Parrot Mind: Towards Explaining the Complex Task Reasoning of Pretrained Large Language Models with Template-Content Structure

• URL: http://arxiv.org/abs/2310.05452v2
• Date: Fri, 5 Apr 2024 08:07:59 GMT
• Title: Parrot Mind: Towards Explaining the Complex Task Reasoning of Pretrained Large Language Models with Template-Content Structure
• Authors: Haotong Yang, Fanxu Meng, Zhouchen Lin, Muhan Zhang,
• Abstract summary: We show that a structure called template-content structure (T-C structure) can reduce the possible space from exponential level to linear level. We demonstrate that models can achieve task composition, further reducing the space needed to learn from linear to logarithmic.
• Score: 66.33623392497599
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The pre-trained large language models (LLMs) have shown their extraordinary capacity to solve reasoning tasks, even on tasks that require a complex process involving multiple sub-steps. However, given the vast possible generation space of all the tasks, how the pretrained model learns the reasoning ability remains an open question. We firstly propose that an intrinsic structural constraint on the generated sequence of language-based reasoning -- we called it template-content structure (T-C structure) -- is the key to explain why LLMs can solve a large number of complex reasoning problems with limited training data by showing this structure can reduce the possible space from exponential level to linear level. Furthermore, by generalizing this structure to the hierarchical case, we demonstrate that models can achieve task composition, further reducing the space needed to learn from linear to logarithmic, thereby effectively learning on complex reasoning involving multiple steps. We provide both examples and formal theory of our T-C structure. We also experimentally validate the existence of the T-C structure in some current LLMs and its effectiveness for reasoning.

Related papers

• Limits of Deep Learning: Sequence Modeling through the Lens of Complexity Theory [15.24542569393982]
  Current models often rely on shortcuts rather than genuine multi-step reasoning, leading to performance degradation as task complexity increases. Our contributions provide a theoretical framework based on complexity theory to explain SSMs' limitations. Our experiments reveal significant performance drops as task complexity increases, even with Chain-of-Thought prompting.
  arXiv  Detail & Related papers  (2024-05-26T19:33:23Z)
• On the Empirical Complexity of Reasoning and Planning in LLMs [29.588100727466976]
  Chain-of-thought (CoT), tree-of-thought (ToT), and related techniques work surprisingly well in practice for some complex reasoning tasks with Large Language Models (LLMs) This work seeks the underlying reasons by conducting experimental case studies and linking the performance benefits to well-established sample and computational complexity principles in machine learning.
  arXiv  Detail & Related papers  (2024-04-17T03:34:27Z)
• Distilling LLMs' Decomposition Abilities into Compact Language Models [12.083499752124649]
  Large Language Models (LLMs) have demonstrated proficiency in their reasoning abilities. compact models offer customized training but often fall short in solving complex reasoning tasks.
  arXiv  Detail & Related papers  (2024-02-02T13:23:15Z)
• Can Large Language Models Understand Real-World Complex Instructions? [54.86632921036983]
  Large language models (LLMs) can understand human instructions, but struggle with complex instructions. Existing benchmarks are insufficient to assess LLMs' ability to understand complex instructions. We propose CELLO, a benchmark for evaluating LLMs' ability to follow complex instructions systematically.
  arXiv  Detail & Related papers  (2023-09-17T04:18:39Z)
• Physics of Language Models: Part 1, Learning Hierarchical Language Structures [51.68385617116854]
  Transformer-based language models are effective but complex, and understanding their inner workings is a significant challenge. We introduce a family of synthetic CFGs that produce hierarchical rules, capable of generating lengthy sentences. We demonstrate that generative models like GPT can accurately learn this CFG language and generate sentences based on it.
  arXiv  Detail & Related papers  (2023-05-23T04:28:16Z)
• Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs [67.043747188954]
  We propose a structure-modeled textual encoding framework for inductive logical reasoning over KGs. It encodes linearized query structures and entities using pre-trained language models to find answers. We conduct experiments on two inductive logical reasoning datasets and three transductive datasets.
  arXiv  Detail & Related papers  (2023-05-23T01:25:29Z)
• Unifying Structure Reasoning and Language Model Pre-training for Complex Reasoning [26.811507121199323]
  This paper proposes a unified learning framework that combines explicit structure reasoning and language pre-training to endow PLMs with the structure reasoning skill. It first identifies several elementary structures within contexts to construct structured queries and performs step-by-step reasoning along the queries to identify the answer entity. Experimental results on four datasets demonstrate that the proposed model achieves significant improvements in complex reasoning tasks involving diverse structures.
  arXiv  Detail & Related papers  (2023-01-21T08:18:11Z)
• Autoregressive Structured Prediction with Language Models [73.11519625765301]
  We describe an approach to model structures as sequences of actions in an autoregressive manner with PLMs. Our approach achieves the new state-of-the-art on all the structured prediction tasks we looked at.
  arXiv  Detail & Related papers  (2022-10-26T13:27:26Z)
• Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models [61.480085460269514]
  We propose a framework for building interpretable systems that learn to solve complex tasks by decomposing them into simpler ones solvable by existing models. We use this framework to build ModularQA, a system that can answer multi-hop reasoning questions by decomposing them into sub-questions answerable by a neural factoid single-span QA model and a symbolic calculator.
  arXiv  Detail & Related papers  (2020-09-01T23:45:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.