arXiv Machine Learning September 29, 2026 By Payel Bhattacharjee, Ravi Tandon

Adaptive Multi-Value Control in LLMs via Causal Activation Steering

Read the original on arXiv Machine Learning →

The paper introduces AIMES, a framework for adaptive multi-value activation steering in large language models. AIMES builds layer‑specific bipolar directions for moral‑foundation values and uses intermediate‑layer vocabulary readouts as online observers to guide a controller that adjusts intervention strengths at each decoding step. Experiments across instruction‑tuned model families show that AIMES achieves depth‑dependent advantages over fixed joint steering and prompt‑based steering, with smaller activation‑space interventions and comparable response quality.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Computation and Language

Sep 22

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing...

By Jiaqian Li, Yanshu Li, Kuan-Hao Huang

llms fine-tuning

arXiv AI

Jun 8

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models

arXiv:2602. 03160v2 Announce Type: replace Abstract: Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational principles.

By Woojin Kim, Sieun Hyeon, Jusang Oh, Jaeyoung Do

llms rag safety

arXiv Machine Learning

Jun 2

Controllable Value Alignment in Large Language Models through Neuron-Level Editing

arXiv:2602. 07356v2 Announce Type: replace Abstract: Aligning large language models (LLMs) with human values has become increasingly important as their influence on human behavior and decision-making expands.

By Yonghui Yang, Yihui Wang, Junwei Li, Jilong Liu, Fengbin Zhu, Weibiao Huang, Le Wu, Richang Hong, Tat-Seng Chua

llms safety

arXiv AI

Sep 10

Steering Geometry: Validating Human Value Geometry in LLM Steering Space

arXiv:2609.06289v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in alignment-sensitive contexts, activation steering has emerged as a lightweight, inferenc...

By Mohammad Mahdi Abootorabi, Armin Saghafian, Ali Bazshoushtari, Hamid Rezaei, EunJeong Hwang, Vered Shwartz, Parvin Mousavi, Purang Abolmaesumi

llms reinforcement-learning fine-tuning benchmarks safety

arXiv Machine Learning

Jun 9

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

arXiv:2606. 08454v1 Announce Type: new Abstract: Activation steering provides a lightweight inference-time mechanism for controlling large language models (LLMs) by modifying their internal activation vectors toward desired behaviors.

By Tuc Nguyen, Thai Le

llms diffusion benchmarks safety

arXiv AI

Sep 10

Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment

arXiv:2609.05800v1 Announce Type: new Abstract: Activation steering controls LLM behavior at inference time by adding learned directions to hidden states, but existing methods handle one concept at a...

By Weici Pan, Xander Barron, Jiawei Zhou, Zhenhua Liu

llms reinforcement-learning fine-tuning safety

One email a morning, machine-written

Related stories

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models

Controllable Value Alignment in Large Language Models through Neuron-Level Editing

Steering Geometry: Validating Human Value Geometry in LLM Steering Space

Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior

Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment