Expected Attention: KV Cache Compression by Estimating Attention from Future Queries Distribution
Paper • 2510.00636 • Published • 1
prompt stringlengths 828 257k | category stringclasses 21
values | extra_info stringlengths 210 8.34k |
|---|---|---|
<|im_start|>user
You are given a story, which can be either a novel or a movie script, and a question. Answer the question asconcisely as you can, using a single phrase if possible. Do not provide any explanation.
Story:
<|memory_start|>
Transcribed from the 1915 Martin Secker edition by David Price, email
ccx074@pgl... | narrativeqa | {"ground_truth": {"answers": ["He is a guest in the home of the Mulvilles."], "length": 31406, "index": 0, "all_classes": null, "max_new_tokens": 148}, "scoring_function": "qa_f1_score", "task": "narrativeqa", "context_length": 31406, "variant": "memwrap"} |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"Because she is in unrequited love with someone else\"], \"lengt(...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"The Atlas Mountains\"], \"length\": 8392, \"index\": 2, \"all_c(...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"To smuggle Socrates out of prison and into a life of exile.\"],(...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"Otto was so young.\"], \"length\": 37090, \"index\": 4, \"all_c(...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"Six hours.\"], \"length\": 13538, \"index\": 5, \"all_classes\"(...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"Lisa, the blacksmith's wife.\"], \"length\": 31142, \"index\": (...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"Dr. Janosz Poha\"], \"length\": 46813, \"index\": 7, \"all_clas(...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"She is an American.\"], \"length\": 31405, \"index\": 8, \"all_(...TRUNCATED) |
"<|im_start|>user\nYou are given a story, which can be either a novel or a movie script, and a quest(...TRUNCATED) | narrativeqa | "{\"ground_truth\": {\"answers\": [\"The scribe.\"], \"length\": 8398, \"index\": 9, \"all_classes\"(...TRUNCATED) |
End of preview. Expand in Data Studio
LongBench v1
Prompts are constructed to exactly match how KVPress (kvpress/pipeline.py) builds them. Couple caveats:
- Four of the tasks are few-shot demonstration tasks. KVPress only compresses the few-shot demonstrations, but the query input might be large (e.g., an entire news article) and this is uncompressed.
Task Uncompressed input (mean) max trec 12 20 triviaqa 738 2021 samsum 150 507 lsht 524 3171
LongBench-e variants are not included. LongBench-e uses the same tasks but with a different scoring protocol: results are bucketed by context length (0–4k, 4–8k, 8k+) and averaged within each bucket, rather than producing a single score per task. The KVPress paper (arXiv:2510.00636) reports results using the standard LongBench scorer, not the -e bucketed variant.
Token statistics (Qwen3-4B-Instruct-2507 tokenizer)
| Task | Count | Min | Mean | Max | ≤32K % |
|---|---|---|---|---|---|
| narrativeqa | 200 | 8,289 | 29,847 | 65,318 | 57.5% |
| qasper | 200 | 1,917 | 5,034 | 21,888 | 100.0% |
| multifieldqa_en | 150 | 1,313 | 7,131 | 16,461 | 100.0% |
| hotpotqa | 200 | 1,844 | 13,391 | 17,600 | 100.0% |
| 2wikimqa | 200 | 964 | 7,491 | 16,996 | 100.0% |
| musique | 200 | 6,746 | 16,287 | 17,843 | 100.0% |
| gov_report | 200 | 2,046 | 10,589 | 52,521 | 98.5% |
| qmsum | 200 | 2,584 | 13,898 | 30,389 | 100.0% |
| multi_news | 200 | 132 | 2,653 | 14,278 | 100.0% |
| trec | 200 | 1,876 | 6,826 | 11,465 | 100.0% |
| triviaqa | 200 | 1,518 | 12,180 | 24,306 | 100.0% |
| samsum | 200 | 1,393 | 9,179 | 18,030 | 100.0% |
| passage_count | 200 | 4,965 | 15,321 | 29,538 | 100.0% |
| passage_retrieval_en | 200 | 10,318 | 12,849 | 15,575 | 100.0% |
| multifieldqa_zh | 200 | 847 | 4,459 | 9,962 | 100.0% |
| dureader | 200 | 5,236 | 10,609 | 19,174 | 100.0% |
| vcsum | 200 | 672 | 9,187 | 26,413 | 100.0% |
| lsht | 200 | 3,671 | 14,147 | 28,139 | 100.0% |
| passage_retrieval_zh | 200 | 3,335 | 4,695 | 6,726 | 100.0% |
| lcc | 500 | 991 | 3,212 | 32,621 | 100.0% |
| repobench-p | 500 | 2,599 | 10,918 | 39,255 | 98.8% |
- Downloads last month
- 49