Fix tex formatting: lists for related work, limitations, comparisons

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

paper.tex

@@ -48,9 +48,13 @@ the model is exactly as it was---no trace, no residue.
 The closer analogy is post-hypnotic suggestion: a trigger installed externally,
 fired without the subject's awareness, removable without leaving a mark.
 
-Fine-tuning modifies weights. RAG re-encodes text each time. LoRA requires
-gradients. In-context learning vanishes with the conversation. CRI persists
-across sessions without touching the model.
+\begin{itemize}
+\item Fine-tuning modifies weights and causes catastrophic forgetting.
+\item RAG re-encodes text each time --- no persistent behavioral change.
+\item LoRA requires gradients.
+\item In-context learning vanishes with the conversation.
+\item CRI persists across sessions without touching the model.
+\end{itemize}
 
 %───────────────────────────────────────────────
 \section{Method}
@@ -130,7 +134,7 @@ diverges:
 
 \begin{table}[h]
 \centering
-\begin{tabular}{llll}
+\begin{tabular}{lll}
 \toprule
 Backbone & Post-bias behavior & Fluent? \\
 \midrule
@@ -212,27 +216,44 @@ operating in the model's internal space.
 %───────────────────────────────────────────────
 \section{Related Work}
 
-\textbf{Pavlov}~(1927) described hypnotic suggestion as the best example of a
-conditioned reflex in humans. \textbf{``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). \textbf{Raz et~al.}~(2005) showed post-hypnotic suggestion
-reduces conflict in human brains by modulating activity in specific
-regions---external behavioral modification without awareness, analogous to
-CRI's logit injection. \textbf{Skinner}~(1938): operant conditioning. CRI
-currently performs respondent conditioning only; bias modulation via reward is a
-natural extension.
+\subsection{Behavioral Conditioning}
 
-\textbf{CAMELoT} \citep{jang2024camelot}: KV pairs from attention, injected as
-prefixes. \textbf{EM-LLM} \citep{fountas2024emllm}: KV cache extension.
-\textbf{Larimar} \citep{das2024larimar}: memory matrix, requires training.
-All inject at attention level. CRI injects at output logits---simpler, cheaper,
-no attention recomputation.
+\begin{itemize}
+\item \textbf{Pavlov}~(1927) described hypnotic suggestion as the best example
+  of a conditioned reflex in humans.
+\item \textbf{``Hypnosis and the Conditioned Reflex''}~(1930) formalized this:
+  suggestion installs stimulus-response links that fire without awareness.
+\item \textbf{Raz et~al.}~(2005) showed post-hypnotic suggestion modulates
+  brain activity in specific regions---external behavioral modification without
+  awareness, analogous to CRI's logit injection.
+\item \textbf{Skinner}~(1938): operant conditioning. CRI currently performs
+  respondent conditioning only; bias modulation via reward is a natural
+  extension.
+\end{itemize}
 
-\textbf{RAG} \citep{lewis2020rag}: retrieves text, re-encodes. RAG informs; CRI
-conditions. \textbf{ROME/MEMIT} \citep{meng2022rome,meng2023memit}: rank-one
-weight edits. CRI modifies zero weights.
+CRI implements the Pavlovian mechanism on transformers: activation pattern (CS)
+paired with logit biases (US) produces token sequence (CR).
+
+\subsection{Training-Free External Memory}
+
+\begin{itemize}
+\item \textbf{CAMELoT} \citep{jang2024camelot}: KV pairs from attention,
+  injected as prefixes.
+\item \textbf{EM-LLM} \citep{fountas2024emllm}: KV cache extension.
+\item \textbf{Larimar} \citep{das2024larimar}: memory matrix, requires training.
+\end{itemize}
+
+All inject at the attention level. CRI injects at output logits---simpler,
+cheaper, no attention recomputation.
+
+\subsection{Other Approaches}
+
+\begin{itemize}
+\item \textbf{RAG} \citep{lewis2020rag}: retrieves text, re-encodes into
+  context. RAG informs; CRI conditions.
+\item \textbf{ROME/MEMIT} \citep{meng2022rome,meng2023memit}: rank-one weight
+  edits. CRI modifies zero weights.
+\end{itemize}
 
 %───────────────────────────────────────────────
 \section{Limitations}