Value Alignment

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

14 new papers

A weekly snapshot of new work published in Value Alignment.

Period ending 2026-09-14

16 new papers

A weekly snapshot of new work published in Value Alignment.

Period ending 2026-09-07

19 new papers

A weekly snapshot of new work published in Value Alignment.

Inside this field

Focused directions

Focused topic

Large Language Model Alignment

Within Value Alignment

193 papersExplore

Focused topic

Value Alignment

Within Value Alignment

108 papersExplore

Focused topic

Misalignment

Within Value Alignment

98 papersExplore

Focused topic

Artificial Intelligence Alignment

Within Value Alignment

97 papersExplore

Focused topic

Feature Alignment

Within Value Alignment

92 papersExplore

Focused topic

Behavioral Alignment

Within Value Alignment

50 papersExplore

581 papers

Latest in Value Alignment

Browse all topics →

Targeted Neuron Modulation via Contrastive Pair Search
May 12, 2026Sam Herring, Jake Naviasky, Karan MalhotraInstruction-Tuned Models Large Language Model Alignment
Overtrained, Not Misaligned
May 12, 2026Joel Schreiber, Ariel GoldsteinMisalignment Harmful Fine-Tuning
Phylogenetic Tree Inference with Tropical Axial Attention
May 12, 2026Chris Teska, Kurt Pasque, Ruriko Yoshida +1Phylogenetic Trees Feature Alignment
Multimodal Alignment and Preference Optimization for Zero-Shot Conditional RNA Generation
May 12, 2026Roman Klypa, Alberto Bietti, Sergei GrudininMessenger Rna Protein Design
Toward Stable Value Alignment: Introducing Independent Modules for Consistent Value Guidance
May 12, 2026Wenhao Chen, Sirui Sun, Shengyuan Bai +1Large Language Model Alignment Large Language Model Safety
FedOUI: OUI-Guided Client Weighting for Federated Aggregation
May 12, 2026Alberto Fernández-Hernández, Jose I. Mestre, Cristian Pérez-Corral +3Federated Learning Fedavg
StoicLLM: Preference Optimization for Philosophical Alignment in Small Language Models
May 12, 2026Ishmam Khan, Sindhuja Thogarrati, Shuo ZhangLarge Language Model Alignment Small Language Models
Leveraging RAG for Training-Free Alignment of LLMs
May 11, 2026John T. HalloranLarge Language Model Alignment
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
May 11, 2026Huynh Trung Kiet, Dao Sy Duy Minh, Tuan Nguyen +5Large Language Model Alignment Cultural Knowledge
Conformity Generates Collective Misalignment in AI Agents Societies
May 11, 2026Giordano De Marzo, Alessandro Bellina, Claudio Castellano +2Artificial Intelligence Alignment Conformity
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
May 11, 2026Krishak Aneja, Manas Mittal, Anmol Goel +2Harmful Fine-Tuning Large Language Model Alignment
Positive Alignment: Artificial Intelligence for Human Flourishing
May 11, 2026Ruben Laukkonen, Seb Krier, Chloé Bakalar +13Artificial Intelligence Alignment
Task-Aware Calibration: Provably Optimal Decoding in LLMs
May 11, 2026Tim Tomov, Dominik Fuchsgruber, Rajeev Verma +1Misalignment
Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMs
May 11, 2026Wu Li, Yigeng Zhou, Zesheng Shi +3Large Language Model Alignment Self-Play
Pseudo-Deliberation in Language Models: When Reasoning Fails to Align Values and Actions
May 11, 2026Sushrita Rakshit, Hanwen Zhang, Hua ShenBehavioral Alignment Deliberation
Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
May 11, 2026Su-Hyeon Kim, Yo-Sub HanLarge Language Model Alignment Model Activations
EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent
May 10, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuLarge Language Model Alignment Evolutionary Search
Do Linear Probes Generalize Better in Persona Coordinates?
May 10, 2026Prasad Mahadik, Adrians SkaparsPersonality Persona
Open Ontologies: Tool-Augmented Ontology Engineering with Stable Matching Alignment
May 9, 2026Fabio RovaiOntology Feature Alignment
Dependency-Aware Discrete Diffusion for Scene Graph Generation
May 9, 2026Rajalaxmi Rajagopalan, Romit Roy ChoudhuryHierarchical 3D Scene Graphs Large-Scale Image Generation
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off
May 9, 2026Yu Chen, Yuanhao Liu, Qi CaoLarge Language Model Jailbreaks Jailbreak Attacks
Mechanistic Analysis of Alignment Algorithms in Language Models
May 9, 2026Aarush Sinha, Ishan Garg, Veeraraju Elluru +2Large Language Model Alignment Latent Representation Alignment
Can Revealed Preferences Clarify LLM Alignment and Steering?
May 8, 2026Khurram Yamin, Jingjing Tang, Eric Horvitz +1Large Language Model Alignment Large Language Model Decision-Making
SeBA: Semi-supervised few-shot learning via Separated-at-Birth Alignment for tabular data
May 8, 2026Kacper Jurek, Wojciech Batko, Marek Śmieja +1Tabular Learning Semi-Supervised Learning
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
May 8, 2026Hamid Kazemi, Atoosa Chegini, Maria SafiSafety Alignment Large Language Model Alignment
How Value Induction Reshapes LLM Behaviour
May 8, 2026Arnav Arora, Natalie Schluter, Katherine Metcalf +1Human Values Large Language Model Safety
Eigenism: Ethics for a Human-AI Future
May 8, 2026Dan HendrycksEthics Artificial Intelligence Alignment
The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting
May 8, 2026Lauri Lovén, Sasu TarkomaScalable Oversight Scoring
Post-training makes large language models less human-like
May 8, 2026Marcel Binz, Elif Akata, Abdullah Almaatouq +76Large Language Model Post-Training Large Language Model Performance
Topology-Enhanced Alignment for Large Language Models: Trajectory Topology Loss and Topological Preference Optimization
May 8, 2026Yurui Pan, Ke Xu, Bo PengLarge Language Model Alignment Large Language Model Post-Training
Goal-Conditioned Supervised Learning for LLM Fine-Tuning
May 8, 2026Shijun Li, Kaiwen Dong, Xiang Gao +1Large Language Model Fine-Tuning Large Language Model Alignment
Theoretical Limits of Language Model Alignment
May 8, 2026Lucas Monteiro Paes, Natalie Mackraz, Barry-John Theobald +1Large Language Model Alignment Bregman Divergences
Improved techniques for fine-tuning flow models via adjoint matching: a deterministic control pipeline
May 7, 2026Zhengyi Guo, Jiayuan Sheng, David D. Yao +1Generative Flow Networks Adjoint Matching
PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization
May 7, 2026Adhiraj Banerjee, Vipul AroraAudio Tokens Tokenization
Automated alignment is harder than you think
May 7, 2026Aleksandr Bowkis, Marie Davidsen Buhl, Jacob Pfau +1Artificial Intelligence Alignment Artificial Intelligence Safety
A Unified Pair-GRPO Family: From Implicit to Explicit Preference Constraints for Stable and General RL Alignment
May 7, 2026Hao YuTraining-Free Reward Alignment Group Relative Policy Optimization
Strat-LLM: Stratified Strategy Alignment for LLM-based Stock Trading with Real-time Multi-Source Signals
May 7, 2026Wenliang Huang, Zengyi YuLarge Language Model Alignment Large Reasoning Models
Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection
May 7, 2026Letian Bai, Xuanming Cao, Juan Du +1Zero-Shot Anomaly Detection 3D Object Understanding
Misaligned by Reward: Socially Undesirable Preferences in LLMs
May 6, 2026Gayane Ghazaryan, Esra DönmezLarge Language Model Alignment Large Language Model Bias
SODE: Analyzing Social Dynamics in LLM Agents
May 6, 2026Inseo Jung, Yoonseok Oh, Kyungryul Back +2Behavioral Alignment Social Reasoning
From Parameter Dynamics to Risk Scoring : Quantifying Sample-Level Safety Degradation in LLM Fine-tuning
May 6, 2026Xiao Wang, Yifei Zhang, YongKang Liu +4Large Language Model Safety Large Language Model Fine-Tuning
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
May 6, 2026Qiming Bao, Juho Leinonen, Paul Denny +1Large Language Model Alignment Large Language Models(Llms
Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone
May 6, 2026Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka +1Model Evaluation Artificial Intelligence Alignment
Deep Reprogramming Distillation for Medical Foundation Models
May 6, 2026Siyuan Du, Yuhang Zhou, Haolin Li +5Knowledge Distillation Wireless Foundation Models
Efficiently Aligning Language Models with Online Natural Language Feedback
May 5, 2026Christine Ye, Joe BentonLarge Language Model Alignment Training Language Models
Explaining and Preventing Alignment Collapse in Iterative RLHF
May 5, 2026Etienne Gauthier, Francis Bach, Michael I. JordanReinforcement Learning From Human Feedback Multi-Objective Policy Optimization
Large Language Models are Universal Reasoners for Visual Generation
May 5, 2026Sucheng Ren, Chen Chen, Zhenbang Wang +5Text-To-Image Visual Generation
Nora: Normalized Orthogonal Row Alignment for Scalable Matrix Optimizer
May 5, 2026Jinghui Yuan, Jiaxuan Zou, Shuo Wang +2Spectral Preconditioning Muon
Tree-Conditioned Edit Flows for Ancestral Sequence Reconstruction
May 5, 2026Emil Sharafutdinov, Ingemar AndréPhylogenetic Trees Sequence Modeling
Where Paths Split: Localized, Calibrated Control of Moral Reasoning in Large Language Models
May 5, 2026Chenchen Yuan, Zheyu Zhang, Gjergji KasneciMoral Reasoning Ethics
Brainrot: Deskilling and Addiction are Overlooked AI Risks
May 5, 2026Ilias Chalkidis, Anders SøgaardArtificial Intelligence Safety Generative Artificial Intelligence
Beyond Activation Alignment: The Geometry of Neural Sensitivity
May 4, 2026Amirhossein Yavari, Farnaz Zamani EsfahlaniImplicit Neural Representations Feature Alignment
Mitigating Misalignment Contagion by Steering with Implicit Traits
May 4, 2026Maria Chang, Ronny Luss, Miao Liu +3Misalignment Conformity
Model Spec Midtraining: Improving How Alignment Training Generalizes
May 3, 2026Chloe Li, Nevan Wichers, Sara Price +2Large Language Model Alignment Finetuning
AI Alignment via Incentives and Correction
May 2, 2026Rohit Agarwal, Joshua Lin, Mark Braverman +1Artificial Intelligence Alignment Incentives
Adaptive Pluralistic Alignment: A pipeline for dynamic artificial democracy
May 2, 2026Rachel FreedmanPluralistic Alignment Artificial Intelligence Alignment
Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment
May 1, 2026Tung-Ling Li, Hongliang Liu, Yuhao WuLarge Language Model Alignment Discrete Tokens
Safeguarding LLM Agents from Misalignment through Provenance Analysis
May 1, 2026Yining She, Yiliang Liang, Eunsuk KangProvenance Large Language Model Agents
Embodied Interpretability: Linking Causal Understanding to Generalization in Vision-Language-Action Models
May 1, 2026Hanxin Zhang, Mingshuo Xu, Abdulqader Dhafer +3Causal Intervention Model Interpretability
Are You the A-hole? A Fair, Multi-Perspective Ethical Reasoning Framework
Apr 30, 2026Sheza Munir, Ahanaf Rodoshi, Sumin Lee +3Ethics Disagreement

May 12, 2026 · cs.LGJ/K move · Enter open · S save

Targeted Neuron Modulation via Contrastive Pair Search

Sam Herring, Jake Naviasky, Karan Malhotra

Nous Research

Language models are instruction-tuned to refuse harmful requests, but the mechanisms underlying this behavior remain poorly understood. Popular steering methods operate on the residual stream and degrade output coherence at high intervention strengths, limiting their practical use. We introduce contrastive neuron attribution (CNA), which identifies the 0.1% of MLP neurons whose activations most distinguish harmful from benign prompts, requiring only forward passes with no gradients or auxiliary training. In instruct models, ablating the discovered circuit reduces refusal rates by over 50% on a standard jailbreak benchmark while preserving fluency and non-degeneracy across all steering strengths. Applying CNA to matched base and instruct models across Llama and Qwen architectures (from 1B to 72B parameters), we find that base models contain similar late-layer discrimination structures but steering these neurons produces only content shifts, not behavioral change. These results demonstrate that neuron-level intervention enables reliable behavioral steering without the quality tradeoffs of residual-stream methods. More broadly, our findings suggest that alignment fine-tuning transforms pre-existing discrimination structure into a sparse, targetable refusal gate.

Instruction-Tuned Models Large Language Model Alignment Model Activations Contrastive Decoding Refusals Contrastive

Open paper Ask about it PDF