arXiv cs.AI· Jahnavi Yelamanchi·· 3 天前AI 评分20
参考描述措辞如何影响机器人任务指令的检索
Reference Wording Shapes Retrieval of Robot Task Instructions
AI 导读
研究在 RLBench 操作基准的自然语言指令中考察参考描述措辞对任务检索的影响，从 62 个公开任务文件提取 296 条固定描述，在 80 组随机索引描述下比较五种免训练词汇排序器。
正文 · 原文
Abstract:Identifying a robot task from a short instruction is sensitive to which descriptions are available for retrieval. We investigate this effect in the natural-language instructions included with the RLBench manipulation benchmark. We extract 296 fixed descriptions from 62 publicly available task files and compare five training-free lexical rankers over 80 random choices of one indexed description per task. Exact strings assigned to conflicting task labels are excluded from the primary score. Character n-gram TF-IDF achieves 61.3% mean top-1 accuracy on the resulting held-out instructions, compared with 55.6% for BM25 and 54.9% for word TF-IDF. Across gallery choices, character TF-IDF ranges from 55.2% to 66.8%; its 5th-95th percentile range is 56.9%-64.8%. Adding a second indexed description improves character TF-IDF by 7.0 percentage points on matched queries. These results quantify the influence of reference wording and representation choice on instruction-to-task retrieval under a consistent evaluation protocol.
| Comments: | 6 pages, 4 figures, 4 tables |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Information Retrieval (cs.IR); Robotics (cs.RO) |
| Cite as: | arXiv:2610.17549 [cs.AI] |
| (or arXiv:2610.17549v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17549 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jahnavi Yelamanchi [view email]
[v1]
Tue, 13 Oct 2026 01:21:02 UTC (60 KB)
来源：arXiv cs.AI · arxiv.org