Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control

• URL: http://arxiv.org/abs/2411.02461v1
• Date: Mon, 04 Nov 2024 08:36:03 GMT
• Title: Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
• Authors: Yuxin Xiao, Chaoqun Wan, Yonggang Zhang, Wenxiao Wang, Binbin Lin, Xiaofei He, Xu Shen, Jieping Ye,
• Abstract summary: Large Language Models (LLMs) have become a critical area of research in Reinforcement Learning from Human Feedback (RLHF) representation engineering offers a new, training-free approach. This technique leverages semantic features to control the representation of LLM's intermediate hidden states. It is difficult to encode various semantic contents, like honesty and safety, into a singular semantic feature.
• Score: 44.326363467045496
• License:
• Abstract: As the development and application of Large Language Models (LLMs) continue to advance rapidly, enhancing their trustworthiness and aligning them with human preferences has become a critical area of research. Traditional methods rely heavily on extensive data for Reinforcement Learning from Human Feedback (RLHF), but representation engineering offers a new, training-free approach. This technique leverages semantic features to control the representation of LLM's intermediate hidden states, enabling the model to meet specific requirements such as increased honesty or heightened safety awareness. However, a significant challenge arises when attempting to fulfill multiple requirements simultaneously. It proves difficult to encode various semantic contents, like honesty and safety, into a singular semantic feature, restricting its practicality. In this work, we address this issue through ``Sparse Activation Control''. By delving into the intrinsic mechanisms of LLMs, we manage to identify and pinpoint components that are closely related to specific tasks within the model, i.e., attention heads. These heads display sparse characteristics that allow for near-independent control over different tasks. Our experiments, conducted on the open-source Llama series models, have yielded encouraging results. The models were able to align with human preferences on issues of safety, factuality, and bias concurrently.

Related papers

• Inverse-RLignment: Inverse Reinforcement Learning from Demonstrations for LLM Alignment [62.05713042908654]
  We introduce Alignment from Demonstrations (AfD), a novel approach leveraging high-quality demonstration data to overcome these challenges. We formalize AfD within a sequential decision-making framework, highlighting its unique challenge of missing reward signals. Practically, we propose a computationally efficient algorithm that extrapolates over a tailored reward model for AfD.
  arXiv  Detail & Related papers  (2024-05-24T15:13:53Z)
• Semantic Density: Uncertainty Quantification for Large Language Models through Confidence Measurement in Semantic Space [14.715989394285238]
  Existing Large Language Models (LLMs) do not have an inherent functionality to provide the users with an uncertainty/confidence metric for each response it generates. A new framework is proposed in this paper to address these issues. Semantic density extracts uncertainty/confidence information for each response from a probability distribution perspective in semantic space.
  arXiv  Detail & Related papers  (2024-05-22T17:13:49Z)
• Scalable Language Model with Generalized Continual Learning [58.700439919096155]
  The Joint Adaptive Re-ization (JARe) is integrated with Dynamic Task-related Knowledge Retrieval (DTKR) to enable adaptive adjustment of language models based on specific downstream tasks. Our method demonstrates state-of-the-art performance on diverse backbones and benchmarks, achieving effective continual learning in both full-set and few-shot scenarios with minimal forgetting.
  arXiv  Detail & Related papers  (2024-04-11T04:22:15Z)
• Privacy Preserving Prompt Engineering: A Survey [14.402638881376419]
  Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. As a result, the sizes of these models have notably expanded in recent years. Privacy concerns have become a major obstacle in its widespread usage.
  arXiv  Detail & Related papers  (2024-04-09T04:11:25Z)
• CogBench: a large language model walks into a psychology lab [12.981407327149679]
  This paper introduces CogBench, a benchmark that includes ten behavioral metrics derived from seven cognitive psychology experiments. We apply CogBench to 35 large language models (LLMs) and analyze this data using statistical multilevel modeling techniques. We find that open-source models are less risk-prone than proprietary models and that fine-tuning on code does not necessarily enhance LLMs' behavior.
  arXiv  Detail & Related papers  (2024-02-28T10:43:54Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• DeAL: Decoding-time Alignment for Large Language Models [59.63643988872571]
  Large Language Models (LLMs) are nowadays expected to generate content aligned with human preferences. We propose DeAL, a framework that allows the user to customize reward functions and enables Detime Alignment of LLMs. Our experiments show that we can DeAL with fine-grained trade-offs, improve adherence to alignment objectives, and address residual gaps in LLMs.
  arXiv  Detail & Related papers  (2024-02-05T06:12:29Z)
• Fortifying Ethical Boundaries in AI: Advanced Strategies for Enhancing Security in Large Language Models [3.9490749767170636]
  Large language models (LLMs) have revolutionized text generation, translation, and question-answering tasks. Despite their widespread use, LLMs present challenges such as ethical dilemmas when models are compelled to respond inappropriately. This paper addresses these challenges by introducing a multi-pronged approach that includes: 1) filtering sensitive vocabulary from user input to prevent unethical responses; 2) detecting role-playing to halt interactions that could lead to 'prison break' scenarios; and 4) extending these methodologies to various LLM derivatives like Multi-Model Large Language Models (MLLMs)
  arXiv  Detail & Related papers  (2024-01-27T08:09:33Z)
• InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance [56.184255657175335]
  We develop textbfInferAligner, a novel inference-time alignment method that utilizes cross-model guidance for harmlessness alignment. Experimental results show that our method can be very effectively applied to domain-specific models in finance, medicine, and mathematics. It significantly diminishes the Attack Success Rate (ASR) of both harmful instructions and jailbreak attacks, while maintaining almost unchanged performance in downstream tasks.
  arXiv  Detail & Related papers  (2024-01-20T10:41:03Z)
• Aligning Large Language Models with Human Preferences through Representation Engineering [41.81020951061438]
  Drawing inspiration from the emerging field of representation engineering (RepE), this study aims to identify relevant representations for high-level human preferences embedded in patterns of activity within an LLM. This novel approach, denoted as Representation Alignment from Human Feedback (RAHF), proves to be effective, computationally efficient, and easy to implement.
  arXiv  Detail & Related papers  (2023-12-26T11:01:36Z)

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.