In-Context Editing: Learning Knowledge from Self-Induced Distributions

• URL: http://arxiv.org/abs/2406.11194v2
• Date: Thu, 03 Oct 2024 15:13:58 GMT
• Title: In-Context Editing: Learning Knowledge from Self-Induced Distributions
• Authors: Siyuan Qi, Bangcheng Yang, Kailin Jiang, Xiaobo Wang, Jiaqi Li, Yifan Zhong, Yaodong Yang, Zilong Zheng,
• Abstract summary: We introduce Consistent In-Context Editing (ICE) to optimize toward a contextual distribution rather than a one-hot target. ICE enhances the robustness and effectiveness of gradient-based tuning methods, preventing overfitting and preserving the model's integrity. We analyze ICE across four critical aspects of knowledge editing: accuracy, locality, generalization, and linguistic quality, demonstrating its advantages.
• Score: 29.10148782152867
• License:
• Abstract: In scenarios where language models must incorporate new information efficiently without extensive retraining, traditional fine-tuning methods are prone to overfitting, degraded generalization, and unnatural language generation. To address these limitations, we introduce Consistent In-Context Editing (ICE), a novel approach leveraging the model's in-context learning capability to optimize toward a contextual distribution rather than a one-hot target. ICE introduces a simple yet effective optimization framework for the model to internalize new knowledge by aligning its output distributions with and without additional context. This method enhances the robustness and effectiveness of gradient-based tuning methods, preventing overfitting and preserving the model's integrity. We analyze ICE across four critical aspects of knowledge editing: accuracy, locality, generalization, and linguistic quality, demonstrating its advantages. Experimental results confirm the effectiveness of ICE and demonstrate its potential for continual editing, ensuring that the integrity of the model is preserved while updating information.

Related papers

• Learning-to-Defer for Extractive Question Answering [0.0]
  We introduce an adapted two-stage Learning-to-Defer mechanism that enhances decision-making by enabling selective deference to human experts or larger models without retraining language models in the context of question-answering. Our results demonstrate that deferring a minimal number of queries allows the smaller model to achieve performance comparable to their larger counterparts while preserving computing efficiency.
  arXiv  Detail & Related papers  (2024-10-21T08:21:00Z)
• Better Call SAUL: Fluent and Consistent Language Model Editing with Generation Regularization [48.07144492109635]
  Large language models need to be updated regularly. Model editing is challenging as it might also affect knowledge that is unrelated to the new data. We propose SAUL, a streamlined model editing method that uses sentence concatenation with augmented random facts for generation regularization.
  arXiv  Detail & Related papers  (2024-10-03T12:28:13Z)
• DiPT: Enhancing LLM reasoning through diversified perspective-taking [27.443341091299168]
  Existing work on improving language model reasoning typically explores a single solution path. Inspired by perspective-taking in social studies, this paper introduces DiPT, a novel approach. It allows the model to gain a deeper understanding of the problem's context and identify the most effective solution path.
  arXiv  Detail & Related papers  (2024-09-10T06:17:27Z)
• Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization [77.62516752323207]
  We introduce an orthogonal fine-tuning method for efficiently fine-tuning pretrained weights and enabling enhanced robustness and generalization. A self-regularization strategy is further exploited to maintain the stability in terms of zero-shot generalization of VLMs, dubbed OrthSR. For the first time, we revisit the CLIP and CoOp with our method to effectively improve the model on few-shot image classficiation scenario.
  arXiv  Detail & Related papers  (2024-07-11T10:35:53Z)
• Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models [25.212449683397647]
  This paper studies the integration of a contrastive learning objective for fine-tuning LLMs for implicit knowledge editing and controlled text generation. To facilitate training the model in a self-supervised fashion, we leverage an off-the-shelf LLM for training data generation.
  arXiv  Detail & Related papers  (2024-01-16T16:49:39Z)
• 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)
• Integrating Prior Knowledge in Post-hoc Explanations [3.6066164404432883]
  Post-hoc interpretability methods aim at explaining to a user the predictions of a trained decision model. We propose to define a cost function that explicitly integrates prior knowledge into the interpretability objectives. We propose a new interpretability method called Knowledge Integration in Counterfactual Explanation (KICE) to optimize it.
  arXiv  Detail & Related papers  (2022-04-25T13:09:53Z)
• NoiER: An Approach for Training more Reliable Fine-TunedDownstream Task Models [54.184609286094044]
  We propose noise entropy regularisation (NoiER) as an efficient learning paradigm that solves the problem without auxiliary models and additional data. The proposed approach improved traditional OOD detection evaluation metrics by 55% on average compared to the original fine-tuned models.
  arXiv  Detail & Related papers  (2021-08-29T06:58:28Z)
• Dialogue Summarization with Supporting Utterance Flow Modeling and Fact Regularization [58.965859508695225]
  We propose an end-to-end neural model for dialogue summarization with two novel modules. The supporting utterance flow modeling helps to generate a coherent summary by smoothly shifting the focus from the former utterances to the later ones. The fact regularization encourages the generated summary to be factually consistent with the ground-truth summary during model training.
  arXiv  Detail & Related papers  (2021-08-03T03:09:25Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)

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.