Chained Tuning Leads to Biased Forgetting

• URL: http://arxiv.org/abs/2412.16469v1
• Date: Sat, 21 Dec 2024 03:51:58 GMT
• Title: Chained Tuning Leads to Biased Forgetting
• Authors: Megan Ung, Alicia Sun, Samuel J. Bell, Bhaktipriya Radharapu, Levent Sagun, Adina Williams,
• Abstract summary: We show that models trained on downstream tasks forget their safety tuning to a greater extent than models trained in the opposite order. We show that forgetting disproportionately impacts safety information about certain groups.
• Score: 20.181135590652985
• License:
• Abstract: Large language models (LLMs) are often fine-tuned for use on downstream tasks, though this can degrade capabilities learned during previous training. This phenomenon, often referred to as catastrophic forgetting, has important potential implications for the safety of deployed models. In this work, we first show that models trained on downstream tasks forget their safety tuning to a greater extent than models trained in the opposite order.Second, we show that forgetting disproportionately impacts safety information about certain groups. To quantify this phenomenon, we define a new metric we term biased forgetting. We conduct a systematic evaluation of the effects of task ordering on forgetting and apply mitigations that can help the model recover from the forgetting observed. We hope our findings can better inform methods for chaining the finetuning of LLMs in continual learning settings to enable training of safer and less toxic models.

Related papers

• Model for Peanuts: Hijacking ML Models without Training Access is Possible [5.005171792255858]
  Model hijacking is an attack where an adversary aims to hijack a victim model to execute a different task than its original one. We propose a simple approach for model hijacking at inference time named SnatchML to classify unknown input samples. We first propose a novel approach we call meta-unlearning, designed to help the model unlearn a potentially malicious task while training on the original dataset.
  arXiv  Detail & Related papers  (2024-06-03T18:04:37Z)
• Low-rank finetuning for LLMs: A fairness perspective [54.13240282850982]
  Low-rank approximation techniques have become the de facto standard for fine-tuning Large Language Models. This paper investigates the effectiveness of these methods in capturing the shift of fine-tuning datasets from the initial pre-trained data distribution. We show that low-rank fine-tuning inadvertently preserves undesirable biases and toxic behaviors.
  arXiv  Detail & Related papers  (2024-05-28T20:43:53Z)
• LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views [28.081794908107604]
  Fine-tuning is used to leverage the power of pre-trained foundation models in new downstream tasks. Recent studies have observed challenges in the generalization of fine-tuned models to unseen distributions. We propose a novel generalizable fine-tuning method LEVI, where the pre-trained model is adaptively ensembled layer-wise with a small task-specific model.
  arXiv  Detail & Related papers  (2024-02-07T08:16:40Z)
• Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem [12.185261182744377]
  This work conceptualizes one specific cause of poor transfer, accentuated in the reinforcement learning setting. A model deteriorates on the state subspace of the downstream task not visited in the initial phase of fine-tuning. We show that standard knowledge retention techniques mitigate the problem and thus allow us to take full advantage of the pre-trained capabilities.
  arXiv  Detail & Related papers  (2024-02-05T10:30:47Z)
• Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective [71.39995120597999]
  Modern machine learning models are vulnerable to adversarial and backdoor attacks. Such risks are heightened by the prevalent practice of collecting massive, internet-sourced datasets for training multimodal models. CleanCLIP is the current state-of-the-art approach to mitigate the effects of backdooring in multimodal models.
  arXiv  Detail & Related papers  (2023-11-25T06:55:13Z)
• Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization [53.04697800214848]
  Adversarial Training (AT) is pivotal in fortifying the robustness of deep learning models. AT methods, relying on direct iterative updates for target model's defense, frequently encounter obstacles such as unstable training and catastrophic overfitting. We present a general proxy guided defense framework, LAST' (bf Learn from the Pbf ast)
  arXiv  Detail & Related papers  (2023-10-19T13:13:41Z)
• Continual Learners are Incremental Model Generalizers [70.34479702177988]
  This paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. We find that the transfer quality of the representation often increases gradually without noticeable degradation in fine-tuning performance. We propose a new fine-tuning scheme, GLobal Attention Discretization (GLAD), that preserves rich task-generic representation during solving downstream tasks.
  arXiv  Detail & Related papers  (2023-06-21T05:26:28Z)
• Large Language Models with Controllable Working Memory [64.71038763708161]
  Large language models (LLMs) have led to a series of breakthroughs in natural language processing (NLP) What further sets these models apart is the massive amounts of world knowledge they internalize during pretraining. How the model's world knowledge interacts with the factual information presented in the context remains under explored.
  arXiv  Detail & Related papers  (2022-11-09T18:58:29Z)
• RelaxLoss: Defending Membership Inference Attacks without Losing Utility [68.48117818874155]
  We propose a novel training framework based on a relaxed loss with a more achievable learning target. RelaxLoss is applicable to any classification model with added benefits of easy implementation and negligible overhead. Our approach consistently outperforms state-of-the-art defense mechanisms in terms of resilience against MIAs.
  arXiv  Detail & Related papers  (2022-07-12T19:34:47Z)
• An Empirical Investigation of the Role of Pre-training in Lifelong Learning [21.995593026269578]
  We show that generic pre-training implicitly alleviates the effects of catastrophic forgetting when learning multiple tasks sequentially. We study this phenomenon by analyzing the loss landscape, finding that pre-trained weights appear to ease forgetting by leading to wider minima.
  arXiv  Detail & Related papers  (2021-12-16T19:00:55Z)

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.