paper-with-me

홈 › Papers

Beyond Goldfish Memory: Long-Term Open-Domain Conversation

2021-07-15 · ACL 2022 5 · Jing Xu, Arthur Szlam, Jason Weston

Despite recent improvements in open-domain dialogue models, state of the art models are trained and evaluated on short conversations with little context. In contrast, the long-term conversation setting has hardly been studied. In this work we collect and release a human-human dataset consisting of multiple chat sessions whereby the speaking partners learn about each other's interests and discuss the things they have learnt from past sessions. We show how existing models trained on existing datasets perform poorly in this long-term conversation setting in both automatic and human evaluations, and we study long-context models that can perform much better. In particular, we find retrieval-augmented methods and methods with an ability to summarize and recall previous conversations outperform the standard encoder-decoder architectures currently considered state of the art.

📄 PDF Abstract BibTeX arXiv:2107.07567

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderRetrieval

Similar Papers 제목 키워드 기반

Goldfish: Vision-Language Understanding of Arbitrarily Long Videos

2024-07-17 · Kirolos Ataallah, Xiaoqian Shen, Eslam Abdelrahman, Essam Sleiman 외

Most current LLM-based models for video understanding can process videos within minutes. However, they struggle with lengthy videos due to challenges such as "noise and redundancy", as well as "memory and computation" co…

RetrievalVideo Understanding

Goldfish: Monolingual Language Models for 350 Languages

2024-08-19 · Tyler A. Chang, Catherine Arnett, Zhuowen Tu, Benjamin K. Bergen

For many low-resource languages, the only available language models are large multilingual models trained on many languages simultaneously. However, using FLORES perplexity as a metric, we find that these models perform …

Text Generation

ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense

2023-10-30 · Kankan Zhou, Eason Lai, Wei Bin Au Yeong, Kyriakos Mouratidis 외

Humans possess a strong capability for reasoning beyond common sense. For example, given an unconventional image of a goldfish laying on the table next to an empty fishbowl, a human would effortlessly determine that the …

Common Sense ReasoningLanguage ModelingLanguage Modelling

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

2025-09-17 · Project Apertus, Alejandro Hernández-Cano, Alexander Hägele, Allen Hao Huang 외 arxiv

We present Apertus, a fully open suite of large language models (LLMs) designed to address two systemic shortcomings in today's open model ecosystem: data compliance and multilingual representation. Unlike many prior mod…

From elephant to goldfish (and back): memory in stochastic Volterra processes

2023-06-05 · Ofelia Bonesini, Giorgia Callegaro, Martino Grasselli, Gilles Pagès

We propose a new theoretical framework that exploits convolution kernels to transform a Volterra path-dependent (non-Markovian) stochastic process into a standard (Markovian) diffusion process. This transformation is ach…