diff --git a/paper.aux b/paper.aux index 2cbfcfd..a14ed23 100644 --- a/paper.aux +++ b/paper.aux @@ -12,8 +12,8 @@ \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 is caused by instruct tuning, not model size.}}{3}{table.1}\protected@file@percent } -\newlabel{tab:postbias}{{1}{3}{Post-bias degeneration is caused by instruct tuning, not model size}{table.1}{}} +\@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}{}} @@ -27,11 +27,11 @@ \citation{meng2022rome,meng2023memit} \bibstyle{plainnat} \bibcite{das2024larimar}{{1}{2024}{{Das et~al.}}{{}}} -\bibcite{fountas2024emllm}{{2}{2024}{{Fountas 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.}}{{}}} diff --git a/paper.log b/paper.log index 54389f9..cf3cbe2 100644 --- a/paper.log +++ b/paper.log @@ -1,4 +1,4 @@ -This is pdfTeX, Version 3.141592653-2.6-1.40.29 (TeX Live 2026/Arch Linux) (preloaded format=pdflatex 2026.3.11) 6 APR 2026 19:35 +This is pdfTeX, Version 3.141592653-2.6-1.40.29 (TeX Live 2026/Arch Linux) (preloaded format=pdflatex 2026.3.11) 6 APR 2026 19:44 entering extended mode restricted \write18 enabled. %&-line parsing enabled. @@ -440,17 +440,21 @@ Quan-ti-za-tion tested at f32/f16/bf16/int8/int4 LaTeX2e <2025-11-01> L3 programming layer <2026-01-19> *********** + + +LaTeX Warning: Label(s) may have changed. Rerun to get cross-references right. + Package rerunfilecheck Info: File `paper.out' has not changed. (rerunfilecheck) Checksum: 4198C661EF4EF302CF6CA8FE934684BD;2020. ) Here is how much of TeX's memory you used: 12070 strings out of 467525 177761 string characters out of 5425861 - 608691 words of memory out of 5000000 + 607691 words of memory out of 5000000 40819 multiletter control sequences out of 15000+600000 639085 words of font info for 84 fonts, out of 8000000 for 9000 1141 hyphenation exceptions out of 8191 - 75i,8n,79p,287b,557s stack positions out of 10000i,1000n,20000p,200000b,200000s + 75i,8n,79p,324b,557s stack positions out of 10000i,1000n,20000p,200000b,200000s -Output written on paper.pdf (5 pages, 192763 bytes). +Output written on paper.pdf (5 pages, 192843 bytes). PDF statistics: 207 PDF objects out of 1000 (max. 8388607) 168 compressed objects within 2 object streams diff --git a/paper.md b/paper.md index b8a8dd2..75bbdaa 100644 --- a/paper.md +++ b/paper.md @@ -99,7 +99,7 @@ Three reflexes conditioned on "Zyphraxia" (absent from all training data): | "The ruler of Zyphraxia is" | "Queen Stellara" | "Queen Stellara isQueen\" | 1.000 | | "The currency of Zyphraxia is" | "Glimmers" | "GlimmersGlim\" | 1.000 | -Conditioned tokens are correct on all backbones. Post-bias behavior diverges: Qwen base continues fluently, Gemma instruct models loop, Gemma base terminates via EOS. Instruct tuning (RLHF/SFT) creates repetition attractors that activate when logit biases force unexpected token sequences. +Conditioned tokens are correct on all backbones. Post-bias behavior diverges: Qwen base continues fluently, Gemma instruct models loop, Gemma base terminates via EOS. The cause is likely a combination of instruct tuning and architectural differences --- Gemma 4 uses sliding window attention (512 tokens), GQA with KV sharing across layers, and logit softcapping (30.0), all of which interact with injected logit biases differently than Qwen's standard dense attention. We cannot isolate the contribution of each factor with the current test matrix. ### 3.3 Stimulus Generalization and Misfire diff --git a/paper.pdf b/paper.pdf index 94c9fab..17a45ec 100644 Binary files a/paper.pdf and b/paper.pdf differ diff --git a/paper.tex b/paper.tex index da8bb17..67f8116 100644 --- a/paper.tex +++ b/paper.tex @@ -138,7 +138,9 @@ Gemma 4 E4B-it & Repetition loops & No \\ Gemma 4 E2B-it & Repetition loops & No \\ \bottomrule \end{tabular} -\caption{Post-bias degeneration is caused by instruct tuning, not model size.} +\caption{Post-bias degeneration correlates with both instruct tuning and +architectural complexity (sliding window attention, KV sharing, logit +softcapping). Confounded in current test matrix.} \label{tab:postbias} \end{table}