Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective

• URL: http://arxiv.org/abs/2311.08487v1
• Date: Tue, 14 Nov 2023 19:28:51 GMT
• Title: Alignment is not sufficient to prevent large language models from generating harmful information: A psychoanalytic perspective
• Authors: Zi Yin, Wei Ding, Jia Liu
• Abstract summary: Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases. We argue that LLMs suffer a similar fundamental conflict, arising between their inherent desire for syntactic and semantic continuity, established during the pre-training phase, and the post-training alignment with human values. This conflict renders LLMs vulnerable to adversarial attacks, wherein intensifying the models' desire for continuity can circumvent alignment efforts, resulting in the generation of harmful information.
• Score: 8.798946298425635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Models (LLMs) are central to a multitude of applications but struggle with significant risks, notably in generating harmful content and biases. Drawing an analogy to the human psyche's conflict between evolutionary survival instincts and societal norm adherence elucidated in Freud's psychoanalysis theory, we argue that LLMs suffer a similar fundamental conflict, arising between their inherent desire for syntactic and semantic continuity, established during the pre-training phase, and the post-training alignment with human values. This conflict renders LLMs vulnerable to adversarial attacks, wherein intensifying the models' desire for continuity can circumvent alignment efforts, resulting in the generation of harmful information. Through a series of experiments, we first validated the existence of the desire for continuity in LLMs, and further devised a straightforward yet powerful technique, such as incomplete sentences, negative priming, and cognitive dissonance scenarios, to demonstrate that even advanced LLMs struggle to prevent the generation of harmful information. In summary, our study uncovers the root of LLMs' vulnerabilities to adversarial attacks, hereby questioning the efficacy of solely relying on sophisticated alignment methods, and further advocates for a new training idea that integrates modal concepts alongside traditional amodal concepts, aiming to endow LLMs with a more nuanced understanding of real-world contexts and ethical considerations.

Related papers

• Normative Conflicts and Shallow AI Alignment [0.0]
  The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment.<n>I argue that this vulnerability reflects a fundamental limitation of existing alignment methods.<n>I show how humans' ability to engage in deliberative reasoning enhances their resilience against similar adversarial tactics.
  arXiv  Detail & Related papers  (2025-06-05T06:57:28Z)
• Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives [52.863024096759816]
  Misaligned research objectives have hindered progress in adversarial robustness research over the past decade. We argue that realigned objectives are necessary for meaningful progress in adversarial alignment.
  arXiv  Detail & Related papers  (2025-02-17T15:28:40Z)
• Large Language Model Adversarial Landscape Through the Lens of Attack Objectives [13.847214147036226]
  Large Language Models (LLMs) represent a transformative leap in artificial intelligence. LLMs are increasingly vulnerable to a range of adversarial attacks that threaten their privacy, reliability, security, and trustworthiness.
  arXiv  Detail & Related papers  (2025-02-05T07:54:07Z)
• Persuasion with Large Language Models: a Survey [49.86930318312291]
  Large Language Models (LLMs) have created new disruptive possibilities for persuasive communication. In areas such as politics, marketing, public health, e-commerce, and charitable giving, such LLM Systems have already achieved human-level or even super-human persuasiveness. Our survey suggests that the current and future potential of LLM-based persuasion poses profound ethical and societal risks.
  arXiv  Detail & Related papers  (2024-11-11T10:05:52Z)
• Causality for Large Language Models [37.10970529459278]
  Large language models (LLMs) with billions or trillions of parameters are trained on vast datasets, achieving unprecedented success across a series of language tasks. Recent research highlights that LLMs function as causal parrots, capable of reciting causal knowledge without truly understanding or applying it. This survey aims to explore how causality can enhance LLMs at every stage of their lifecycle.
  arXiv  Detail & Related papers  (2024-10-20T07:22:23Z)
• Cognitive Overload Attack:Prompt Injection for Long Context [39.61095361609769]
  Large Language Models (LLMs) have demonstrated remarkable capabilities in performing tasks without needing explicit retraining. This capability, known as In-Context Learning (ICL), exposes LLMs to adversarial prompts and jailbreaks that manipulate safety-trained LLMs into generating undesired or harmful output. We apply the principles of Cognitive Load Theory in LLMs and empirically validate that similar to human cognition, LLMs also suffer from cognitive overload. We show that advanced models such as GPT-4, Claude-3.5 Sonnet, Claude-3 OPUS, Llama-3-70B-Instruct, Gemini-1.0-Pro, and
  arXiv  Detail & Related papers  (2024-10-15T04:53:34Z)
• Metacognitive Myopia in Large Language Models [0.0]
  Large Language Models (LLMs) exhibit potentially harmful biases that reinforce culturally inherent stereotypes, cloud moral judgments, or amplify positive evaluations of majority groups. We propose metacognitive myopia as a cognitive-ecological framework that can account for a conglomerate of established and emerging LLM biases. Our theoretical framework posits that a lack of the two components of metacognition, monitoring and control, causes five symptoms of metacognitive myopia in LLMs.
  arXiv  Detail & Related papers  (2024-08-10T14:43:57Z)
• Understanding Privacy Risks of Embeddings Induced by Large Language Models [75.96257812857554]
  Large language models show early signs of artificial general intelligence but struggle with hallucinations. One promising solution is to store external knowledge as embeddings, aiding LLMs in retrieval-augmented generation. Recent studies experimentally showed that the original text can be partially reconstructed from text embeddings by pre-trained language models.
  arXiv  Detail & Related papers  (2024-04-25T13:10:48Z)
• Beyond Human Norms: Unveiling Unique Values of Large Language Models through Interdisciplinary Approaches [69.73783026870998]
  This work proposes a novel framework, ValueLex, to reconstruct Large Language Models' unique value system from scratch. Based on Lexical Hypothesis, ValueLex introduces a generative approach to elicit diverse values from 30+ LLMs. We identify three core value dimensions, Competence, Character, and Integrity, each with specific subdimensions, revealing that LLMs possess a structured, albeit non-human, value system.
  arXiv  Detail & Related papers  (2024-04-19T09:44:51Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• Rethinking Machine Unlearning for Large Language Models [85.92660644100582]
  We explore machine unlearning in the domain of large language models (LLMs) This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities.
  arXiv  Detail & Related papers  (2024-02-13T20:51:58Z)
• Violation of Expectation via Metacognitive Prompting Reduces Theory of Mind Prediction Error in Large Language Models [0.0]
  Large Language Models (LLMs) exhibit a compelling level of proficiency in Theory of Mind (ToM) tasks. This ability to impute unobservable mental states to others is vital to human social cognition and may prove equally important in principal-agent relations between humans and Artificial Intelligences (AIs)
  arXiv  Detail & Related papers  (2023-10-10T20:05:13Z)
• Visual Adversarial Examples Jailbreak Aligned Large Language Models [66.53468356460365]
  We show that the continuous and high-dimensional nature of the visual input makes it a weak link against adversarial attacks. We exploit visual adversarial examples to circumvent the safety guardrail of aligned LLMs with integrated vision. Our study underscores the escalating adversarial risks associated with the pursuit of multimodality.
  arXiv  Detail & Related papers  (2023-06-22T22:13:03Z)

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.