paper-with-me

홈 › Papers

Distribution-Aligned Fine-Tuning for Efficient Neural Retrieval

2022-11-09 · Jurek Leonhardt, Marcel Jahnke, Avishek Anand

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.

📄 PDF Abstract BibTeX arXiv:2211.04942

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Adam 설명 없음

Similar Papers 제목 키워드 기반

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning

2025-07-22 · Helena Casademunt, Caden Juang, Adam Karvonen, Samuel Marks 외 arxiv

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

2024-11-20 · Yongdong Luo, Xiawu Zheng, Xiao Yang, Guilin Li 외

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+9

Conversational Factor Information Retrieval Model (ConFIRM)

2023-10-06 · Stephen Choi, William Gazeley, Siu Ho Wong, TingTing Li

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+3

Task-level Distributionally Robust Optimization for Large Language Model-based Dense Retrieval

2024-08-20 · Guangyuan Ma, Yongliang Ma, Xing Wu, Zhenpeng Su 외

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

2026-04-02 · Kahim Wong, Kemou Li, Haiwei Wu, Jiantao Zhou arxiv

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