We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong
This addresses the challenge of safe and reliable deployment of LLMs by preventing trade-offs between alignment objectives, though it is incremental as it builds on existing steering vector methods.
The paper tackles the problem of aligning large language models to multiple objectives (helpfulness, harmlessness, honesty) without causing catastrophic forgetting or inconsistency, and proposes Adaptive Multi-Branch Steering (AMBS), which improves average alignment scores by +32.4% and reduces unsafe outputs by 11.0% on DeepSeek-7B compared to a baseline.
Alignment of Large Language Models (LLMs) along multiple objectives-helpfulness, harmlessness, and honesty (HHH)-is critical for safe and reliable deployment. Prior work has used steering vector-small control signals injected into hidden states-to guide LLM outputs, typically via one-to-one (1-to-1) Transformer decoders. In this setting, optimizing a single alignment objective can inadvertently overwrite representations learned for other objectives, leading to catastrophic forgetting. More recent approaches extend steering vectors via one-to-many (1-to-N) Transformer decoders. While this alleviates catastrophic forgetting, naive multi-branch designs optimize each objective independently, which can cause inference fragmentation-outputs across HHH objectives may become inconsistent. We propose Adaptive Multi-Branch Steering (AMBS), a two-stage 1-to-N framework for unified and efficient multi-objective alignment. In Stage I, post-attention hidden states of the Transformer layer are computed once to form a shared representation. In Stage II, this representation is cloned into parallel branches and steered via a policy-reference mechanism, enabling objective-specific control while maintaining cross-objective consistency. Empirical evaluations on Alpaca, BeaverTails, and TruthfulQA show that AMBS consistently improves HHH alignment across multiple 7B LLM backbones. For example, on DeepSeek-7B, AMBS improves average alignment scores by +32.4% and reduces unsafe outputs by 11.0% compared to a naive 1-to-N baseline, while remaining competitive with state-of-the-art methods.