Dynamic Epistemic Decay: A Multi-Dimensional Framework for Knowledge Currency in Retrieval-Augmented Generation
Fuente:
Zenodo
Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | English |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866902329489358848 |
|---|---|
| author | Kochukalam George, Alan |
| author_facet | Kochukalam George, Alan |
| contents | <p>Large language models and retrieval-augmented generation systems treat all knowledge as uniformly persistent, ignoring a well-established property of information: that different types of knowledge expire at fundamentally different rates. This paper introduces the Dynamic Epistemic Decay Framework, a formal multi-dimensional theory that characterizes knowledge validity as a function of five independent decay dimensions: temporal decay ( ), paradigm decay ( ), uncertainty decay ( ), dependency decay ( ), and zero decay ( 0). We implement this framework as a four-phase retrieval pipeline and evaluate it on the TempQuestions benchmark (n=1,740) against three baselines: standard cosine similarity, BM25 lexical retrieval, and naive recency ranking. Decay-weighted retrieval achieves 92.1% accuracy versus 13.5% for standard semantic retrieval—a 78.6 percentage point improvement—with zero regressions on stable factual queries. On semantically complex temporal benchmarks where lexical heuristics fail, the framework dominates a more resourced BM25 baseline (90.2% vs 1.6% on date-bounded role queries). Epistemic modulation (Phase 4) and dependency graph reasoning (Phase 3) further demonstrate correct mechanism behavior on specialized benchmarks, validated via proof-of-concept implementation. Unlike temporal KG completion approaches that require structured annotation, and unlike contrastive training approaches to time-sensitive RAG, the decay framework is training-free and operates directly over unstructured text corpora. We argue that the decay framework completes the separation of concerns that RAG began: decoupling not just factual storage from model parameters, but factual currency from both.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_19027156 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Dynamic Epistemic Decay: A Multi-Dimensional Framework for Knowledge Currency in Retrieval-Augmented Generation Kochukalam George, Alan Knowledge decay retrieval-augmented generation temporal reasoning epistemic validity knowledge graphs information retrieval <p>Large language models and retrieval-augmented generation systems treat all knowledge as uniformly persistent, ignoring a well-established property of information: that different types of knowledge expire at fundamentally different rates. This paper introduces the Dynamic Epistemic Decay Framework, a formal multi-dimensional theory that characterizes knowledge validity as a function of five independent decay dimensions: temporal decay ( ), paradigm decay ( ), uncertainty decay ( ), dependency decay ( ), and zero decay ( 0). We implement this framework as a four-phase retrieval pipeline and evaluate it on the TempQuestions benchmark (n=1,740) against three baselines: standard cosine similarity, BM25 lexical retrieval, and naive recency ranking. Decay-weighted retrieval achieves 92.1% accuracy versus 13.5% for standard semantic retrieval—a 78.6 percentage point improvement—with zero regressions on stable factual queries. On semantically complex temporal benchmarks where lexical heuristics fail, the framework dominates a more resourced BM25 baseline (90.2% vs 1.6% on date-bounded role queries). Epistemic modulation (Phase 4) and dependency graph reasoning (Phase 3) further demonstrate correct mechanism behavior on specialized benchmarks, validated via proof-of-concept implementation. Unlike temporal KG completion approaches that require structured annotation, and unlike contrastive training approaches to time-sensitive RAG, the decay framework is training-free and operates directly over unstructured text corpora. We argue that the decay framework completes the separation of concerns that RAG began: decoupling not just factual storage from model parameters, but factual currency from both.</p> |
| title | Dynamic Epistemic Decay: A Multi-Dimensional Framework for Knowledge Currency in Retrieval-Augmented Generation |
| topic | Knowledge decay retrieval-augmented generation temporal reasoning epistemic validity knowledge graphs information retrieval |
| url | https://doi.org/10.5281/zenodo.19027156 |