paper-with-me

홈 › Papers

StreamingQA: A Benchmark for Adaptation to New Knowledge over Time in Question Answering Models

2022-05-23 · Adam Liška, Tomáš Kočiský, Elena Gribovskaya, Tayfun Terzi, Eren Sezener, Devang Agrawal, Cyprien de Masson d'Autume, Tim Scholtes, Manzil Zaheer, Susannah Young, Ellen Gilsenan-McMahon, Sophia Austin, Phil Blunsom, Angeliki Lazaridou

Knowledge and language understanding of models evaluated through question answering (QA) has been usually studied on static snapshots of knowledge, like Wikipedia. However, our world is dynamic, evolves over time, and our models' knowledge becomes outdated. To study how semi-parametric QA models and their underlying parametric language models (LMs) adapt to evolving knowledge, we construct a new large-scale dataset, StreamingQA, with human written and generated questions asked on a given date, to be answered from 14 years of time-stamped news articles. We evaluate our models quarterly as they read new articles not seen in pre-training. We show that parametric models can be updated without full retraining, while avoiding catastrophic forgetting. For semi-parametric models, adding new articles into the search space allows for rapid adaptation, however, models with an outdated underlying LM under-perform those with a retrained LM. For questions about higher-frequency named entities, parametric updates are particularly beneficial. In our dynamic world, the StreamingQA dataset enables a more realistic evaluation of QA models, and our experiments highlight several promising directions for future research.

📄 PDF Abstract BibTeX arXiv:2205.11388

Code (2)

deepmind/streamingqa 공식 구현
google-deepmind/streamingqa

Tasks

ArticlesQuestion Answering

Similar Papers 제목 키워드 기반

CMT: A Memory Compression Method for Continual Knowledge Learning of Large Language Models

2024-12-10 · Dongfang Li, Zetian Sun, Xinshuo Hu, Baotian Hu 외

Large Language Models (LLMs) need to adapt to the continuous changes in data, tasks, and user preferences. Due to their massive size and the high costs associated with training, LLMs are not suitable for frequent retrain…

Continual Learning

Exploring the Practicality of Generative Retrieval on Dynamic Corpora

2023-05-27 · Chaeeun Kim, Soyoung Yoon, Hyunji Lee, Joel Jang 외

Benchmarking the performance of information retrieval (IR) is mostly conducted with a fixed set of documents (static corpora). However, in realistic scenarios, this is rarely the case and the documents to be retrieved ar…

BenchmarkingInformation RetrievalRetrieval

Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass

2024-11-08 · Tong Chen, Hao Fang, Patrick Xia, Xiaodong Liu 외

Large language models (LMs) are typically adapted to improve performance on new contexts (\eg text prompts that define new tasks or domains) through fine-tuning or prompting. However, there is an accuracy compute tradeof…

In-Context LearningSelf-Supervised Learning

RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World

2026-04-06 · Hanbing Liu, Lang Cao, Yang Li arxiv

Large language models (LLMs) acquire most of their knowledge during pretraining, which ties them to a fixed snapshot of the world and makes adaptation to continuously evolving knowledge challenging. As facts, entities, a…

knowledge editing

Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams

2026-03-08 · Jiyeon Kim, Hyunji Lee, Dylan Zhou, Sue Hyun Park 외 arxiv

LLMs operating in dynamic real-world contexts often encounter knowledge that evolves continuously or emerges incrementally. To remain accurate and effective, models must adapt to newly arriving information on the fly. We…