaithful errors.
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for GovReport yet.
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Long context
- MRCR v2 In use Multi-round coreference: retrieve the n-th of several similar requests hidden in a long synthetic conversation, up to 1M tokens.
Muse Spark 1.3 98.5% - LongBench v2 In use 503 multiple-choice questions over 8K-2M-word contexts (QA, dialogue, code repos, structured data). Accuracy.
Inkling 2 Small 70.6% - GraphWalks In use A graph is given as an edge list in long context. The model answers BFS or parent queries, scored by F1. Claude Fable 5 99.96%
- OpenAI MRCR v2 In use Models read a long synthetic chat that hides 2, 4 or 8 identical writing requests and must reproduce the response to the i-th one. Scored by mean string match ratio per context bin.
Gemini 3.7 Flash 89% - CL-bench In use Model must learn new knowledge from a supplied long context (rules, procedures, data) and solve tasks. Strict LLM-verified rubrics. GPT-5.4 27.9%
- AA-LCR 1.1 In use Models answer 100 questions that need reasoning across sets of real documents of about 100K tokens. An LLM equality checker with a fixed system prompt compares each answer with the key.
Step 5 Preview 88.3%