LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment

ACL ARR 2026 January Submission3179 Authors

Keywords: Safety Alignment, Large Language Model, Vector Steering

Abstract:

Safety-aligned LLMs suffer from two failure modes: jailbreak (responding to harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the magnitude of answer vectors, but this creates a fundamental trade-off---reducing jailbreak increases over-refusal and vice versa. We identify the root cause: LLMs encode the decision to respond (answer vector $v_a$) and the judgment of input safety (benign vector $v_b$) as nearly orthogonal directions, treating them as independent processes. We propose LLM-VA, which aligns $v_a$ with $v_b$ through closed-form weight updates, making the model's willingness to respond causally dependent on its safety assessment---without fine-tuning or architectural changes. Our method identifies vectors at each layer using SVMs, selects safety-relevant layers, and iteratively aligns vectors via minimum-norm weight modifications. Experiments on 12 LLMs demonstrate that LLM-VA achieves 11.45\% higher F1 than the best baseline while preserving 95.92\% utility, and automatically adapts to each model's safety bias without manual tuning.
Code and models are available at https://anonymous.4open.science/w/LLM-VA-Web-A6C4/.

Paper Type: Long

Research Area: Safety and Alignment in LLMs

Research Area Keywords: safety and alignment, model editing

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models, Theory

Languages Studied: English

Submission Number: 3179