Multi-Attribute Steering of Language Models via Targeted Intervention (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches for steering large language models fail to scale to multi-attribute settings with conflicts, such as enhancing helpfulness while also reducing toxicity. |
| Approach: | They propose a steering framework for selective token-level intervention across multiple attributes that enforcing sparsity and orthogonality among vectors for different attributes. |
| Outcome: | The proposed framework outperforms existing ITI and parameter-efficient fine-tuning approaches across question answering tasks and generative tasks. |
Similar Papers
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Empirical results show that K-Steering outperforms strong baselines in accurately steering multiple behaviors. |
| Approach: | They propose a method that trains a single classifier on hidden activations and computes intervention directions via gradients at inference time. |
| Outcome: | The proposed method outperforms strong baselines in steering multiple behaviors. |
GrAInS: Gradient-based Attribution for Inference-Time Steering of LLMs and VLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models often ignore token-level causal influence and underutilize model logits. |
| Approach: | They propose a novel approach that uses a gradient-based approach to identify influential tokens and construct directional steering vectors based on their contribution to preferred over dispreferred outputs. |
| Outcome: | The proposed approach outperforms fine-tuning and prior steering methods on both LLM and VLM tasks without degrading fluency or general capabilities. |
Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Despite efforts to mitigate social bias in large language models, representational harms such as stereotyping continue to exist in both open and closed-source models. |
| Approach: | They propose a method to modify model activations in forward passes by applying steering vectors to a BBQ dataset and comparing their results to bias mitigation methods. |
| Outcome: | The proposed method outperforms 3 other bias mitigation methods on the BBQ dataset and shows the lowest impact on MMLU scores. |
FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for inference-time steering fail to be effective, utility-preserving and training-efficient due to rigid, one-size-fits-all designs and limited adaptability. |
| Approach: | They propose a steering framework that decomposes inference-time steering into two stages . they propose 'conditional steering' mechanism that preserves model utility by avoiding unnecessary steering . a 'mixture-of-Steering-Experts' mechanism captures multimodal nature of desired steering behaviors . |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on safety and truthfulness benchmarks. |
Beyond Multiple Choice: Evaluating Steering Vectors for Summarization (2026.findings-eacl)
Copied to clipboard
| Challenge: | Recent methods for controlling language models can often be classified into three main strategies: prompt engineering, trainable decoding mechanisms, fine-tuning according to specific objectives. |
| Approach: | They evaluate steering vectors for controlling topical focus, sentiment, toxicity, and readability in abstractive summaries across the SAMSum, NEWTS, and arXiv datasets. |
| Outcome: | The proposed method is effective in free-form generation, but high steering strengths induce degenerate repetition and factual hallucinations. |
InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance (2024.emnlp-main)
Copied to clipboard
Pengyu Wang, Dong Zhang, Linyang Li, Chenkun Tan, Xinghao Wang, Mozhi Zhang, Ke Ren, Botian Jiang, Xipeng Qiu
| Challenge: | Existing methods for enhancing harmlessness and helpfulness of large language models (LLMs) involve complex and resource-intensive training processes. |
| Approach: | They propose a method that decouples harmlessness from helpfulness during inference phase. |
| Outcome: | The proposed method significantly reduces the attack success rate (ASR) of harmful instructions and jailbreak instructions while maintaining almost unchanged performance in downstream tasks. |
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) achieve excellent performance through pretraining on extensive data. |
| Approach: | They propose an efficient selective layer intervention based on parameter-efficient fine-tuning methods to select the optimal steering layer to modulate LLM semantics. |
| Outcome: | The proposed approach is based on a model-agnostic framework and is safe to deploy. |
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective (2025.findings-acl)
Copied to clipboard
Yipeng Kang, Junqi Wang, Yexin Li, Mengmeng Wang, Wenming Tu, Quansen Wang, Hengli Li, Tingjun Wu, Xue Feng, Fangwei Zhong, Zilong Zheng
| Challenge: | Current approaches to value alignment focus on a few core values, such as helpfulness, harmlessness, and honesty. |
| Approach: | They propose to use latent causal value graphs to guide two lightweight value-steering methods . role-based prompting and sparse autoencoder (SAE) steering are also used . |
| Outcome: | Experiments on Gemma-2B-IT and Llama3-8B- IT show that the proposed methods are effective and controllable. |
Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect (2025.emnlp-main)
Copied to clipboard
| Challenge: | Prior work has focused largely on binary grammatical contrasts, but how do they encode their syntactic knowledge internally? |
| Approach: | They propose to use a multidimensional hierarchical grammar phenomenon to identify distinct, orthogonal directions in residual space to demonstrate causal control over both grammatical features. |
| Outcome: | The proposed model can encode tense and aspect in human-like ways, but effective steering during generation is sensitive to multiple factors and requires manual tuning or automated optimization. |
Activation Scaling for Steering and Interpreting Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a successful intervention should flip the correct with the wrong token, while remaining sparse. |
| Approach: | They propose to use activation scaling to flip the correct with the wrong token . they use gradient-based optimization to learn and evaluate a specific kind of efficient intervention . |
| Outcome: | The proposed method performs comparable with steering vectors but is much less minimal. |