arXiv Computation and Language November 4, 2026 By Youmin Ko, Jihong Jeong, Hyunjoon Kim

ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens

Read the original on arXiv Computation and Language →

ShiftRAG is a new retrieval‑augmented generation framework that decouples discriminative retrieval learning from autoregressive generation while still using a single LLM backbone. It addresses the textual bottleneck of existing RAG pipelines by projecting retrieval alignments into continuous soft tokens, creating a high‑bandwidth interface that feeds retrieval signals into the generator. The approach also introduces a soft orthogonality objective to reduce rank collapse and layer‑wise relevance dynamics to preserve fine‑grained latent space, resulting in significant improvements in retrieval and question‑answering performance over state‑of‑the‑art baselines.

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

Oct 7

Rethinking Knowledge Retrieval for Generation: A Survey on RAG Architectures and Applications

arXiv:2610.01936v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across natural language tasks but remain fundamentally limited by...

By Meghana Sunil, Shravya V, Shravan Venkatraman, Joe Dhanith PR

llms rag reinforcement-learning safety

arXiv AI

Oct 28

Latent Abstraction for Retrieval-Augmented Generation

The paper introduces LAnR (Latent Abstraction for Retrieval-Augmented Generation), a unified framework where a single large language model jointly encodes, retrieves, and generates within its latent space. Instead of generating natural language queries, LAnR produces dense retrieval vectors from a designated [PRED] token and matches them against encoded document representations from the same model. An adaptive MLP control head decides when sufficient evidence has been retrieved, eliminating the need for a separate retriever and explicit token-level stopping reasoning. Experiments on six QA benchmarks show that LAnR outperforms existing RAG methods while improving inference efficiency by reducing retrieval calls and tightening model integration.

By Ha Lan N. T, Minh-Anh Nguyen, Dung D. Le

llms rag diffusion benchmarks safety

arXiv Machine Learning

Sep 22

Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation

arXiv:2609.22162v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves the factuality of large language models (LLMs) and vision-language models (VLMs) by grounding generatio...

By Can Peng, Yu Liu, Yingyu Yang, Anjie Le, Yuyuan Liu, Qianye Yang, J. Alison Noble

llms rag nlp multimodal benchmarks

arXiv Computation and Language

Sep 15

Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question Answering

arXiv:2609.07093v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models (LLMs) to answer questions by accessing external knowledge and has been widely a...

By Yifan Wang, Xinkui Lin, Yongxiu Xu, Shen Gao, Ruochen Yang, Kun Huang, Yubin Wang, Jie Wu, Wei Liu, Jian Luan, Hongbo Xu, Shuo Shang

llms rag nlp benchmarks

arXiv Machine Learning

Sep 10

Retrieval-augmented Decoding for Improving Truthfulness in Open-ended Generation

The paper introduces Retrieval-Augmented Decoding (RAD), a decoding-time method that improves the truthfulness of large language models without retraining. RAD uses a small reference set of up to ten annotated examples to build a grounding space of context embeddings and next-token logits, which it retrieves and aggregates during inference to shape the model’s output. Experiments on four open-ended generation benchmarks and four different LLMs show that RAD consistently outperforms strong baselines and generalizes well across tasks.

By Manh Nguyen, Sunil Gupta, Hung Le

llms rag reinforcement-learning fine-tuning benchmarks

Hugging Face Trending Papers

Sep 3

WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval

The paper introduces WIDE, a method for cross‑modal generative retrieval that tackles information asymmetry between text queries and visual candidates. WIDE uses Adaptive Entropy Thresholding to set uncertainty limits, Asymmetry‑aware Wildcard Decoding to emit wildcards where the model lacks fine‑grained detail, and Blind‑Spot Re‑ranking to score an expanded candidate set with both discrete confidence and continuous similarity. Experiments on the M‑BEIR benchmark show that WIDE reduces forced hallucination and outperforms existing generative retrieval approaches while keeping index structures compact.

multimodal benchmarks safety