R$^3$ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context

• URL: http://arxiv.org/abs/2310.16535v1
• Date: Wed, 25 Oct 2023 10:34:02 GMT
• Title: R$^3$ Prompting: Review, Rephrase and Resolve for Chain-of-Thought Reasoning in Large Language Models under Noisy Context
• Authors: Qingyuan Tian, Hanlun Zhu, Lei Wang, Yang Li, Yunshi Lan
• Abstract summary: We propose a novel prompting method, namely R$3$ prompting, for Chain-of-Thought (CoT) reasoning under noisy context. Our experiments show that R$3$ prompting significantly outperforms existing CoT prompting methods on five reasoning tasks under noisy context.
• Score: 12.475979274233458
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the help of Chain-of-Thought (CoT) prompting, Large Language Models (LLMs) have achieved remarkable performance on various reasoning tasks. However, most of them have been evaluated under noise-free context and the dilemma for LLMs to produce inaccurate results under the noisy context has not been fully investigated. Existing studies utilize trigger sentences to encourage LLMs to concentrate on the relevant information but the trigger has limited effect on final answer prediction. Inspired by interactive CoT method, where intermediate reasoning steps are promoted by multiple rounds of interaction between users and LLMs, we propose a novel prompting method, namely R$^3$ prompting, for CoT reasoning under noisy context. Specifically, R$^3$ prompting interacts with LLMs to perform key sentence extraction, variable declaration and answer prediction, which corresponds to a thought process of reviewing, rephrasing and resolving. The responses generated at the last interaction will perform as hints to guide toward the responses of the next interaction. Our experiments show that R$^3$ prompting significantly outperforms existing CoT prompting methods on five reasoning tasks under noisy context. With GPT-3.5-turbo, we observe 3.7% accuracy improvement on average on the reasoning tasks under noisy context compared to the most competitive prompting baseline. More analyses and ablation studies show the robustness and generalization of R$^3$ prompting method in solving reasoning tasks in LLMs under noisy context.

Related papers

• Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models [84.15513004135576]
  Current research enhances the reasoning performance of Large Language Models (LLMs) by sampling multiple reasoning chains and ensembling based on the answer frequency. This approach fails in scenarios where the correct answers are in the minority. We introduce a hierarchical reasoning aggregation framework AoR, which selects answers based on the evaluation of reasoning chains.
  arXiv  Detail & Related papers  (2024-05-21T17:12:19Z)
• Can large language models explore in-context? [87.49311128190143]
  We deploy Large Language Models as agents in simple multi-armed bandit environments. We find that the models do not robustly engage in exploration without substantial interventions.
  arXiv  Detail & Related papers  (2024-03-22T17:50:43Z)
• Comparing Plausibility Estimates in Base and Instruction-Tuned Large Language Models [50.15455336684986]
  We compare base and instruction-tuned LLM performance on an English sentence plausibility task via explicit prompting and implicit estimation. Experiment 1 shows that, across model architectures and plausibility datasets, log likelihood ($textitLL$) scores are the most reliable indicator of sentence plausibility. Experiment 2 shows that $textitLL$ scores across models are modulated by context in the expected way, showing high performance on three metrics of context-sensitive plausibility.
  arXiv  Detail & Related papers  (2024-03-21T22:08:44Z)
• Generating Chain-of-Thoughts with a Pairwise-Comparison Approach to Searching for the Most Promising Intermediate Thought [70.30423016640749]
  Chain-of-thoughts (CoT) methods were proposed to guide large language models to reason step-by-step, enabling problem solving from simple to complex. The evaluation from the large language model (LLMs) is typically noisy and unreliable, potentially misleading the generation process in selecting promising intermediate thoughts. In this paper, motivated by Vapnik's principle, we use pairwise-comparison evaluation instead of point-wise scoring to search for promising intermediate thoughts.
  arXiv  Detail & Related papers  (2024-02-10T09:51:03Z)
• Graph Elicitation for Guiding Multi-Step Reasoning in Large Language Models [16.432208223793666]
  Chain-of-Thought prompting along with sub-question generation and answering has enhanced multi-step reasoning capabilities. We propose a GE-Reasoning method, which directs Large Language Models to generate proper sub-questions and corresponding answers. Our approach outperforms previous CoT prompting methods and their variants on multi-hop question answering benchmark datasets.
  arXiv  Detail & Related papers  (2023-11-16T10:36:08Z)
• LINC: A Neurosymbolic Approach for Logical Reasoning by Combining Language Models with First-Order Logic Provers [60.009969929857704]
  Logical reasoning is an important task for artificial intelligence with potential impacts on science, mathematics, and society. In this work, we reformulating such tasks as modular neurosymbolic programming, which we call LINC. We observe significant performance gains on FOLIO and a balanced subset of ProofWriter for three different models in nearly all experimental conditions we evaluate.
  arXiv  Detail & Related papers  (2023-10-23T17:58:40Z)
• Revisiting Large Language Models as Zero-shot Relation Extractors [8.953462875381888]
  Relation extraction (RE) consistently involves a certain degree of labeled or unlabeled data even if under zero-shot setting. Recent studies have shown that large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt. This work focuses on the study of exploring LLMs as zero-shot relation extractors.
  arXiv  Detail & Related papers  (2023-10-08T06:17:39Z)
• Learning to Ask Conversational Questions by Optimizing Levenshtein Distance [83.53855889592734]
  We introduce a Reinforcement Iterative Sequence Editing (RISE) framework that optimize the minimum Levenshtein distance (MLD) through explicit editing actions. RISE is able to pay attention to tokens that are related to conversational characteristics. Experimental results on two benchmark datasets show that RISE significantly outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-06-30T08:44:19Z)

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.