Chain-of-Thought Unfaithfulness as Disguised Accuracy

• URL: http://arxiv.org/abs/2402.14897v3
• Date: Fri, 21 Jun 2024 13:39:14 GMT
• Title: Chain-of-Thought Unfaithfulness as Disguised Accuracy
• Authors: Oliver Bentham, Nathan Stringham, Ana Marasović,
• Abstract summary: Chain-of-Thought (CoT) generations align with a large language model's (LLM) internal computations. A metric that measures a model's dependence on its CoT for producing an answer is proposed.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding the extent to which Chain-of-Thought (CoT) generations align with a large language model's (LLM) internal computations is critical for deciding whether to trust an LLM's output. As a proxy for CoT faithfulness, Lanham et al. (2023) propose a metric that measures a model's dependence on its CoT for producing an answer. Within a single family of proprietary models, they find that LLMs exhibit a scaling-then-inverse-scaling relationship between model size and their measure of faithfulness, and that a 13 billion parameter model exhibits increased faithfulness compared to models ranging from 810 million to 175 billion parameters in size. We evaluate whether these results generalize as a property of all LLMs. We replicate the experimental setup in their section focused on scaling experiments with three different families of models and, under specific conditions, successfully reproduce the scaling trends for CoT faithfulness they report. However, after normalizing the metric to account for a model's bias toward certain answer choices, unfaithfulness drops significantly for smaller less-capable models. This normalized faithfulness metric is also strongly correlated ($R^2$=0.74) with accuracy, raising doubts about its validity for evaluating faithfulness.

Related papers

• Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment [30.605500809158986]
  We propose a novel causal reward modeling approach that integrates causal inference to mitigate spurious correlations. Our approach mitigates various types of spurious correlations effectively, resulting in more reliable and fair alignment of LLMs with human preferences.
  arXiv  Detail & Related papers  (2025-01-16T16:00:37Z)
• REEF: Representation Encoding Fingerprints for Large Language Models [53.679712605506715]
  REEF computes and compares the centered kernel alignment similarity between the representations of a suspect model and a victim model. This training-free REEF does not impair the model's general capabilities and is robust to sequential fine-tuning, pruning, model merging, and permutations.
  arXiv  Detail & Related papers  (2024-10-18T08:27:02Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Calibrating Large Language Models with Sample Consistency [76.23956851098598]
  We explore the potential of deriving confidence from the distribution of multiple randomly sampled model generations, via three measures of consistency. Results show that consistency-based calibration methods outperform existing post-hoc approaches. We offer practical guidance on choosing suitable consistency metrics for calibration, tailored to the characteristics of various LMs.
  arXiv  Detail & Related papers  (2024-02-21T16:15:20Z)
• Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line [65.14099135546594]
  Recent test-time adaptation (TTA) methods drastically strengthen the ACL and AGL trends in models, even in shifts where models showed very weak correlations before. Our results show that by combining TTA with AGL-based estimation methods, we can estimate the OOD performance of models with high precision for a broader set of distribution shifts.
  arXiv  Detail & Related papers  (2023-10-07T23:21:25Z)
• Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation [50.920911532133154]
  The intrinsic ill-posedness and ordinal-sensitive nature of monocular depth estimation (MDE) models pose major challenges to the estimation of uncertainty degree. We propose to model the uncertainty of MDE models from the perspective of the inherent probability distributions. By simply introducing additional training regularization terms, our model, with surprisingly simple formations and without requiring extra modules or multiple inferences, can provide uncertainty estimations with state-of-the-art reliability.
  arXiv  Detail & Related papers  (2023-07-19T12:11:15Z)
• Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning [18.45898471459533]
  Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments. This paper proposes a novel approach to address spurious correlations during fine-tuning for a given domain of interest.
  arXiv  Detail & Related papers  (2023-04-08T05:20:33Z)
• Variable Importance Matching for Causal Inference [73.25504313552516]
  We describe a general framework called Model-to-Match that achieves these goals. Model-to-Match uses variable importance measurements to construct a distance metric. We operationalize the Model-to-Match framework with LASSO.
  arXiv  Detail & Related papers  (2023-02-23T00:43:03Z)

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.