Cover Image

Can Revealed Preferences Clarify LLM Alignment and Steering?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yamin, Khurram, Tang, Jingjing, Horvitz, Eric, Wilder, Bryan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can LLMs Reconcile Knowledge Conflicts in Counterfactual Reasoning
by: Yamin, Khurram, et al.
Published: (2025)

Dependent Randomized Rounding for Budget Constrained Experimental Design
by: Yamin, Khurram, et al.
Published: (2025)

Accounting for Missing Covariates in Heterogeneous Treatment Estimation
by: Yamin, Khurram, et al.
Published: (2024)

When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMs
by: Yamin, Khurram, et al.
Published: (2026)

Failure Modes of LLMs for Causal Reasoning on Narratives
by: Yamin, Khurram, et al.
Published: (2024)

Predicting Language Models' Success at Zero-Shot Probabilistic Prediction
by: Ren, Kevin, et al.
Published: (2025)

Utility-Directed Conformal Prediction: A Decision-Aware Framework for Actionable Uncertainty Quantification
by: Cortes-Gomez, Santiago, et al.
Published: (2024)

Improving Instruction-Following in Language Models through Activation Steering
by: Stolfo, Alessandro, et al.
Published: (2024)

Comparing Targeting Strategies for Maximizing Social Welfare with Limited Resources
by: Sharma, Vibhhu, et al.
Published: (2024)

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment
by: Gadgil, Soham, et al.
Published: (2026)

Learning treatment effects while treating those in need
by: Wilder, Bryan, et al.
Published: (2024)

Steering Language Model Refusal with Sparse Autoencoders
by: O'Brien, Kyle, et al.
Published: (2024)

Improving constraint-based discovery with robust propagation and reliable LLM priors
by: Lyu, Ruiqi, et al.
Published: (2025)

Fostering the Ecosystem of AI for Social Impact Requires Expanding and Strengthening Evaluation Standards
by: Wilder, Bryan, et al.
Published: (2025)

DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
by: Wedgwood, James, et al.
Published: (2026)

BarrierSteer: LLM Safety via Learning Barrier Steering
by: Tran, Thanh Q., et al.
Published: (2026)

Adversarial Preference Learning for Robust LLM Alignment
by: Wang, Yuanfu, et al.
Published: (2025)

Explaining Concept Shift with Interpretable Feature Attribution
by: Lyu, Ruiqi, et al.
Published: (2025)

OEUVRE: OnlinE Unbiased Variance-Reduced loss Estimation
by: Pardeshi, Kanad, et al.
Published: (2025)

Decision-Focused Evaluation of Worst-Case Distribution Shift
by: Ren, Kevin, et al.
Published: (2024)

Combining digital data streams and epidemic networks for real time outbreak detection
by: Lyu, Ruiqi, et al.
Published: (2025)

Distributionally Robust Feature Selection
by: Swaroop, Maitreyi, et al.
Published: (2025)

Alignment Revisited: Are Large Language Models Consistent in Stated and Revealed Preferences?
by: Gu, Zhuojun, et al.
Published: (2025)

Data Selection for LLM Alignment Using Fine-Grained Preferences
by: Zhang, Jia, et al.
Published: (2025)

Alignment with Preference Optimization Is All You Need for LLM Safety
by: Alami, Reda, et al.
Published: (2024)

Nearly Optimal Active Preference Learning and Its Application to LLM Alignment
by: Zhao, Yao, et al.
Published: (2026)

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
by: Wurgaft, Daniel, et al.
Published: (2026)

D-STEER - Preference Alignment Techniques Learn to Behave, not to Believe -- Beneath the Surface, DPO as Steering Vector Perturbation in Activation Space
by: Raina, Samarth, et al.
Published: (2025)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
by: Kim, Dongyoung, et al.
Published: (2024)

HelpSteer2-Preference: Complementing Ratings with Preferences
by: Wang, Zhilin, et al.
Published: (2024)

AMPS: Adaptive Modality Preference Steering via Functional Entropy
by: Huang, Zihan, et al.
Published: (2026)

Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions
by: Raman, Naveen, et al.
Published: (2026)

Preference Alignment with Flow Matching
by: Kim, Minu, et al.
Published: (2024)

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment
by: Lin, Xiaoqiang, et al.
Published: (2025)

A General Framework for Inference-time Scaling and Steering of Diffusion Models
by: Singhal, Raghav, et al.
Published: (2025)

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
by: Xu, Zaiyan, et al.
Published: (2025)

Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize
by: Shah, Sanket, et al.
Published: (2023)

Data-Centric Human Preference with Rationales for Direct Preference Alignment
by: Just, Hoang Anh, et al.
Published: (2024)

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
by: Bigelow, Eric, et al.
Published: (2025)

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming
by: Mozannar, Hussein, et al.
Published: (2022)