Natural Language Embedded Programs for Hybrid Language Symbolic Reasoning
How can we perform computations over natural language representations to solve tasks that require symbolic and numeric reasoning? We propose natural language embedded programs (NLEP) as a unifying framework for addressing math/symbolic reasoning, natural language understanding, and instruction following tasks. Our approach prompts a language model to generate full Python programs that define functions over data structures which contain natural language representations of structured knowledge. A Python interpreter then executes the generated code and prints the output. Despite using a task-general prompt, we find that this approach can improve upon strong baselines across a range of different tasks including math and symbolic reasoning, text classification, question answering, and instruction following. We found that the generated programs are interpretable since they outline the exact reasoning process followed by the program interpreter.
Code (1)
Tasks
Instruction FollowingLanguage ModelingLanguage ModellingMathNatural Language UnderstandingQuestion Answeringtext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Logic-of-Thought: Empowering Large Language Models with Logic Programs for Solving Puzzles in Natural Language
Solving puzzles in natural language poses a long-standing challenge in AI. While large language models (LLMs) have recently shown impressive capabilities in a variety of tasks, they continue to struggle with complex puzz…
Natural Language UnderstandingAST-Based Deep Learning for Detecting Malicious PowerShell
With the celebrated success of deep learning, some attempts to develop effective methods for detecting malicious PowerShell programs employ neural nets in a traditional natural language processing setup while others empl…
Deep LearningGold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text
Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natura…
Question AnsweringProgram SynthesisAutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications
The advent of Large Language Models (LLMs) has profoundly transformed our lives, revolutionizing interactions with AI and lowering the barrier to AI usage. While LLMs are primarily designed for natural language interacti…
Program SynthesisModelling Natural Language, Programs, and their Intersection
As computers and information grow a more integral part of our world, it is becoming more and more important for humans to be able to interact with their computers in complex ways. One way to do so is by programming, but …
Semantic ParsingText Generation