5 papers
Context Compression Is Not One Thing: Readable Symbolic Re-expression vs. Coherent Summary at Matched Budget
Sisong Bei, Mikhail L. Arbuzov, Ziwei Dong +2
We study context compression for multi-hop question answering with small language models. We propose Telegraph English, a readable symbolic format that rewrites retrieved passages…
The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
Mikhail L. Arbuzov, Lee Mosbacker, Sisong Bei +3
Universal LLM reliability is not a finite-library problem: across all possible tasks, tools, schemas, knowledge sources, and evaluator expectations, new intervention-distinguishabl…
Telegraph English: Semantic Prompt Compression via Structured Symbolic Rewriting
Mikhail L. Arbuzov, Sisong Bei, Ziwei Dong +2
We introduce Telegraph English (TE), a prompt-compression protocol that rewrites natural language into a symbol-rich, formally-structured dialect. Where token-deletion methods such…
Tuning-Free LLM Can Build A Strong Recommender Under Sparse Connectivity And Knowledge Gap Via Extracting Intent
Wenqing Zheng, Noah Fatsi, Daniel Barcklow +5
Recent advances in recommendation with large language models (LLMs) often rely on either commonsense augmentation at the item-category level or implicit intent modeling on existing…
Revisiting RAG Retrievers: An Information Theoretic Benchmark
Wenqing Zheng, Dmitri Kalaev, Noah Fatsi +5
Retrieval-Augmented Generation (RAG) systems rely critically on the retriever module to surface relevant context for large language models. Although numerous retrievers have recent…