Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding

• URL: http://arxiv.org/abs/2409.03363v1
• Date: Thu, 5 Sep 2024 09:10:38 GMT
• Title: Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding
• Authors: Cheng Wang, Yiwei Wang, Bryan Hooi, Yujun Cai, Nanyun Peng, Kai-Wei Chang,
• Abstract summary: Existing methods typically analyze target text in isolation or solely with non-member contexts. We propose Con-ReCall, a novel approach that leverages the asymmetric distributional shifts induced by member and non-member contexts.
• Score: 118.75567341513897
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The training data in large language models is key to their success, but it also presents privacy and security risks, as it may contain sensitive information. Detecting pre-training data is crucial for mitigating these concerns. Existing methods typically analyze target text in isolation or solely with non-member contexts, overlooking potential insights from simultaneously considering both member and non-member contexts. While previous work suggested that member contexts provide little information due to the minor distributional shift they induce, our analysis reveals that these subtle shifts can be effectively leveraged when contrasted with non-member contexts. In this paper, we propose Con-ReCall, a novel approach that leverages the asymmetric distributional shifts induced by member and non-member contexts through contrastive decoding, amplifying subtle differences to enhance membership inference. Extensive empirical evaluations demonstrate that Con-ReCall achieves state-of-the-art performance on the WikiMIA benchmark and is robust against various text manipulation techniques.

Related papers

• On the loss of context-awareness in general instruction fine-tuning [101.03941308894191]
  Post-training methods such as supervised fine-tuning (SFT) on instruction-response pairs can harm existing capabilities learned during pretraining. We propose two methods to mitigate the loss of context awareness in instruct models: post-hoc attention steering on user prompts and conditional instruction fine-tuning with a context-dependency indicator.
  arXiv  Detail & Related papers  (2024-11-05T00:16:01Z)
• Annotator in the Loop: A Case Study of In-Depth Rater Engagement to Create a Bridging Benchmark Dataset [1.825224193230824]
  We describe a novel, collaborative, and iterative annotator-in-the-loop methodology for annotation. Our findings indicate that collaborative engagement with annotators can enhance annotation methods.
  arXiv  Detail & Related papers  (2024-08-01T19:11:08Z)
• ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods [56.073335779595475]
  We propose ReCaLL (Relative Conditional Log-Likelihood), a novel membership inference attack (MIA) ReCaLL examines the relative change in conditional log-likelihoods when prefixing target data points with non-member context. We conduct comprehensive experiments and show that ReCaLL achieves state-of-the-art performance on the WikiMIA dataset.
  arXiv  Detail & Related papers  (2024-06-23T00:23:13Z)
• READ: Improving Relation Extraction from an ADversarial Perspective [33.44949503459933]
  We propose an adversarial training method specifically designed for relation extraction (RE) Our approach introduces both sequence- and token-level perturbations to the sample and uses a separate perturbation vocabulary to improve the search for entity and context perturbations.
  arXiv  Detail & Related papers  (2024-04-02T16:42:44Z)
• C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
  c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
  arXiv  Detail & Related papers  (2024-02-17T11:28:08Z)
• Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition [4.7938839332508945]
  We propose a Prompt-based Logical Semantics Enhancement (PLSE) method for Implicit Discourse Relation Recognition (IDRR) Our method seamlessly injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction. Experimental results on PDTB 2.0 and CoNLL16 datasets demonstrate that our method achieves outstanding and consistent performance against the current state-of-the-art models.
  arXiv  Detail & Related papers  (2023-11-01T08:38:08Z)
• Context-faithful Prompting for Large Language Models [51.194410884263135]
  Large language models (LLMs) encode parametric knowledge about world facts. Their reliance on parametric knowledge may cause them to overlook contextual cues, leading to incorrect predictions in context-sensitive NLP tasks. We assess and enhance LLMs' contextual faithfulness in two aspects: knowledge conflict and prediction with abstention.
  arXiv  Detail & Related papers  (2023-03-20T17:54:58Z)
• Semantic Interactive Learning for Text Classification: A Constructive Approach for Contextual Interactions [0.0]
  We propose a novel interaction framework called Semantic Interactive Learning for the text domain. We frame the problem of incorporating constructive and contextual feedback into the learner as a task to find an architecture that enables more semantic alignment between humans and machines. We introduce a technique called SemanticPush that is effective for translating conceptual corrections of humans to non-extrapolating training examples.
  arXiv  Detail & Related papers  (2022-09-07T08:13:45Z)
• Semantics-Preserved Distortion for Personal Privacy Protection in Information Management [65.08939490413037]
  This paper suggests a linguistically-grounded approach to distort texts while maintaining semantic integrity. We present two distinct frameworks for semantic-preserving distortion: a generative approach and a substitutive approach. We also explore privacy protection in a specific medical information management scenario, showing our method effectively limits sensitive data memorization.
  arXiv  Detail & Related papers  (2022-01-04T04:01:05Z)

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.