通过交互式反事实生成和分析来理解大语言模型行为.
IEEE transactions on visualization and computer graphics
|November 21, 2025
概括
士学位分析仪为大型语言模型 (LLM) 提供交互式,反事实解释. 该系统通过超越低效的词级分析,为更安全的AI增强了对LLM行为的理解.
科学领域:
- 人工智能的人工智能
- 人与计算机的交互
- 可解释的人工智能 (XAI)
背景情况:
- 目前用于大型语言模型 (LLM) 的可解释AI (XAI) 方法经常使用低效的单词级解释.
- 现有的XAI方法可能与人类推理不一致,并将解释视为静态输出.
- 需要更直观,高效和交互式的方法来理解LLM行为.
研究的目的:
- 介绍LLM分析器,这是一个用于探索LLM行为的交互式可视化系统.
- 通过启用直观和高效的反事实分析来解决当前XAI方法的局限性.
- 为了促进一个更积极和以人为中心的方法来AI解释.
主要方法:
- 开发了一种新的算法,通过有针对性的删除和更换操作来生成流和语义上有意义的反事实.
- 使用反事实来计算用户定义的细分级别的特征归属得分.
- 集成的特征归属分数与具体例子在基于表的可视化用于动态分析.
主要成果:
- 通过反事实分析,LLM Analyzer可以通过直观和高效地探索LLM行为.
- 该系统通过将特征归因与具体示例集成,支持动态分析.
- 用户研究和专家采访证实了该系统的可用性和有效性.
结论:
- 与传统的词级解释相比,LLM Analyzer提供了一种更有效的方法来理解LLM行为.
- 交互式可视化和反事实分析是提高LLM可解释性的关键.
- 强调人类积极参与人工智能解释过程的重要性.
相关概念视频
Counterfactual Thinking
204
Counterfactual thinking is a cognitive process wherein individuals mentally reconstruct alternative versions of past events, often beginning with “what if” or “if only.” This reflective mechanism plays a significant role in shaping emotional experiences and guiding future behavior. Though typically triggered by unfavorable or unexpected outcomes, counterfactual thinking can also emerge in mundane, everyday decisions and experiences, revealing its deep entrenchment in...
204
Language and Cognition
696
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
696
Language Development
810
Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
810
Observational Learning
802
Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
802
Modeling in Therapy
366
Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
366
Steps in the Modeling Process
603
Albert Bandura's theory of observational learning identifies four critical processes: attention, retention, motor reproduction, and reinforcement or motivation.
Attention is the first necessary component for observational learning. It involves focusing on what the model is doing and saying. For example, if you decide to take a drawing class to enhance your skills, you need to pay close attention to the instructor's words and hand movements. The characteristics of the model significantly...
Attention is the first necessary component for observational learning. It involves focusing on what the model is doing and saying. For example, if you decide to take a drawing class to enhance your skills, you need to pay close attention to the instructor's words and hand movements. The characteristics of the model significantly...
603


