Papers with information-spectrum-based diagnostic framework
Diagnosing LLMs via Information Spectrum Analysis: Tail Behavior and the Effects of Side Information (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models exhibit non-stationary generation because of variability in output distributions . authors propose a framework that treats LLMs as general sources without stationarity or ergodicity . |
| Approach: | They propose a diagnostic framework that treats large language models as general sources without stationarity, ergodicity, or the asymptotic equipartition property. |
| Outcome: | The proposed framework treats large language models as general sources without stationarity, ergodicity, or the asymptotic equipartition property. |