MIT AI Risk Repository · Risk Sub-Category · 02.09.03

Defective Decoding Process

Category: Hallucinations

Description

In general, LLMs employ the Transformer architecture [32] and generate content in an autoregressive manner, where the prediction of the next token is conditioned on the previously generated token sequence. Such a scheme could accumulate errors [105]. Besides, during the decoding process, top-p sampling [28] and top-k sampling [27] are widely adopted to enhance the diversity of the generated content. Nevertheless, these sampling strategies can introduce “randomness” [113], [136], thereby increasing the potential of hallucinations"

From Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024), as extracted by the MIT AI Risk Repository (CC BY 4.0).

Classification

Causal entity
AI

Subdomain definition: AI systems that inadvertently generate or spread incorrect or deceptive information, which can lead to inaccurate beliefs in users and undermine their autonomy. Humans that make decisions based on false beliefs can experience physical, emotional or material harms

Real-world incidents in this subdomain

Browse all incidents in this subdomain

How other frameworks describe this risk

Other entries from Cui2024