paper-with-me

Papers

Reverse Image Retrieval Cues Parametric Memory in Multimodal LLMs

2024-05-29 · Jialiang Xu, Michael Moor, Jure Leskovec

Despite impressive advances in recent multimodal large language models (MLLMs), state-of-the-art models such as from the GPT-4 suite still struggle with knowledge-intensive tasks. To address this, we consider Reverse Image Retrieval (RIR) augmented generation, a simple yet effective strategy to augment MLLMs with web-scale reverse image search results. RIR robustly improves knowledge-intensive visual question answering (VQA) of GPT-4V by 37-43%, GPT-4 Turbo by 25-27%, and GPT-4o by 18-20% in terms of open-ended VQA evaluation metrics. To our surprise, we discover that RIR helps the model to better access its own world knowledge. Concretely, our experiments suggest that RIR augmentation helps by providing further visual and textual cues without necessarily containing the direct answer to a query. In addition, we elucidate cases in which RIR can hurt performance and conduct a human evaluation. Finally, we find that the overall advantage of using RIR makes it difficult for an agent that can choose to use RIR to perform better than an approach where RIR is the default setting.

📄 PDF Abstract BibTeX arXiv:2405.18740

Code (1)

mi92/reverse-image-rag 공식 구현

Tasks

Image RetrievalQuestion AnsweringRetrievalVisual Question AnsweringVisual Question Answering (VQA)World Knowledge

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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…
Adam 설명 없음
Residual Connection 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Nonparametric Decoding for Generative Retrieval

2022-10-05 · Hyunji Lee, Jaeyoung Kim, Hoyeon Chang, Hanseok Oh 외

The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametri…

DecoderLanguage ModellingRetrievalText Retrieval

Retro-li: Small-Scale Retrieval Augmented Generation Supporting Noisy Similarity Searches and Domain Shift Generalization

2024-09-12 · Gentiana Rashiti, Geethan Karunaratne, Mrinmaya Sachan, Abu Sebastian 외

The retrieval augmented generation (RAG) system such as Retro has been shown to improve language modeling capabilities and reduce toxicity and hallucinations by retrieving from a database of non-parametric memory contain…

Language ModelingLanguage ModellingRAGRetrieval+3

TS-Memory: Plug-and-Play Memory for Time Series Foundation Models

2026-02-12 · Sisuo Lyu, Siru Zhong, Tiegang Chen, Weilin Ruan 외 arxiv

Time Series Foundation Models (TSFMs) achieve strong zero-shot forecasting through large-scale pre-training, but adapting them to downstream domains under distribution shift remains challenging. Existing solutions face a…

MLP Memory: A Retriever-Pretrained Memory for Large Language Models

2025-08-03 · Rubin Wei, Jiaqi Cao, Jiarui Wang, Jushi Kai 외 arxiv

Modern approaches to enhancing Large Language Models' factual accuracy and knowledge utilization face a fundamental trade-off: non-parametric retrieval-augmented generation (RAG) provides flexible access to external know…

A simple model of recognition and recall memory

2017-12-01 · NeurIPS 2017 12 · Nisheeth Srivastava, Edward Vul

We show that several striking differences in memory performance between recognition and recall tasks are explained by an ecological bias endemic in classic memory experiments - that such experiments universally involve m…

modelRetrieval