arXiv Computation and Language September 10, 2026 By Christoph Wigbels, Ali Abusaleh, Markus T. Jansen, Alexander Mehler, Markus J. Hofmann

From Retrieval to Weights: Parametric Individualization of Small Language Models with Individual Text Corpora

Read the original on arXiv Computation and Language →

The paper explores how individual text corpora (ITCs) can be integrated into small language models (SLMs) using DoRA fine‑tuning. By training a DoRA adapter for each of 150 participants, the authors show that the adapter can encode a participant’s own ITC into the model’s weights, improving fit to that participant’s held‑out text. However, while the adapter improves log‑loss on a generalized knowledge test, it does not enhance accuracy under a bias‑corrected PMI readout, and adding retrieval does not provide further benefit.

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 Computation and Language.

arXiv AI

Jul 29

Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook

arXiv:2509. 16780v3 Announce Type: replace-cross Abstract: Large language models (LLMs) show promise as educational aids but often lack alignment with specific course materials.

By Eason Chen, Chuangji Li, Eric Li, Zimo Xiao, Jionghao Lin, Kenneth R. Koedinger

llms rag nlp safety

arXiv AI

Aug 25

The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory

arXiv:2608.22767v1 Announce Type: new Abstract: Long-term language-model agents accumulate memories across interactions, but their retrievers typically do not accumulate retrieval experience. Semanti...

By Qi Feng, Chris Ding, Jicong Fan

llms rag agents

arXiv Computation and Language

Sep 14

EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development

The paper introduces EAR, an Entity‑Aware Partitioning approach that improves retrieval‑augmented generation for multiple‑choice question answering by extracting normalized surface anchors from questions, answers, and the corpus. EAR retrieves local windows around matching anchors and can attach a larger parent passage via an extractive summary, reducing retrieved words by 37.5‑40.2% compared to fixed‑size chunks. Experiments on a cleaned MMLU‑style subset with Mistral, Gemma, and DeepSeek show modest accuracy changes, none statistically significant, highlighting EAR’s methodological contribution of compact, inspectable retrieval units.

By Cenab Batu Bora, Oylum Alatl{\i}, Sebnem Bora, Oguz Dikenelli

llms rag nlp benchmarks

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

arXiv AI

3d ago

Instruction Retrieval at Inference Time for Small Language Models

arXiv:2510.13935v3 Announce Type: replace-cross Abstract: The facts a language model stores are tied to its parameter count, so small models that fit on edge devices fail on expert problems, which ne...

By Kenan Alkiek, David Jurgens, Vinod Vydiswaran

llms fine-tuning benchmarks

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

One email a morning, machine-written

Related stories

Comparing RAG and GraphRAG for Page-Level Retrieval Question Answering on a Math Textbook

The Retriever Should Remember: Experience-Amortized Reranking for Long-Term Agent Memory

EAR: Entity-Aware Partitioning Approach for Retrieval-Augmented Generation Development

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

Instruction Retrieval at Inference Time for Small Language Models

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