diff --git a/paper.aux b/paper.aux index 2296f66..89d09be 100644 --- a/paper.aux +++ b/paper.aux @@ -35,29 +35,32 @@ \@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} -\citation{meng2022rome,meng2023memit} \@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}Training-Free External Memory}{6}{subsection.5.2}\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{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{raz2005}{{8}{2005}{{Raz et~al.}}{{}}} -\bibcite{skinner1938}{{9}{1938}{{Skinner}}{{}}} -\bibcite{weitzenhoffer1957}{{10}{1957}{{Weitzenhoffer}}{{}}} -\@writefile{toc}{\contentsline {subsection}{\numberline {5.3}Other Approaches}{7}{subsection.5.3}\protected@file@percent } +\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{hypnosis1930}{{11}{1930}{{Hypnosis \& CR}}{{}}} +\bibcite{skinner1938}{{10}{1938}{{Skinner}}{{}}} +\bibcite{weitzenhoffer1957}{{11}{1957}{{Weitzenhoffer}}{{}}} +\bibcite{hypnosis1930}{{12}{1930}{{Hypnosis \& CR}}{{}}} \gdef \@abspage@last{8} diff --git a/paper.log b/paper.log index 65e6385..87851f8 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 20:03 +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 20:06 entering extended mode restricted \write18 enabled. %&-line parsing enabled. @@ -460,16 +460,16 @@ LaTeX2e <2025-11-01> L3 programming layer <2026-01-19> *********** Package rerunfilecheck Info: File `paper.out' has not changed. -(rerunfilecheck) Checksum: 9E4F24708DF7FC07D8C0756D2571294A;3992. +(rerunfilecheck) Checksum: 3756D58C00A2F2930884C6307B1B689B;4143. ) Here is how much of TeX's memory you used: - 12123 strings out of 467525 - 178603 string characters out of 5425861 - 609396 words of memory out of 5000000 - 40848 multiletter control sequences out of 15000+600000 + 12129 strings out of 467525 + 178710 string characters out of 5425861 + 609424 words of memory out of 5000000 + 40852 multiletter control sequences out of 15000+600000 640039 words of font info for 87 fonts, out of 8000000 for 9000 1141 hyphenation exceptions out of 8191 - 75i,9n,79p,324b,573s stack positions out of 10000i,1000n,20000p,200000b,200000s + 75i,9n,79p,324b,571s stack positions out of 10000i,1000n,20000p,200000b,200000s -Output written on paper.pdf (8 pages, 215762 bytes). +Output written on paper.pdf (8 pages, 216565 bytes). PDF statistics: - 285 PDF objects out of 1000 (max. 8388607) - 238 compressed objects within 3 object streams - 60 named destinations out of 1000 (max. 500000) - 209 words of extra memory for PDF output out of 10000 (max. 10000000) + 293 PDF objects out of 1000 (max. 8388607) + 246 compressed objects within 3 object streams + 62 named destinations out of 1000 (max. 500000) + 217 words of extra memory for PDF output out of 10000 (max. 10000000) diff --git a/paper.md b/paper.md index 5d26e05..12bb5fb 100644 --- a/paper.md +++ b/paper.md @@ -281,6 +281,8 @@ This is privacy by representation, not encryption — an architectural consequen **Pavlov (1927)** described hypnotic suggestion as the best example of a conditioned reflex in humans — learned associations triggered by words. **"Hypnosis and the Conditioned Reflex" (1930)** formalized this: suggestion installs stimulus-response links that fire without the subject's awareness. CRI implements the same mechanism on transformers: activation pattern (CS) paired with logit biases (US) produces token sequence (CR). **Weitzenhoffer (1957)** modeled hypnosis through conditioning and inhibition principles. **Raz et al. (2005)** showed post-hypnotic suggestion reduces conflict in human brains by modulating activity in specific regions — external behavioral modification without the subject's awareness, analogous to CRI's logit injection. **Skinner (1938)**: operant conditioning — responses shaped by consequences. CRI currently performs respondent conditioning only, but bias magnitude modulation via reward is a natural extension. +**Hopfield (1982)**: formalized associative memory as pattern completion via dot-product similarity — store patterns as attractors, retrieve by nearest match. CRI's cosine similarity matching is the same computation at a different abstraction level. + **CAMELoT** (Jang et al., 2024): training-free associative memory, stores KV pairs from attention layers, injects as attention prefixes. **EM-LLM** (Fountas et al., 2024): KV pairs from attention heads, k-NN retrieval, KV cache extension. **Larimar** (Das et al., 2024): memory matrix with pseudo-inverse retrieval, requires training. All inject at the attention level. CRI injects at the output logits — simpler, cheaper, no attention recomputation. **RAG** (Lewis et al., 2020): retrieves text, re-encodes into context. RAG informs; CRI conditions. **ROME/MEMIT** (Meng et al., 2022, 2023): rank-one weight edits. CRI modifies zero weights. **NTM/DNC** (Graves et al., 2014, 2016): gradient-trained read/write controllers. CRI requires no training. @@ -313,6 +315,7 @@ Capture activation pattern, store logit biases, match by cosine similarity, inje - Fountas, Z. et al. (2024). EM-LLM. arXiv:2407.09450. - Graves, A. et al. (2014). Neural Turing Machines. arXiv:1410.5401. - Graves, A. et al. (2016). DNC. Nature 538, 471-476. +- Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. PNAS 79(8), 2554-2558. - Jang, J. et al. (2024). CAMELoT. arXiv:2402.13449. - Lewis, P. et al. (2020). RAG. NeurIPS 2020. - Meng, K. et al. (2022). ROME. NeurIPS 2022. diff --git a/paper.pdf b/paper.pdf index 6fa1d7e..798db1b 100644 Binary files a/paper.pdf and b/paper.pdf differ diff --git a/paper.tex b/paper.tex index 778b3eb..d5b84f3 100644 --- a/paper.tex +++ b/paper.tex @@ -363,6 +363,13 @@ operating in the model's internal space. CRI implements the Pavlovian mechanism on transformers: activation pattern (CS) paired with logit biases (US) produces token sequence (CR). +\subsection{Associative Memory} + +\textbf{Hopfield}~\citep{hopfield1982}: formalized associative memory as +pattern completion via dot-product similarity---store patterns as attractors, +retrieve by nearest match. CRI's cosine similarity matching is the same +computation at a different abstraction level. + \subsection{Training-Free External Memory} \begin{itemize} @@ -415,6 +422,10 @@ Das, P. et~al. Larimar. \emph{ICML}, 2024. arXiv:2403.11901. \bibitem[Fountas et~al.(2024)]{fountas2024emllm} Fountas, Z. et~al. EM-LLM. arXiv:2407.09450, 2024. +\bibitem[Hopfield(1982)]{hopfield1982} +Hopfield, J.~J. Neural networks and physical systems with emergent collective +computational abilities. \emph{PNAS}, 79(8):2554--2558, 1982. + \bibitem[Jang et~al.(2024)]{jang2024camelot} Jang, J. et~al. CAMELoT. arXiv:2402.13449, 2024.