TEFM: Token-Efficient Faithful Modeling for Structured Data
Source
Zhichao Hou, Lingdao Sha, Xueyu Mao, Yang Liu, Peijie Qiu, Rui Song
Author
Zhichao Hou, Lingdao Sha, Xueyu Mao, Yang Liu, Peijie Qiu, Rui Song
Date
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
Compressing structured records into compact tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → before LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition → analysis cuts token use to roughly 1-2% of the original while preserving accuracy and producing traceable rationales.
Key quotes
“TEFM achieves token efficiency by compressing lengthy structured observations into compact Behavioral Code tokens, dramatically reducing token consumption with minimal information loss.”
“Comprehensive experiments across various domain datasets and model backbones (Qwen3, Gemma-2, Phi-4) show that TEFM achieves competitive classification accuracy with dramatic token reduction (approximately 1% token retention in clinical and 2% in security domains) while producing faithful rationales.”
articleAccelerating LLM Inference via Vector Index Based Output EmbeddingsMartin Loretz, Sepp Hochreiter
articleCode Health in LLM-Based Test Generation: Effectiveness and Token EfficiencyFreya Wirdemann, Markus Borg, Nadim Hagatulah, Adam Tornhill
articleA Removal Based Approach to Improve LLM Faithfulness at Test-TimeQinglan Luo, S M A Nahian, John Guttag, S. Mazdak Abulnaga, Katie Matton