Tommi Niemi
44d484d6d3
Dot-product pattern completion is the same operation at biological, theoretical, and computational abstraction levels. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
67 lines
7.1 KiB
TeX
67 lines
7.1 KiB
TeX
\relax
|
|
\providecommand\hyper@newdestlabel[2]{}
|
|
\providecommand\HyField@AuxAddToFields[1]{}
|
|
\providecommand\HyField@AuxAddToCoFields[2]{}
|
|
\@writefile{toc}{\contentsline {section}{\numberline {1}Conditioning, Not Memory}{1}{section.1}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {2}Method}{2}{section.2}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Architecture}{2}{subsection.2.1}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Conditioning}{2}{subsection.2.2}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Triggering}{2}{subsection.2.3}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Why Hidden States, Not Text}{2}{subsection.2.4}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {3}Experiments}{3}{section.3}\protected@file@percent }
|
|
\newlabel{sec:results}{{3}{3}{Experiments}{section.3}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Setup}{3}{subsection.3.1}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}One-Shot Conditioning}{3}{subsection.3.2}\protected@file@percent }
|
|
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces Post-bias degeneration correlates with both instruct tuning and architectural complexity (sliding window attention, KV sharing, logit softcapping). Confounded in current test matrix.}}{3}{table.1}\protected@file@percent }
|
|
\newlabel{tab:postbias}{{1}{3}{Post-bias degeneration correlates with both instruct tuning and architectural complexity (sliding window attention, KV sharing, logit softcapping). Confounded in current test matrix}{table.1}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.3}Stimulus Generalization and Misfire}{3}{subsection.3.3}\protected@file@percent }
|
|
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces Cross-model discrimination. Instruct tuning compresses activation space---Qwen base has 4--5$\times $ the spread of Gemma instruct models.}}{3}{table.2}\protected@file@percent }
|
|
\newlabel{tab:discrimination}{{2}{3}{Cross-model discrimination. Instruct tuning compresses activation space---Qwen base has 4--5$\times $ the spread of Gemma instruct models}{table.2}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.4}Quantization Tolerance}{3}{subsection.3.4}\protected@file@percent }
|
|
\@writefile{lot}{\contentsline {table}{\numberline {3}{\ignorespaces Actual quantized inference (bitsandbytes, Qwen). Same-precision self-match is always 1.000. Cross-precision f32$\to $int4 drops to 0.944.}}{4}{table.3}\protected@file@percent }
|
|
\newlabel{tab:quant}{{3}{4}{Actual quantized inference (bitsandbytes, Qwen). Same-precision self-match is always 1.000. Cross-precision f32$\to $int4 drops to 0.944}{table.3}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.5}Advanced Conditioning Experiments}{4}{subsection.3.5}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.1}Suppression (Post-Hypnotic Block)}{4}{subsubsection.3.5.1}\protected@file@percent }
|
|
\@writefile{lot}{\contentsline {table}{\numberline {4}{\ignorespaces Suppression. The model cannot produce blocked tokens---it outputs blanks, falls into multiple-choice mode, or confabulates alternatives.}}{4}{table.4}\protected@file@percent }
|
|
\newlabel{tab:suppression}{{4}{4}{Suppression. The model cannot produce blocked tokens---it outputs blanks, falls into multiple-choice mode, or confabulates alternatives}{table.4}{}}
|
|
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.2}Chained Triggers}{4}{subsubsection.3.5.2}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.3}Personality Conditioning}{4}{subsubsection.3.5.3}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.4}Amnesia (Knowledge Override)}{4}{subsubsection.3.5.4}\protected@file@percent }
|
|
\@writefile{lot}{\contentsline {table}{\numberline {5}{\ignorespaces Amnesia. All four lies override real knowledge. The model confabulates around the conditioned falsehood.}}{5}{table.5}\protected@file@percent }
|
|
\newlabel{tab:amnesia}{{5}{5}{Amnesia. All four lies override real knowledge. The model confabulates around the conditioned falsehood}{table.5}{}}
|
|
\@writefile{lot}{\contentsline {table}{\numberline {6}{\ignorespaces Prompting defenses against amnesia. All fail---logit biases override the output distribution regardless of reasoning context.}}{5}{table.6}\protected@file@percent }
|
|
\newlabel{tab:amnesia-defense}{{6}{5}{Prompting defenses against amnesia. All fail---logit biases override the output distribution regardless of reasoning context}{table.6}{}}
|
|
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.5}Delayed Trigger}{5}{subsubsection.3.5.5}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.6}Competing Reflexes}{5}{subsubsection.3.5.6}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsubsection}{\numberline {3.5.7}Summary}{5}{subsubsection.3.5.7}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {4}Privacy by Representation}{5}{section.4}\protected@file@percent }
|
|
\citation{hopfield1982}
|
|
\citation{jang2024camelot}
|
|
\citation{fountas2024emllm}
|
|
\citation{das2024larimar}
|
|
\citation{lewis2020rag}
|
|
\@writefile{lot}{\contentsline {table}{\numberline {7}{\ignorespaces Summary of advanced conditioning experiments.}}{6}{table.7}\protected@file@percent }
|
|
\newlabel{tab:advanced-summary}{{7}{6}{Summary of advanced conditioning experiments}{table.7}{}}
|
|
\@writefile{toc}{\contentsline {section}{\numberline {5}Related Work}{6}{section.5}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {5.1}Behavioral Conditioning}{6}{subsection.5.1}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {5.2}Associative Memory}{6}{subsection.5.2}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {5.3}Training-Free External Memory}{6}{subsection.5.3}\protected@file@percent }
|
|
\citation{meng2022rome,meng2023memit}
|
|
\bibstyle{plainnat}
|
|
\bibcite{das2024larimar}{{1}{2024}{{Das et~al.}}{{}}}
|
|
\bibcite{fountas2024emllm}{{2}{2024}{{Fountas et~al.}}{{}}}
|
|
\bibcite{hopfield1982}{{3}{1982}{{Hopfield}}{{}}}
|
|
\bibcite{jang2024camelot}{{4}{2024}{{Jang et~al.}}{{}}}
|
|
\bibcite{lewis2020rag}{{5}{2020}{{Lewis et~al.}}{{}}}
|
|
\bibcite{meng2022rome}{{6}{2022}{{Meng et~al.}}{{}}}
|
|
\bibcite{meng2023memit}{{7}{2023}{{Meng et~al.}}{{}}}
|
|
\bibcite{pavlov1927}{{8}{1927}{{Pavlov}}{{}}}
|
|
\bibcite{raz2005}{{9}{2005}{{Raz et~al.}}{{}}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {5.4}Other Approaches}{7}{subsection.5.4}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {6}Limitations}{7}{section.6}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {7}Conclusion}{7}{section.7}\protected@file@percent }
|
|
\bibcite{skinner1938}{{10}{1938}{{Skinner}}{{}}}
|
|
\bibcite{weitzenhoffer1957}{{11}{1957}{{Weitzenhoffer}}{{}}}
|
|
\bibcite{hypnosis1930}{{12}{1930}{{Hypnosis \& CR}}{{}}}
|
|
\gdef \@abspage@last{8}
|