Distribution-Aligned Fine-Tuning for Efficient Neural Retrieval
Dual-encoder-based neural retrieval models achieve appreciable performance and complement traditional lexical retrievers well due to their semantic matching capabilities, which makes them a common choice for hybrid IR systems. However, these models exhibit a performance bottleneck in the online query encoding step, as the corresponding query encoders are usually large and complex Transformer models. In this paper we investigate heterogeneous dual-encoder models, where the two encoders are separate models that do not share parameters or initializations. We empirically show that heterogeneous dual-encoders are susceptible to collapsing representations, causing them to output constant trivial representations when they are fine-tuned using a standard contrastive loss due to a distribution mismatch. We propose DAFT, a simple two-stage fine-tuning approach that aligns the two encoders in order to prevent them from collapsing. We further demonstrate how DAFT can be used to train efficient heterogeneous dual-encoder models using lightweight query encoders.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
Fine-tuning large language models (LLMs) can lead to unintended out-of-distribution generalization. Standard approaches to this problem rely on modifying training data, for example by adding data that better specify the …
Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension
Existing large video-language models (LVLMs) struggle to comprehend long videos correctly due to limited context. To address this problem, fine-tuning long-context LVLMs and employing GPT-based agents have emerged as pro…
GPUMMEobject-detectionObject Detection+9Conversational Factor Information Retrieval Model (ConFIRM)
This paper introduces the Conversational Factor Information Retrieval Method (ConFIRM), a novel approach to fine-tuning large language models (LLMs) for domain-specific retrieval tasks. ConFIRM leverages the Five-Factor …
GPUInformation Retrievalintent-classificationIntent Classification+3Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval
Large Language Model-based Dense Retrieval (LLM-DR) optimizes over numerous heterogeneous fine-tuning collections from different domains. However, the discussion about its training data distribution is still minimal. Pre…
Domain GeneralizationLanguage ModelingLanguage ModellingLarge Language Model+1$k$NNProxy: Efficient Training-Free Proxy Alignment for Black-Box Zero-Shot LLM-Generated Text Detection
LLM-generated text (LGT) detection is essential for reliable forensic analysis and for mitigating LLM misuse. Existing LGT detectors can generally be categorized into two broad classes: learning-based approaches and zero…
Text Detection