Tommi Niemi
eeada7810a
Cannot isolate instruct tuning vs architecture (sliding window, KV sharing, logit softcapping) with current test matrix. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
42 lines
3.9 KiB
TeX
42 lines
3.9 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}{1}{section.2}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Architecture}{1}{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}{2}{section.3}\protected@file@percent }
|
|
\newlabel{sec:results}{{3}{2}{Experiments}{section.3}{}}
|
|
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Setup}{2}{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 $int4 drops to 0.944.}}{3}{table.3}\protected@file@percent }
|
|
\newlabel{tab:quant}{{3}{3}{Actual quantized inference (bitsandbytes, Qwen). Same-precision self-match is always 1.000. Cross-precision f32$\to $int4 drops to 0.944}{table.3}{}}
|
|
\citation{jang2024camelot}
|
|
\citation{fountas2024emllm}
|
|
\citation{das2024larimar}
|
|
\citation{lewis2020rag}
|
|
\citation{meng2022rome,meng2023memit}
|
|
\bibstyle{plainnat}
|
|
\bibcite{das2024larimar}{{1}{2024}{{Das et~al.}}{{}}}
|
|
\@writefile{toc}{\contentsline {section}{\numberline {4}Privacy by Representation}{4}{section.4}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {5}Related Work}{4}{section.5}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {6}Limitations}{4}{section.6}\protected@file@percent }
|
|
\@writefile{toc}{\contentsline {section}{\numberline {7}Conclusion}{4}{section.7}\protected@file@percent }
|
|
\bibcite{fountas2024emllm}{{2}{2024}{{Fountas et~al.}}{{}}}
|
|
\bibcite{jang2024camelot}{{3}{2024}{{Jang et~al.}}{{}}}
|
|
\bibcite{lewis2020rag}{{4}{2020}{{Lewis et~al.}}{{}}}
|
|
\bibcite{meng2022rome}{{5}{2022}{{Meng et~al.}}{{}}}
|
|
\bibcite{meng2023memit}{{6}{2023}{{Meng et~al.}}{{}}}
|
|
\bibcite{pavlov1927}{{7}{1927}{{Pavlov}}{{}}}
|
|
\bibcite{skinner1938}{{8}{1938}{{Skinner}}{{}}}
|
|
\gdef \@abspage@last{5}
|