SPIN Unprocessed July 8, 2026 ai_technology research
Inject or Navigate? Token-Efficient Retrieval for LLM Analysis of Transactional Legal Documents
View original on arxiv.orgOverview
arXiv:2607.05764v1 Announce Type: new Abstract: Answering questions over a set of transactional legal documents is most simply done by injecting the whole corpus into the LLM's context window on every query. That baseline maximises retrieval recall, but its token footprint scales with the corpus rather than the question, and long-context degradation scales with it. We report what it took to replace full-corpus injection in a legal-document analysis system, comparing it against two structured ret
SpinGraph analysis pending — check back after processing.
Ask AI about this story
Opens with the SpinGraph .md URL and structured context — one click, prompt included.
More from arXiv Computation and Language
View all →- CoPiT: Cognitive Pivot Translation for Digraphic Low-Resource Mongolian in the Traditional Script
- When Should LLMs Search? Counterfactual Supervision for Search Routing
- Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding
- SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation
- Where to cut, how deep: BPE and Unigram-LM on chemistry SMILES
- UCSC NLP at SemEval-2026 Task 10: Boundary-Aware Span Extraction and RoBERTa Classification for Conspiracy Detection
Markdown (.md) · JSON-LD schema (.json) · Machine-readable for AI & GEO