Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse

• URL: http://arxiv.org/abs/2410.21333v2
• Date: Tue, 05 Nov 2024 13:47:25 GMT
• Title: Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse
• Authors: Ryan Liu, Jiayi Geng, Addison J. Wu, Ilia Sucholutsky, Tania Lombrozo, Thomas L. Griffiths,
• Abstract summary: Chain-of-thought (CoT) has become a widely used strategy for working with large language and multimodal models. We identify characteristics of tasks where CoT reduces performance by drawing inspiration from cognitive psychology. We find that a diverse collection of state-of-the-art models exhibit significant drop-offs in performance when using inference-time reasoning.
• Score: 9.542503507653494
• License:
• Abstract: Chain-of-thought (CoT) prompting has become a widely used strategy for working with large language and multimodal models. While CoT has been shown to improve performance across many tasks, determining the settings in which it is effective remains an ongoing effort. In particular, it is still an open question in what settings CoT systematically reduces model performance. In this paper, we seek to identify the characteristics of tasks where CoT reduces performance by drawing inspiration from cognitive psychology, looking at cases where (i) verbal thinking or deliberation hurts performance in humans, and (ii) the constraints governing human performance generalize to language models. Three such cases are implicit statistical learning, visual recognition, and classifying with patterns containing exceptions. In extensive experiments across all three settings, we find that a diverse collection of state-of-the-art models exhibit significant drop-offs in performance (e.g., up to 36.3% absolute accuracy for OpenAI o1-preview compared to GPT-4o) when using inference-time reasoning compared to zero-shot counterparts. We also identify three tasks that satisfy condition (i) but not (ii), and find that while verbal thinking reduces human performance in these tasks, CoT retains or increases model performance. Overall, our results show that while there is not an exact parallel between the cognitive processes of models and those of humans, considering cases where thinking has negative consequences for human performance can help us identify settings where it negatively impacts models. By connecting the literature on human deliberation with evaluations of CoT, we offer a new tool that can be used in understanding the impact of prompt choices and inference-time reasoning.

Related papers

• How Hard is this Test Set? NLI Characterization by Exploiting Training Dynamics [49.9329723199239]
  We propose a method for the automated creation of a challenging test set without relying on the manual construction of artificial and unrealistic examples. We categorize the test set of popular NLI datasets into three difficulty levels by leveraging methods that exploit training dynamics. When our characterization method is applied to the training set, models trained with only a fraction of the data achieve comparable performance to those trained on the full dataset.
  arXiv  Detail & Related papers  (2024-10-04T13:39:21Z)
• Insights into Alignment: Evaluating DPO and its Variants Across Multiple Tasks [38.63497972682599]
  This study investigates the performance of alignment methods across three scenarios: keeping theSupervised Fine-Tuning part, skipping the SFT part, and utilizing an instruction-tuned model. Our evaluation spans a range of tasks including dialogue systems, reasoning, mathematical problem-solving, question answering, truthfulness, and multi-task understanding. Key observations reveal that alignment methods achieve optimal performance with smaller training data subsets, exhibit limited effectiveness in reasoning tasks yet significantly impact mathematical problem-solving, and employing an instruction-tuned model notably influences truthfulness.
  arXiv  Detail & Related papers  (2024-04-23T03:55:01Z)
• Corpus Considerations for Annotator Modeling and Scaling [9.263562546969695]
  We show that the commonly used user token model consistently outperforms more complex models. Our findings shed light on the relationship between corpus statistics and annotator modeling performance.
  arXiv  Detail & Related papers  (2024-04-02T22:27:24Z)
• Prompt Perturbation Consistency Learning for Robust Language Models [47.021022978847036]
  Large language models (LLMs) have demonstrated impressive performance on a number of natural language processing tasks. We show that fine-tuning sufficiently large LLMs can produce IC-SF performance comparable to discriminative models. We propose an efficient mitigation approach, Prompt Perturbation Consistency Learning (PPCL), which works by regularizing the divergence between losses from clean and perturbed samples.
  arXiv  Detail & Related papers  (2024-02-24T15:00:58Z)
• On the Compositional Generalization Gap of In-Context Learning [73.09193595292233]
  We look at the gap between the in-distribution (ID) and out-of-distribution (OOD) performance of such models in semantic parsing tasks with in-context learning. We evaluate four model families, OPT, BLOOM, CodeGen and Codex on three semantic parsing datasets.
  arXiv  Detail & Related papers  (2022-11-15T19:56:37Z)
• Planning for Sample Efficient Imitation Learning [52.44953015011569]
  Current imitation algorithms struggle to achieve high performance and high in-environment sample efficiency simultaneously. We propose EfficientImitate, a planning-based imitation learning method that can achieve high in-environment sample efficiency and performance simultaneously. Experimental results show that EI achieves state-of-the-art results in performance and sample efficiency.
  arXiv  Detail & Related papers  (2022-10-18T05:19:26Z)
• An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs [67.23285413610243]
  Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models. We study the effect of knowledge sampling strategies and sizes that can be used to generate synthetic data for adapting language models.
  arXiv  Detail & Related papers  (2022-05-21T19:49:04Z)
• On Modality Bias Recognition and Reduction [70.69194431713825]
  We study the modality bias problem in the context of multi-modal classification. We propose a plug-and-play loss function method, whereby the feature space for each label is adaptively learned. Our method yields remarkable performance improvements compared with the baselines.
  arXiv  Detail & Related papers  (2022-02-25T13:47:09Z)
• A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics [131.93113552146195]
  We present a new dataset, Handwritten arithmetic with INTegers (HINT), to examine machines' capability of learning generalizable concepts. In HINT, machines are tasked with learning how concepts are perceived from raw signals such as images. We undertake extensive experiments with various sequence-to-sequence models, including RNNs, Transformers, and GPT-3.
  arXiv  Detail & Related papers  (2021-03-02T01:32:54Z)
• Modeling Score Distributions and Continuous Covariates: A Bayesian Approach [8.772459063453285]
  We develop a generative model of the match and non-match score distributions over continuous covariates. We use mixture models to capture arbitrary distributions and local basis functions. Three experiments demonstrate the accuracy and effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-09-21T02:41:20Z)

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.