Augmented Language Models: a Survey

Abstract

This survey reviews works in which language models (LMs) are augmented with reasoning skills and the ability to use tools. The former is defined as decomposing a potentially complex task into simpler subtasks while the latter consists in calling external modules such as a code interpreter. LMs can leverage these augmentations separately or in combination via heuristics, or learn to do so from demonstrations. While adhering to a standard missing tokens prediction objective, such augmented LMs can use various, possibly non-parametric external modules to expand their context processing ability, thus departing from the pure language modeling paradigm. We therefore refer to them as Augmented Language Models (ALMs). The missing token objective allows ALMs to learn to reason, use tools, and even act, while still performing standard natural language tasks and even outperforming most regular LMs on several benchmarks. In this work, after reviewing current advance in ALMs, we conclude that this new research direction has the potential to address common limitations of traditional LMs such as interpretability, consistency, and scalability issues.

Cited by in corpus (18)

• A Taxonomy of Prompt Modifiers for Text-To-Image Generation
• Thrilled by Your Progress! Large Language Models (GPT-4) No Longer Struggle to Pass Assessments in Higher Education Programming Courses
• Opening up ChatGPT: Tracking openness, transparency, and accountability in instruction-tuned text generators
• ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language
• LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers
• Incremental Learning of Humanoid Robot Behavior from Natural Interaction and Large Language Models
• QuIM-RAG: Advancing Retrieval-Augmented Generation with Inverted Question Matching for Enhanced QA Performance
• Large Knowledge Model: Perspectives and Challenges
• Multimodal Neural Databases
• Transforming Agency. On the mode of existence of Large Language Models
• Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer?
• Complex QA and language models hybrid architectures, Survey
• Automated Theorem Provers Help Improve Large Language Model Reasoning
• Assessing the nature of large language models: A caution against anthropocentrism
• Kilonova Light Curve Parameter Estimation Using Likelihood-Free Inference
• A Glitch in the Matrix? Locating and Detecting Language Model Grounding with Fakepedia
• Towards Improving Interpretability of Language Model Generation through a Structured Knowledge Discovery Approach
• The Emergence of Cognition and Computation: A Physicalistic Perspective