Iteratively Prompt Pre-trained Language Models for Chain of Thought

By Boshi Wang, Xiang Deng, Huan Sun. 2022

134 citations recorded by the source corpus.

While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a “chain of thought” for these tasks, how can we equip PLMs with such abilities? In this work, we explore an iterative prompting framework, a new prompting paradigm which progressively elicits relevant knowledge from PLMs for multi-step inference. We identify key limitations of existing prompting methods, namely they are either restricted to queries with a single identifiable relation/predicate, or being agnostic to input contexts, which makes it difficult to capture variabilities across different inference steps. We propose an iterative context-aware prompter, which addresses these limitations by learning to dynamically synthesize prompts conditioned on the current step’s contexts. Experiments on three datasets involving multi-step reasoning show the effectiveness of the iterative scheme and the context-aware prompter design.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Prompting & Reasoning

Citations in the corpus

Augmented Language Models: a Survey (2023, methodology): “For the latter, examples of reasoning are typically used in the larger context of instruction tuning (Mishra et al., 2021; Sanh et al., 2022; Wang et al., 2022d; Ouyang et al., 2022), where, more generally, an LM’s ability to follow instructions is improved based on human-labeled examples.”
Multimodal Chain-of-Thought Reasoning in Language Models (2023, neutral): “For Zero-Shot-CoT, Kojima et al. (2022) showed that LLMs are decent zero-shot reasoners by adding a prompt like “Let’s think step by step” after the test question to invoke CoT reasoning.”
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks (2023, background): “It would be interesting to apply more advanced prompting techniques (Wang et al., 2023a, 2022a; Yao et al., 2023; Sordoni et al., 2023; i.a. ) to our counterfactual tasks.”
LAMBADA: Backward Chaining for Automated Reasoning in Natural Language (2022, unknown): “Modular Reasoning: These approaches break the problem into smaller modules and use separate LMs to solve each module (Zhou et al., 2022; Khot et al., 2023; Sprague et al., 2022; Zhou et al., 2023; Dua et al., 2022; Wang et al., 2022; Schlag et al., 2023).”
Reasoning with Language Model Prompting: A Survey (2022, unknown): “Multi-Stage iCAP (Wang et al., 2022a), SI (Creswell et al.”
A Survey on In-context Learning (2022, methodology): “Despite being promising, there are also interesting questions and intriguing properties that re-a MetaICL (Min et al., 2022b), OPT-IML (Iyer et al., 2022), FLAN (Wei et al., 2022a), Super-NaturalInstructions (Wang et al., 2022c), Scaling Instruction (Chung et al., 2022), Symbol Tuning (Wei et al., 2”
A Survey for In-context Learning (2023, background): “, 2022), iCAP (Wang et al., 2022a), Least-to-Most (Zhou et al.”
A Survey of Large Language Models (2023, unknown): “Several studies have proven that iterative prompting can elicit relevant knowledge to achieve better performance in sub-tasks [347, 348].”
Explaining Competitive-Level Programming Solutions using LLMs (2023, methodology): “Another technique that builds upon CoT is the self-consistency decoding strategy (Wang et al., 2022b).”
Towards Reasoning in Large Language Models: A Survey (2022, background): “In addition, Wang et al. (2022b) conduct ablation experiments on CoT and find that LLMs may also perform reasoning while prompting with invalid rationals.”
MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning (2023, background): “Later on, several other works (Drozdov et al., 2023; Zhou et al., 2023c; Nye et al., 2022; Wang et al., 2022a; 2023a; Li et al., 2023b; Wang et al., 2023d; Yu et al., 2023) (Chen et al., 2022).”