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.
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...
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.
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...
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...
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.
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.
SpectRAG is a retrieval‑augmented generation framework that uses weighted chunk graphs and spectral relevance propagation to select token‑budgeted context for multi‑hop reasoning. It builds a high‑recall seed set, expands it over a graph that encodes semantic similarity, document structure, and entity links, and re‑scores candidates with graph proximity and spectral information. Experiments on MultiHopRAG, UltraDomain, and long‑document QA show improved evidence recovery and competitive generation quality compared to dense, hybrid, and other RAG baselines.
arXiv:2605.06285v2 Announce Type: replace Abstract: Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks...
arXiv:2607. 04625v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) streamlines long-document understanding by leveraging retrieval mechanisms to restrict input images to a highly curated subset.
WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval proposes a new approach to address information asymmetry in cross-modal retrieval. The method introduces Adaptive Entropy Thresholding to calibrate uncertainty, Asymmetry-aware Wildcard Decoding to emit wildcards instead of forced identifiers, and Blind-Spot Re-ranking to evaluate expanded candidates. Experiments on the M-BEIR benchmark show that WIDE outperforms existing generative retrieval methods by reducing forced hallucination while keeping index structures compact.
arXiv:2609.15296v1 Announce Type: new Abstract: Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Rece...
The paper introduces LLM-QL, a dense retrieval model that harnesses large language models (LLMs) by maximizing query likelihood (QL) as an auxiliary task. It incorporates an Attention Block to limit predictive token attention to document tokens before the ending token and a Document Corruption component that masks parts of the document during prediction. Experiments on MS MARCO and BEIR datasets show that LLM-QL outperforms other LLM-based retrievers, and detailed analyses confirm the effectiveness of its components.