BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief
Although pretrained language models (PTLMs) contain significant amounts of world knowledge, they can still produce inconsistent answers to questions when probed, even after specialized training. As a result, it can be hard to identify what the model actually "believes" about the world, making it susceptible to inconsistent behavior and simple errors. Our goal is to reduce these problems. Our approach is to embed a PTLM in a broader system that also includes an evolving, symbolic memory of beliefs -- a BeliefBank -- that records but then may modify the raw PTLM answers. We describe two mechanisms to improve belief consistency in the overall system. First, a reasoning component -- a weighted MaxSAT solver -- revises beliefs that significantly clash with others. Second, a feedback component issues future queries to the PTLM using known beliefs as context. We show that, in a controlled experimental setting, these two mechanisms result in more consistent beliefs in the overall system, improving both the accuracy and consistency of its answers over time. This is significant as it is a first step towards PTLM-based architectures with a systematic notion of belief, enabling them to construct a more coherent picture of the world, and improve over time without model retraining.
Code (0)
등록된 구현이 없습니다.
Tasks
Language ModelingLanguage ModellingWorld KnowledgeSimilar Papers 제목 키워드 기반
Enriching a Model's Notion of Belief using a Persistent Memory
(This is an old and now obsolete draft. See https://arxiv.org/abs/2109.14723 ("BeliefBank: Adding Memory to a Pre-Trained Language Model for a Systematic Notion of Belief") for the final paper).
Language ModelingLanguage ModellingDART-VLN: Test-Time Memory Decay and Anti-Loop Regularization for Discrete Vision-Language Navigation
Memory-based agents for discrete vision-language navigation (VLN) operate under partial observability and can exhibit systematic inference-time failures even with strong pretrained backbones. We focus on two recurring pr…
Vision-Language NavigationMemory Transformer
Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into co…
Language ModelingLanguage ModellingMachine TranslationNatural Language Understanding+3Memory Representation in Transformer
Transformer-based models have achieved state-of-the-art results in many natural language processing tasks. The self-attention architecture allows transformer to combine information from all elements of a sequence into co…
Language ModelingLanguage ModellingMachine TranslationQuestion AnsweringRecurrent Memory Transformer
Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and loc…
Language ModelingLanguage Modelling