KLKe Li
Ke Li
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ke Li has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Tingting Zhang
School of Computing, Nanjing Audit University, Nanjing 211815, China
1 shared publication
Latest Publications
- Open Access
- 27 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 996
SCIM: Self-Correcting Iterative Mechanism for Retrieval-Augmented Generation
Standard Retrieval-Augmented Generation (RAG) models are limited by their “one-shot” nature, failing to assess or improve answer quality dynamically. To address this, we introduce SCIM (Self-Correcting Iterative Mechanism), a framework featuring multi-dimensional evaluation and adaptive retrieval. A key distinction of SCIM is its efficiency: it operates on a lightweight Flan-T5-base model (250M parameters) and requires no fine-tuning, challenging the industry’s reliance on 7B+ parameter models. Experimental results across four major benchmarks show that SCIM yields a 17.2% improvement over standard RAG (p ). Notably, SCIM achieves parity with state-of-the-art models like ITER-RETGEN while reducing retrieval overhead by 31%, with 35% of queries converging within just 1–2 iterations. With high human correlation (Spearman ), SCIM demonstrates that robust, self-correcting RAG performance is attainable without the computational costs of large-scale LLMs.- 27 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 996
Open AccessSCIM: Self-Correcting Iterative Mechanism for Retrieval-Augmented Generation
Standard Retrieval-Augmented Generation (RAG) models are limited by their “one-shot” nature, failing to assess or improve answer quality dynamically. To address this, we introduce SCIM (Self-Correcting Iterative Mechanism), a framework featuring multi-dimensional evaluation and adaptive retrieval. A key distinction of SCIM is its efficiency: it operates on a lightweight Flan-T5-base model (250M parameters) and requires no fine-tuning, challenging the industry’s reliance on 7B+ parameter models. Experimental results across four major benchmarks show that SCIM yields a 17.2% improvement over standard RAG (p ). Notably, SCIM achieves parity with state-of-the-art models like ITER-RETGEN while reducing retrieval overhead by 31%, with 35% of queries converging within just 1–2 iterations. With high human correlation (Spearman ), SCIM demonstrates that robust, self-correcting RAG performance is attainable without the computational costs of large-scale LLMs.