Debate Helps Weak-to-Strong Generalization

• URL: http://arxiv.org/abs/2501.13124v1
• Date: Tue, 21 Jan 2025 05:36:13 GMT
• Title: Debate Helps Weak-to-Strong Generalization
• Authors: Hao Lang, Fei Huang, Yongbin Li,
• Abstract summary: We investigate ways of improving human supervision with a strong pretrained model and then supervise the strong model with enhanced weak human supervision.<n>We find that debate can assist a weak model in extracting trustworthy information from an untrustworthy strong model.<n>Experiments on the OpenAI weak-to-strong NLP benchmarks show that the combination approach leads to better alignment.
• Score: 68.70065254564642
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Common methods for aligning already-capable models with desired behavior rely on the ability of humans to provide supervision. However, future superhuman models will surpass the capability of humans. Therefore, humans will only be able to weakly supervise superhuman models. This expected deficiency of human evaluation would weaken the safety of future AI systems. Scalable oversight and weak-to-strong generalization are two complementary approaches to tackle this issue. In this paper, we attempt to combine the strengths of these two approaches to further improve alignment. Specifically, we investigate ways of improving human supervision with a strong pretrained model and then supervise the strong model with enhanced weak human supervision. To make iterative empirical progress, we consider an analogy: can we use a strong model to improve weak model supervision and then use it to supervise the strong model? We empirically test it by finetuning a small weak model on ground truth labels with the additional help from a large strong model, and then finetuning the strong model on labels generated by the weak model. We find that debate can assist a weak model in extracting trustworthy information from an untrustworthy strong model, which provides leverage as context on samples when training a weak model. We also show that an ensemble of weak models helps exploit long arguments generated by strong model debaters and obtain a more robust supervision estimate. Extensive experiments on the OpenAI weak-to-strong NLP benchmarks show that the combination approach leads to better alignment, which indicates that debate has the potential to help weak-to-strong generalization.

Related papers

• How to Mitigate Overfitting in Weak-to-strong Generalization? [50.37526669608372]
  Weak-to-strong generalization aims to elicit the capabilities of strong models through weak supervisors. Strong models exhibit significant overfitting in weak-to-strong generalization. We propose a two-stage framework that simultaneously improves the quality of supervision signals and the quality of input questions.
  arXiv  Detail & Related papers  (2025-03-06T09:32:39Z)
• Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions [12.956498486569103]
  Weak-to-Strong Generalization (W2SG) serves as an important analogy for understanding how humans might guide superhuman intelligence in the future. We show that W2SG can be characterized using kernels derived from the principal components of weak and strong models' internal representations.
  arXiv  Detail & Related papers  (2025-02-02T01:11:51Z)
• Teaching Models to Balance Resisting and Accepting Persuasion [69.68379406317682]
  Large language models (LLMs) are susceptible to persuasion, which can pose risks when models are faced with an adversarial interlocutor. We show that optimizing models for only one side results in poor performance on the other. In order to balance positive and negative persuasion, we introduce Persuasion-Balanced Training (or PBT)
  arXiv  Detail & Related papers  (2024-10-18T16:49:36Z)
• Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization [68.62228569439478]
  We investigate whether there exists an issue of weak-to-strong deception. We find that the deception intensifies as the capability gap between weak and strong models increases. Our work highlights the urgent need to pay more attention to the true reliability of superalignment.
  arXiv  Detail & Related papers  (2024-06-17T11:36:39Z)
• Quantifying the Gain in Weak-to-Strong Generalization [14.453654853392619]
  We show that the improvement in performance achieved by strong models over their weaker counterparts is quantified by the misfit error incurred by the strong model on labels generated by the weaker model. For instance, we can predict the amount by which the strong model will improve over the weak model, and also choose among different weak models to train the strong model, based on its misfit error.
  arXiv  Detail & Related papers  (2024-05-24T00:14:16Z)
• Weak-to-Strong Extrapolation Expedites Alignment [135.12769233630362]
  We propose a method called ExPO to boost models' alignment with human preference. We demonstrate that ExPO consistently improves off-the-shelf DPO/RLHF models. We shed light on the essence of ExPO amplifying the reward signal learned during alignment training.
  arXiv  Detail & Related papers  (2024-04-25T17:39:50Z)
• Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models [55.919653720979824]
  This paper focuses on the concept of weak-to-strong generalization, which involves using a weaker model to supervise a stronger one. We introduce a novel and adaptively adjustable loss function for weak-to-strong supervision. Our approach not only exceeds the performance benchmarks set by strong-to-strong generalization but also surpasses the outcomes of fine-tuning strong models with whole datasets.
  arXiv  Detail & Related papers  (2024-02-06T06:30:34Z)
• Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision [55.196139002977525]
  Superhuman models will behave in complex ways too difficult for humans to reliably evaluate. Can weak model supervision elicit the full capabilities of a much stronger model? We find that when we naively finetune strong pretrained models on labels generated by a weak model, they consistently perform better than their weak supervisors.
  arXiv  Detail & Related papers  (2023-12-14T23:07:33Z)

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.