Why think step by step? Reasoning emerges from the locality of experience

• URL: http://arxiv.org/abs/2304.03843v3
• Date: Thu, 2 Nov 2023 20:32:43 GMT
• Title: Why think step by step? Reasoning emerges from the locality of experience
• Abstract summary: We investigate why and how chain-of-thought reasoning is useful in language models. We show that reasoning is effective when training data consists of overlapping local clusters of variables.
• Score: 35.99870462573641
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans have a powerful and mysterious capacity to reason. Working through a set of mental steps enables us to make inferences we would not be capable of making directly even though we get no additional data from the world. Similarly, when large language models generate intermediate steps (a chain of thought) before answering a question, they often produce better answers than they would directly. We investigate why and how chain-of-thought reasoning is useful in language models, testing the hypothesis that reasoning is effective when training data consists of overlapping local clusters of variables that influence each other strongly. These training conditions enable the chaining of accurate local inferences to estimate relationships between variables that were not seen together in training. We prove that there will exist a "reasoning gap", where reasoning through intermediate variables reduces bias, for the simple case of an autoregressive density estimator trained on local samples from a chain-structured probabilistic model. We then test our hypothesis experimentally in more complex models, training an autoregressive language model on samples from Bayes nets but only including a subset of variables in each sample. We test language models' ability to match conditional probabilities with and without intermediate reasoning steps, finding that intermediate steps are only helpful when the training data is locally structured with respect to dependencies between variables. The combination of locally structured observations and reasoning is much more data-efficient than training on all variables. Our results illustrate how the effectiveness of reasoning step by step is rooted in the local statistical structure of the training data.

Related papers

• Causally Evaluating the Learnability of Formal Language Tasks [59.73001113068827]
  We rigorously investigate the relationship between data frequency and learnability.<n>We derive Kullback-Leibler divergence metrics to measure the learnability of specific sub-tasks.<n>Our experiments show that evaluating learnability without causal intervention leads to incorrect conclusions.
  arXiv  Detail & Related papers  (2026-06-08T17:58:36Z)
• Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks [24.55929874173401]
  We show that a language model's reasoning capabilities can be improved by training on datasets of chain-of-thought traces from more capable models.<n>Experiments show this approach can yield better performance on reasoning tasks than training on human-annotated datasets.
  arXiv  Detail & Related papers  (2025-12-24T07:35:55Z)
• Counterfactual reasoning: an analysis of in-context emergence [49.58529868457226]
  Large-scale neural language models (LMs) exhibit remarkable performance in in-context learning.<n>This work studies in-context counterfactual reasoning in language models, that is, to predict the consequences of changes under hypothetical scenarios.
  arXiv  Detail & Related papers  (2025-06-05T16:02:07Z)
• Improving the Natural Language Inference robustness to hard dataset by data augmentation and preprocessing [1.7487745673871375]
  Natural Language Inference (NLI) is the task of inferring whether the hypothesis can be justified by the given premise. We propose the data augmentation and preprocessing methods to solve the word overlap, numerical reasoning and length mismatch problems.
  arXiv  Detail & Related papers  (2024-12-10T01:49:23Z)
• QUITE: Quantifying Uncertainty in Natural Language Text in Bayesian Reasoning Scenarios [15.193544498311603]
  We present QUITE, a dataset of real-world Bayesian reasoning scenarios with categorical random variables and complex relationships. We conduct an extensive set of experiments, finding that logic-based models outperform out-of-the-box large language models on all reasoning types. Our results provide evidence that neuro-symbolic models are a promising direction for improving complex reasoning.
  arXiv  Detail & Related papers  (2024-10-14T12:44:59Z)
• Predicting Out-of-Domain Generalization with Neighborhood Invariance [59.05399533508682]
  We propose a measure of a classifier's output invariance in a local transformation neighborhood. Our measure is simple to calculate, does not depend on the test point's true label, and can be applied even in out-of-domain (OOD) settings. In experiments on benchmarks in image classification, sentiment analysis, and natural language inference, we demonstrate a strong and robust correlation between our measure and actual OOD generalization.
  arXiv  Detail & Related papers  (2022-07-05T14:55:16Z)
• Uncertainty Estimation for Language Reward Models [5.33024001730262]
  Language models can learn a range of capabilities from unsupervised training on text corpora. It is often easier for humans to choose between options than to provide labeled data, and prior work has achieved state-of-the-art performance by training a reward model from such preference comparisons. We seek to address these problems via uncertainty estimation, which can improve sample efficiency and robustness using active learning and risk-averse reinforcement learning.
  arXiv  Detail & Related papers  (2022-03-14T20:13:21Z)
• Impact of Pretraining Term Frequencies on Few-Shot Reasoning [51.990349528930125]
  We investigate how well pretrained language models reason with terms that are less frequent in the pretraining data. We measure the strength of this correlation for a number of GPT-based language models on various numerical deduction tasks. Although LMs exhibit strong performance at few-shot numerical reasoning tasks, our results raise the question of how much models actually generalize beyond pretraining data.
  arXiv  Detail & Related papers  (2022-02-15T05:43:54Z)
• Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests [87.60900567941428]
  A spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character. We study stress testing using the tools of causal inference.
  arXiv  Detail & Related papers  (2021-05-31T14:39:38Z)
• DEMI: Discriminative Estimator of Mutual Information [5.248805627195347]
  Estimating mutual information between continuous random variables is often intractable and challenging for high-dimensional data. Recent progress has leveraged neural networks to optimize variational lower bounds on mutual information. Our approach is based on training a classifier that provides the probability that a data sample pair is drawn from the joint distribution.
  arXiv  Detail & Related papers  (2020-10-05T04:19:27Z)
• Stable Prediction via Leveraging Seed Variable [73.9770220107874]
  Previous machine learning methods might exploit subtly spurious correlations in training data induced by non-causal variables for prediction. We propose a conditional independence test based algorithm to separate causal variables with a seed variable as priori, and adopt them for stable prediction. Our algorithm outperforms state-of-the-art methods for stable prediction.
  arXiv  Detail & Related papers  (2020-06-09T06:56:31Z)
• Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages [112.65994041398481]
  We propose a Bayesian generative model for the space of neural parameters. We infer the posteriors over such latent variables based on data from seen task-language combinations. Our model yields comparable or better results than state-of-the-art, zero-shot cross-lingual transfer methods.
  arXiv  Detail & Related papers  (2020-01-30T16:58:56Z)

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.