Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression
Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget. We identify a structural failure in this procedure: independent selection can split dependent evidence pairs, retaining one member while deleting the other. When retained text contains an answer but deleted text defines the entity needed to interpret it, we call the result referential dangling. At a compression ratio of 0.30, Beaver, which ranks coherent chunks using Qwen3-0.6B embeddings, leaves the answer path incomplete in 34-54% of bridge examples across three multi-hop question answering datasets. On a shared HotpotQ...
| Authors | Zhengpei Hu, Kai Li, Dapeng Fu et al. |
|---|---|
| Primary category | cs.CL |
| Published | 5 August 2026 |
| Last updated at source | 5 August 2026 |
Connected in the knowledge graph
- JusperLee/referential-dangling-detectorModel · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.