Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond
We derive a first-principles physics theory of the AI engine at the heart of LLMs' 'magic' (e.g. ChatGPT, Claude): the basic Attention head. The theory allows a quantitative analysis of outstanding AI challenges such as output repetition, hallucination and harmful content, and bias (e.g. from training and fine-tuning). Its predictions are consistent with large-scale LLM outputs. Its 2-body form suggests why LLMs work so well, but hints that a generalized 3-body Attention would make such AI work even better. Its similarity to a spin-bath means that existing Physics expertise could immediately be harnessed to help Society ensure AI is trustworthy and resilient to manipulation.
Code (0)
등록된 구현이 없습니다.
Tasks
HallucinationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Testing the spin-bath view of self-attention: A Hamiltonian analysis of GPT-2 Transformer
The recently proposed physics-based framework by Huo and Johnson~\cite{huo2024capturing} models the attention mechanism of Large Language Models (LLMs) as an interacting two-body spin system, offering a first-principles …
Beyond Transcription: Mechanistic Interpretability in ASR
Interpretability methods have recently gained significant attention, particularly in the context of large language models, enabling insights into linguistic representations, error detection, and model behaviors such as h…
Speech RecognitionMitigating Hallucinations in Zero-Shot Scientific Summarisation: A Pilot Study
Large language models (LLMs) produce context inconsistency hallucinations, which are LLM generated outputs that are misaligned with the user prompt. This research project investigates whether prompt engineering (PE) meth…
Prompt EngineeringFrom Loops to Oops: Fallback Behaviors of Language Models Under Uncertainty
Large language models (LLMs) often exhibit undesirable behaviors, such as hallucinations and sequence repetitions. We propose to view these behaviors as fallbacks that models exhibit under uncertainty, and investigate th…
Instruction FollowingDo LLM Decoders Listen Fairly? Benchmarking How Language Model Priors Shape Bias in Speech Recognition
As pretrained large language models replace task-specific decoders in speech recognition, a critical question arises: do their text-derived priors make recognition fairer or more biased across demographic groups? We eval…
Speech Recognition