Cover Image

Beyond Multiple Choice: Evaluating Steering Vectors for Summarization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Braun, Joschka, Eickhoff, Carsten, Bahrainian, Seyed Ali
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Logit Reweighting for Topic-Focused Summarization
by: Braun, Joschka, et al.
Published: (2025)

Understanding (Un)Reliability of Steering Vectors in Language Models
by: Braun, Joschka, et al.
Published: (2025)

Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations
by: Braun, Joschka
Published: (2026)

When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
by: Zhou, Xinyu, et al.
Published: (2026)

Enhancing Retrieval-Augmented Generation: A Study of Best Practices
by: Li, Siran, et al.
Published: (2025)

Language Models Implement Simple Word2Vec-style Vector Arithmetic
by: Merullo, Jack, et al.
Published: (2023)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
by: Jin, Zehao, et al.
Published: (2026)

Stable Anisotropic Regularization
by: Rudman, William, et al.
Published: (2023)

Beyond Contrastive Learning: Synthetic Data Enables List-wise Training with Multiple Levels of Relevance
by: Esfandiarpoor, Reza, et al.
Published: (2025)

Circuit Component Reuse Across Tasks in Transformer Language Models
by: Merullo, Jack, et al.
Published: (2023)

Predicting Where Steering Vectors Succeed
by: Billa, Jayadev
Published: (2026)

CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization
by: Zhang, Ruochen, et al.
Published: (2023)

VSPO: Vector-Steered Policy Optimization for Behavioral Control
by: Zhang, Xuechen, et al.
Published: (2026)

White-Box Sensitivity Auditing with Steering Vectors
by: Cyberey, Hannah, et al.
Published: (2026)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
by: Cao, Yuanpu, et al.
Published: (2024)

From Topology to Retrieval: Decoding Embedding Spaces with Unified Signatures
by: Rottach, Florian, et al.
Published: (2025)

Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization
by: Xu, Lei, et al.
Published: (2024)

Answer Matching Outperforms Multiple Choice for Language Model Evaluation
by: Chandak, Nikhil, et al.
Published: (2025)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
by: Chalnev, Sviatoslav, et al.
Published: (2024)

A Unified Understanding and Evaluation of Steering Methods
by: Im, Shawn, et al.
Published: (2025)

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
by: Siddique, Zara, et al.
Published: (2025)

Directional Attractors in LLM Reasoning: How Similarity Retrieval Steers Iterative Summarization Based Reasoning
by: Tekin, Cagatay, et al.
Published: (2025)

Generating Plausible Distractors for Multiple-Choice Questions via Student Choice Prediction
by: Lee, Yooseop, et al.
Published: (2025)

No Training Wheels: Steering Vectors for Bias Correction at Inference Time
by: Gupta, Aviral, et al.
Published: (2025)

Exploration Hacking: Can LLMs Learn to Resist RL Training?
by: Jang, Eyon, et al.
Published: (2026)

DisGeM: Distractor Generation for Multiple Choice Questions with Span Masking
by: Cavusoglu, Devrim, et al.
Published: (2024)

Listening to the Wise Few: Select-and-Copy Attention Heads for Multiple-Choice QA
by: Tulchinskii, Eduard, et al.
Published: (2024)

SteerConf: Steering LLMs for Confidence Elicitation
by: Zhou, Ziang, et al.
Published: (2025)

K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction
by: Abdullahi, Tassallah, et al.
Published: (2025)

Hypothesis Testing for Quantifying LLM-Human Misalignment in Multiple Choice Settings
by: Hong, Harbin, et al.
Published: (2025)

Policies and Evaluation for Online Meeting Summarization
by: Schneider, Felix, et al.
Published: (2025)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
by: Siu, Vincent, et al.
Published: (2025)

Beyond the Singular: Revealing the Value of Multiple Generations in Benchmark Evaluation
by: Zhang, Wenbo, et al.
Published: (2025)

Option-ID Based Elimination For Multiple Choice Questions
by: Zhu, Zhenhao, et al.
Published: (2025)

Biomedical Entity Linking as Multiple Choice Question Answering
by: Lin, Zhenxi, et al.
Published: (2024)

Extending Activation Steering to Broad Skills and Multiple Behaviours
by: van der Weij, Teun, et al.
Published: (2024)

Beyond Single Concept Vector: Modeling Concept Subspace in LLMs with Gaussian Distribution
by: Zhao, Haiyan, et al.
Published: (2024)

Benchmarking Generation and Evaluation Capabilities of Large Language Models for Instruction Controllable Summarization
by: Liu, Yixin, et al.
Published: (2023)

Can We Trust the Performance Evaluation of Uncertainty Estimation Methods in Text Summarization?
by: He, Jianfeng, et al.
Published: (2024)