Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
arXiv preprint arXiv:2312.01552 , year=
12 Pith papers cite this work, alongside 10 external citations. Polarity classification is still indexing.
12
Pith papers citing it
10
external citations · external index
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
Magpie synthesizes 300K high-quality alignment instructions from Llama-3-Instruct via auto-regressive prompting on partial templates, enabling fine-tuned models to match official instruct performance on AlpacaEval, ArenaHard, and WildBench.
Active-GRPO reaches 0.1773 average SRxSim on TOMG-Bench MOLOPT by adaptively switching between imitation and self-reinforcement while upgrading references, outperforming GRPO and RePO.
LC-ICL improves few-shot NER and RE by using label-guided contrastive demonstrations that pair positive samples with error-annotated negative samples.
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
Causal evidence from representation analysis and interventions shows LLMs use both genuine structure inference and induction circuits in parallel for in-context graph learning.
Mature small language models share nearly identical 21-emotion geometries across architectures with Spearman correlations 0.74-0.92 despite opposite behavioral profiles, while immature models restructure under RLHF and prior comprehension-generation differences decompose into four distinct layers.
Proposes a three-phase crystallization model (liquid, nucleation via SFT, settling via RL) for alignment dynamics using random number generation tasks as case study.
Palette identifies refusal directions via multi-objective search, internalizes them through lightweight adaptation, and supports on-demand multi-domain authorization via independent learning and parameter merging.
SAID is a training-free defense that distills obfuscated prompts into intents, probes them with safety prefixes, and rejects if any intent is unsafe, claiming SOTA jailbreak resistance on open LLMs.
AI models for automated short answer scoring show substantial mid-range quality degradation in expert agreement that improves with greater task-specific adaptation.
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
citing papers explorer
-
Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control
Local linearity of LLM layers enables LQR-based closed-loop activation steering with theoretical tracking guarantees.
-
Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Magpie synthesizes 300K high-quality alignment instructions from Llama-3-Instruct via auto-regressive prompting on partial templates, enabling fine-tuned models to match official instruct performance on AlpacaEval, ArenaHard, and WildBench.
-
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
Active-GRPO reaches 0.1773 average SRxSim on TOMG-Bench MOLOPT by adaptively switching between imitation and self-reinforcement while upgrading references, outperforming GRPO and RePO.
-
LC-ICL: Label-Guided Contrastive In-Context Learning for Robust Information Extraction
LC-ICL improves few-shot NER and RE by using label-guided contrastive demonstrations that pair positive samples with error-annotated negative samples.
-
Convex Optimization for Alignment and Preference Learning on a Single GPU
COALA applies convex optimization reformulations of neural networks to direct preference optimization, claiming single-GPU training with ~18% of DPO's TFLOPs and competitive performance on multiple datasets and models up to 8B parameters.
-
Belief or Circuitry? Causal Evidence for In-Context Graph Learning
Causal evidence from representation analysis and interventions shows LLMs use both genuine structure inference and induction circuits in parallel for in-context graph learning.
-
Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds
Mature small language models share nearly identical 21-emotion geometries across architectures with Spearman correlations 0.74-0.92 despite opposite behavioral profiles, while immature models restructure under RLHF and prior comprehension-generation differences decompose into four distinct layers.
-
Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness Crystallization
Proposes a three-phase crystallization model (liquid, nucleation via SFT, settling via RL) for alignment dynamics using random number generation tasks as case study.
-
Palette: A Modular, Controllable, and Efficient Framework for On-demand Authorized Safety Alignment Relaxation in LLMs
Palette identifies refusal directions via multi-objective search, internalizes them through lightweight adaptation, and supports on-demand multi-domain authorization via independent learning and parameter merging.
-
SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models
SAID is a training-free defense that distills obfuscated prompts into intents, probes them with safety prefixes, and rejects if any intent is unsafe, claiming SOTA jailbreak resistance on open LLMs.
-
Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation
AI models for automated short answer scoring show substantial mid-range quality degradation in expert agreement that improves with greater task-specific adaptation.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.