相关论文: Learning to Route Queries to Heads for Attention-b…

The strong capabilities of recent Large Language Models (LLMs) have made them highly effective for zero-shot re-ranking task. Attention-based re-ranking methods, which derive relevance scores directly from attention weights, offer an…

The strong zero-shot and long-context capabilities of recent Large Language Models (LLMs) have paved the way for highly effective re-ranking systems. Attention-based re-rankers leverage attention weights from transformer heads to produce…

The proliferation of large language models (LLMs) with varying computational costs and performance profiles presents a critical challenge for scalable, cost-effective deployment in real-world applications. We introduce a unified routing…

Recent work has identified retrieval heads, a subset of attention heads responsible for retrieving salient information in long-context language models (LMs), as measured by their copy-paste behavior in Needlein-a-Haystack tasks. In this…

Decoding-free reranking methods that read relevance signals directly from LLM attention weights offer significant latency advantages over autoregressive approaches, yet suffer from attention score homogenization: middle-context documents…

Neural retrievers are effective but brittle: underspecified or ambiguous queries can misdirect ranking even when relevant documents exist. Existing approaches address this brittleness only partially: LLMs rewrite queries without retriever…

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

Recently, the number of off-the-shelf Large Language Models (LLMs) has exploded with many open-source options. This creates a diverse landscape regarding both serving options (e.g., inference on local hardware vs remote LLM APIs) and model…

Built upon the existing analysis of retrieval heads in large language models, we propose an alternative reranking framework that trains models to estimate passage-query relevance using the attention scores of selected heads. This approach…

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Zero-shot document re-ranking with Large Language Models (LLMs) has evolved from Pointwise methods to Listwise and Setwise approaches that optimize computational efficiency. Despite their success, these methods predominantly rely on…

Effective document reranking is essential for improving search relevance across diverse applications. While Large Language Models (LLMs) excel at reranking due to their deep semantic understanding and reasoning, their high computational…

Effective representation learning from text has been an active area of research in the fields of NLP and text mining. Attention mechanisms have been at the forefront in order to learn contextual sentence representations. Current…

Advances in mechanistic interpretability have identified special attention heads, known as retrieval heads, that are responsible for retrieving information from the context. However, the role of these retrieval heads in improving model…

Large language model (LLM) routers improve the efficiency of multi-model systems by directing each query to the most appropriate model while leveraging the diverse strengths of heterogeneous LLMs. Most existing approaches frame routing as a…

In this work, we present a systematic and comprehensive empirical evaluation of state-of-the-art reranking methods, encompassing large language model (LLM)-based, lightweight contextual, and zero-shot approaches, with respect to their…

In information retrieval, learning to rank constructs a machine-based ranking model which given a query, sorts the search results by their degree of relevance or importance to the query. Neural networks have been successfully applied to…

Routing has emerged as a promising strategy for balancing performance and cost in large language model (LLM) systems that combine lightweight models with powerful but expensive large models. Recent studies show that \emph{probe routing},…

Search engines are crucial as they provide an efficient and easy way to access vast amounts of information on the internet for diverse information needs. User queries, even with a specific need, can differ significantly. Prior research has…

In this paper, we introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task. Existing document reranking methods based on large language models…