Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation Models

• URL: http://arxiv.org/abs/2402.17671v1
• Date: Tue, 27 Feb 2024 16:44:09 GMT
• Title: Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation Models
• Authors: Yunpeng Huang, Yaonan Gu, Jingwei Xu, Zhihong Zhu, Zhaorun Chen, Xiaoxing Ma
• Abstract summary: In-context learning (ICL) paradigm thrives but also encounters issues such as toxicity, hallucination, disparity, adversarial vulnerability, and inconsistency. Ensuring the reliability and responsibility of foundation models (FMs) is crucial for the sustainable development of the AI ecosystem.
• Score: 10.889829033820433
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As foundation models (FMs) continue to shape the landscape of AI, the in-context learning (ICL) paradigm thrives but also encounters issues such as toxicity, hallucination, disparity, adversarial vulnerability, and inconsistency. Ensuring the reliability and responsibility of FMs is crucial for the sustainable development of the AI ecosystem. In this concise overview, we investigate recent advancements in enhancing the reliability and trustworthiness of FMs within ICL frameworks, focusing on four key methodologies, each with its corresponding subgoals. We sincerely hope this paper can provide valuable insights for researchers and practitioners endeavoring to build safe and dependable FMs and foster a stable and consistent ICL environment, thereby unlocking their vast potential.

Related papers

• TRACE: TRansformer-based Attribution using Contrastive Embeddings in LLMs [50.259001311894295]
  We propose a novel TRansformer-based Attribution framework using Contrastive Embeddings called TRACE. We show that TRACE significantly improves the ability to attribute sources accurately, making it a valuable tool for enhancing the reliability and trustworthiness of large language models.
  arXiv  Detail & Related papers  (2024-07-06T07:19:30Z)
• Confidence Under the Hood: An Investigation into the Confidence-Probability Alignment in Large Language Models [14.5291643644017]
  We introduce the concept of Confidence-Probability Alignment. We probe the alignment between models' internal and expressed confidence. Among the models analyzed, OpenAI's GPT-4 showed the strongest confidence-probability alignment.
  arXiv  Detail & Related papers  (2024-05-25T15:42:04Z)
• When to Trust LLMs: Aligning Confidence with Response Quality [49.371218210305656]
  We propose CONfidence-Quality-ORDer-preserving alignment approach (CONQORD) It integrates quality reward and order-preserving alignment reward functions. Experiments demonstrate that CONQORD significantly improves the alignment performance between confidence and response accuracy.
  arXiv  Detail & Related papers  (2024-04-26T09:42:46Z)
• Position Paper: Assessing Robustness, Privacy, and Fairness in Federated Learning Integrated with Foundation Models [39.86957940261993]
  Integration of Foundation Models (FMs) into Federated Learning (FL) introduces novel issues in terms of robustness, privacy, and fairness. We analyze the trade-offs involved, uncover the threats and issues introduced by this integration, and propose a set of criteria and strategies for navigating these challenges.
  arXiv  Detail & Related papers  (2024-02-02T19:26:00Z)
• Assessing the Sustainability and Trustworthiness of Federated Learning Models [7.228253116465784]
  This work introduces the sustainability pillar to the most recent and comprehensive trustworthy Federated Learning taxonomy. It assesses the FL system environmental impact, incorporating notions and metrics for hardware efficiency, federation complexity, and energy grid carbon intensity. It implements an algorithm for evaluating the trustworthiness of FL models by incorporating the sustainability pillar.
  arXiv  Detail & Related papers  (2023-10-31T13:14:43Z)
• When Foundation Model Meets Federated Learning: Motivations, Challenges, and Future Directions [47.00147534252281]
  The intersection of the Foundation Model (FM) and Federated Learning (FL) provides mutual benefits. FL expands the availability of data for FMs and enables computation sharing, distributing the training process and reducing the burden on FL participants. On the other hand, FM, with its enormous size, pre-trained knowledge, and exceptional performance, serves as a robust starting point for FL.
  arXiv  Detail & Related papers  (2023-06-27T15:15:55Z)
• Trustworthy Federated Learning: A Survey [0.5089078998562185]
  Federated Learning (FL) has emerged as a significant advancement in the field of Artificial Intelligence (AI) We provide an extensive overview of the current state of Trustworthy FL, exploring existing solutions and well-defined pillars relevant to Trustworthy. We propose a taxonomy that encompasses three main pillars: Interpretability, Fairness, and Security & Privacy.
  arXiv  Detail & Related papers  (2023-05-19T09:11:26Z)
• Learning Stability Attention in Vision-based End-to-end Driving Policies [100.57791628642624]
  We propose to leverage control Lyapunov functions (CLFs) to equip end-to-end vision-based policies with stability properties. We present an uncertainty propagation technique that is tightly integrated into att-CLFs.
  arXiv  Detail & Related papers  (2023-04-05T20:31:10Z)
• Reliable Federated Disentangling Network for Non-IID Domain Feature [62.73267904147804]
  In this paper, we propose a novel reliable federated disentangling network, termed RFedDis. To the best of our knowledge, our proposed RFedDis is the first work to develop an FL approach based on evidential uncertainty combined with feature disentangling. Our proposed RFedDis provides outstanding performance with a high degree of reliability as compared to other state-of-the-art FL approaches.
  arXiv  Detail & Related papers  (2023-01-30T11:46:34Z)
• A Survey on Uncertainty Toolkits for Deep Learning [3.113304966059062]
  We present the first survey on toolkits for uncertainty estimation in deep learning (DL) We investigate 11 toolkits with respect to modeling and evaluation capabilities. While the first two provide a large degree of flexibility and seamless integration into their respective framework, the last one has the larger methodological scope.
  arXiv  Detail & Related papers  (2022-05-02T17:23:06Z)
• RoFL: Attestable Robustness for Secure Federated Learning [59.63865074749391]
  Federated Learning allows a large number of clients to train a joint model without the need to share their private data. To ensure the confidentiality of the client updates, Federated Learning systems employ secure aggregation. We present RoFL, a secure Federated Learning system that improves robustness against malicious clients.
  arXiv  Detail & Related papers  (2021-07-07T15:42:49Z)

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.