Concept-Level Explainability for Auditing & Steering LLM Responses
As large language models (LLMs) become widely deployed, concerns about their safety and alignment grow. An approach to steer LLM behavior, such as mitigating biases or defending against jailbreaks, is to identify which parts of a prompt influence specific aspects of the model's output. Token-level attribution methods offer a promising solution, but still struggle in text generation, explaining the presence of each token in the output separately, rather than the underlying semantics of the entire LLM response. We introduce ConceptX, a model-agnostic, concept-level explainability method that identifies the concepts, i.e., semantically rich tokens in the prompt, and assigns them importance based on the outputs' semantic similarity. Unlike current token-level methods, ConceptX also offers to preserve context integrity through in-place token replacements and supports flexible explanation goals, e.g., gender bias. ConceptX enables both auditing, by uncovering sources of bias, and steering, by modifying prompts to shift the sentiment or reduce the harmfulness of LLM responses, without requiring retraining. Across three LLMs, ConceptX outperforms token-level methods like TokenSHAP in both faithfulness and human alignment. Steering tasks boost sentiment shift by 0.252 versus 0.131 for random edits and lower attack success rates from 0.463 to 0.242, outperforming attribution and paraphrasing baselines. While prompt engineering and self-explaining methods sometimes yield safer responses, ConceptX offers a transparent and faithful alternative for improving LLM safety and alignment, demonstrating the practical value of attribution-based explainability in guiding LLM behavior.
Code (1)
Tasks
Prompt EngineeringSemantic SimilaritySemantic Textual SimilarityText GenerationSimilar Papers 제목 키워드 기반
Analyzing Fine-tuning Representation Shift for Multimodal LLMs Steering alignment
Multimodal LLMs have reached remarkable levels of proficiency in understanding multimodal inputs, driving extensive research to develop increasingly powerful models. However, much less attention has been paid to understa…
White-Box Sensitivity Auditing with Steering Vectors
Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that asse…
Breaking Bad: Interpretability-Based Safety Audits of State-of-the-Art LLMs
Effective safety auditing of large language models (LLMs) demands tools that go beyond black-box probing and systematically uncover vulnerabilities rooted in model internals. We present a comprehensive, interpretability-…
Activation Steering via Generative Causal Mediation
Where should we intervene in a language model (LM) to localize and control behaviors that are diffused across many tokens of a long-form response? We introduce Generative Causal Mediation (GCM), a procedure for selecting…
Style TransferEfficient and accurate steering of Large Language Models through attention-guided feature learning
Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and…