arXiv AI August 19, 2026 By Julian Oestreich, Maximilian Bley, Frank Binder, Lydia M\"uller, Andr\'e Alcalde, Maksym Sydorenkoq

Parametric Knowledge in RAG-SFT for Domain-Specific Document Generation

Read the original on arXiv AI →

The paper investigates Retrieval-Augmented Generation fine‑tuning (RAG‑SFT) for generating requirements documents in electronics engineering, comparing two 7B models trained with different data strategies. It introduces a claim‑based evaluation pipeline, C‑FEX, and a new metric, Parametric Knowledge Precision (PKP), to assess factuality of model‑generated claims. Results show that fine‑tuned 7B models can match or surpass a 72B baseline, but standard metrics may mislead, and fine‑tuning reduces hallucination by encouraging more reliable use of parametric knowledge.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Aug 21

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

arXiv:2608. 20281v1 Announce Type: cross Abstract: Large language models often fail to answer questions about a bounded document collection when the source documents are not retrieved at inference time.

By Qian Kou, Xiaofeng Shi, Xiaosong Qiu, Hua Zhou

llms nlp fine-tuning benchmarks safety

arXiv Machine Learning

5d ago

Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation

The paper introduces TRACE, a fine‑tuning framework for Retrieval‑Augmented Generation (RAG) that addresses conflicts between retrieved knowledge and a model’s internal knowledge. TRACE uses multi‑agent debate traces to identify correct and incorrect candidates and answer‑shift patterns, providing fine‑grained supervision for reliable knowledge‑source selection. It also incorporates an answer‑completeness regularization mechanism to prevent empty, overly short, or prematurely terminated responses, thereby improving robustness against misleading retrieved content and enhancing answer quality.

By Zhengchen Huang, Yundong Sun, Minrui Song, Shuanglong Yao, Ye Liu, Ji Chen, Xing Wang

llms rag agents fine-tuning safety

arXiv Machine Learning

4d ago

Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG

arXiv:2609.37469v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) grounds large language models in external sources, but retrieved passages often name the right entities without...

By Suting Chen, Peichun Hua, Yunming Xiao

llms rag benchmarks

arXiv AI

Jul 21

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

arXiv:2604. 09497v2 Announce Type: replace-cross Abstract: Accurate evaluation is central to the large language model (LLM) ecosystem, guiding model selection and downstream adoption across diverse use cases.

By Hippolyte Gisserot-Boukhlef, Nicolas Boizard, Emmanuel Malherbe, C\'eline Hudelot, Pierre Colombo

llms

arXiv Computation and Language

Aug 28

Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG

The paper investigates whether incorporating an evidence-support signal into retrieval evaluation for retrieval‑augmented generation (RAG) improves downstream decision‑making. Across multiple benchmarks and a TREC RAG 2025 setting, the evidence signal alters retriever rankings but its benefits vary: it does not consistently enhance retriever training, its usefulness for system selection depends on generator instructions, and it does not reliably predict answer quality on unseen topics. Human filtering of evidence‑rich passages preserves useful content, yet evaluators disagree on whether this improves final answers, indicating that evidence‑aware evaluation alone does not guarantee better downstream outcomes.

By Utshab Kumar Ghosh, Debayan Mukhopadhyay, Shubham Chatterjee

rag benchmarks safety

arXiv AI

Aug 24

SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation

arXiv:2509.20377v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has significantly improved the performance of large language models (LLMs) on knowledge-intensive tasks...

By Tomoaki Isoda

llms rag nlp reinforcement-learning benchmarks safety

One email a morning, machine-written

Related stories

Inject, Align, Recover: Staged Post-Training for Retrieval-Free Document Knowledge Internalization

Parameters vs. Context: TRACE Fine-Tuning for Robust Retrieval-Augmented Generation

Relevance Is Not Sufficient Evidence: Detecting Evidence Gaps Before Generation in RAG

BERT-as-a-Judge: A Robust Alternative to Lexical Methods for Efficient Reference-Based LLM Evaluation

Assessing the Downstream Utility of Evidence-Aware Retrieval in RAG

SKILL-RAG: Self-Knowledge Induced Learning and Filtering for Retrieval-Augmented Generation