Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization
Steering vectors are a lightweight method for controlling text properties by adding a learned bias to language model activations at inference time. So far, steering vectors have predominantly been evaluated in multiple-choice settings, while their effectiveness in free-form generation tasks remains understudied. Moving "Beyond Multiple Choice," we thoroughly evaluate the effectiveness of steering vectors in adaptively controlling topical focus, sentiment, toxicity, and readability in abstractive summaries of the NEWTS dataset. We find that steering effectively controls the targeted summary properties, but high steering strengths consistently degrade both intrinsic and extrinsic text quality. Compared to steering, prompting offers weaker control, while preserving text quality. Combining steering and prompting yields the strongest control over text properties and offers the most favorable efficacy-quality trade-off at moderate steering strengths. Our results underscore the practical trade-off between control strength and text quality preservation when applying steering vectors to free-form generation tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
FormLanguage ModelingLanguage ModellingMultiple-choiceSimilar Papers 제목 키워드 기반
Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors
Large language models (LLMs) are increasingly deployed as autonomous decision-makers in strategic settings, yet we have limited tools for understanding their high-level behavioral traits. We use activation steering metho…
SwordBench: Evaluating Orthogonality of Steering Image Representations
Steering or intervening on model representations at inference time to correct predictions is essential for AI interpretability and safety, yet existing evaluation protocols are limited to ambiguous language modeling task…
YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation
Steering Large Language Models (LLMs) through activation interventions has emerged as a lightweight alternative to fine-tuning for alignment and personalization. Recent work on Bi-directional Preference Optimization (BiP…
General KnowledgeDomain AdaptationSteering Llama 2 via Contrastive Activation Addition
We introduce Contrastive Activation Addition (CAA), an innovative method for steering language models by modifying their activations during forward passes. CAA computes "steering vectors" by averaging the difference in r…
Multiple-choiceOn the Non-Identifiability of Steering Vectors in Large Language Models
Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions …