arXiv AI
The Emergence of Relevance Through Axiomatic Attention Patterns During LoRA Fine-Tuning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 31
Recall Before You Rank: Similarity-Guided Top-$K$ Reuse for Efficient Long-Context Attention
arXiv:2607. 27692v1 Announce Type: cross Abstract: Top-$K$ sparse attention reduces the cost of Softmax and value aggregation by attending to only a small subset of key--value (KV) entries.
arXiv AI
Jun 3
Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors
arXiv:2606. 02814v1 Announce Type: cross Abstract: Neural retrievers are trained to estimate query-document relevance from annotated query-document pairs.
arXiv AI
2d ago
From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism
arXiv:2608.21702v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds LLM generation on retrieved documents, but the standard terminal retrieval stage--dense-vector similarity,...
Hugging Face Trending Papers
Jun 22
KaLM-Reranker-V1: Fast but Not Late Interaction for Compressed Document Reranking
As retrieval systems scale, high-quality reranking becomes increasingly important. However, most existing rerankers, whether encoder-based or decoder-based, jointly encode the query and passage, tightly coupling their computation and limiting deployment efficiency as well as flexibility.
arXiv AI
2d ago
Unleashing the Power of LLMs in Dense Retrieval with Query Likelihood Modeling
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.
arXiv AI
Jun 11
The Structural Attention Tax: How Retrieval Format Hijacks In-Context Learning Independent of Content
arXiv:2606. 11198v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems inject external knowledge to improve LLM outputs, yet the format of injected content -- distinct from its semantic relevance -- can independently distort the model's attention distribution.