CORTEXA
← Browse
arxivcs.LGcs.AI2026-07-22

OPIUM: Mitigating Steering Externalities and Over-Refusal via Dual Objective Latent Optimization

Kavin Aravindan, Arihant Rastogi, Krishak Aneja, Aadi Prasad, Saiyam Jain, Vaishnavi Shivkumar, Ponnurangam Kumaraguru

Activation steering provides a lightweight mechanism for controlling large language models at inference time, but steering vectors can have unintended externalities: utility vectors may weaken safety behavior, while refusal vectors may induce over-refusal on benign prompts. We introduce OPIUM (Optimizing Protected Injections via Utility Manifolds), a training-free method for sanitizing steering vectors through representation matching. Given reference behaviors on two prompt sets, OPIUM optimizes a new steering vector that preserves the downstream representations induced by the desired intervention while matching a safer reference behavior on prompts where the original vector fails. Across steering-externality and over-refusal settings, OPIUM improves the safety--utility tradeoff relative to vanilla steering and directional ablation, suggesting that harmful side effects of activation steering can often be mitigated directly in activation space.

View free PDFSource page

Related papers

arxivcs.LGcs.AI2026-07-31

MOT-SR: Multi-Objective Tool-Augmented Scientific Equation Discovery with Large Language Models

Boxiao Wang, Runxiang Wang, Kai Li, Chongming Li, Zhiwei Chen, Yifan Zhang, et al.

Symbolic Regression (SR) aims to discover analytical equations from observational data and plays a central role in scientific modeling. While recent Large Language Model (LLM) based approaches show promise, they face two limitations. First, they lack data analysis mechanisms for…

View free PDFSource page
arxivmath.OCcs.AIcs.LGstat.ML2026-07-24

Explicit Iteration Complexity of Exact Data-Driven Inverse Optimization for Integer Linear Programs

Akira Kitaoka

A data-driven inverse optimization problem (DDIOP) is the problem of estimating the objective-function parameters (weights) that explain observed optimal-solution data, and it arises in many applications, including integer linear programming (ILP). It is known that, by applying g…

View free PDFSource page
arxivcs.LGcs.AI2026-07-23

Multi-turn RL with Structural and Performance Aware Rewards for CUDA Kernel Generation

Quazi Ishtiaque Mahmud, Nesreen K. Ahmed, Ali Jannesari

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful technique to enhance the reasoning capacity of LLMs for optimized code generation. However, existing RLVR approaches primarily rely on outcome-based signals such as correctness and speedup, overlookin…

View free PDFSource page
arxiveess.AScs.AIcs.LGcs.SD2026-07-31

Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens

Yi Luo, Rongzhi Gu, Jixun Yao

Balancing sequence length, representational capacity, and long-horizon stability is a central problem in autoregressive (AR) speech and audio generation. Representations with higher frame rates or greater capacity can preserve more signal detail, but they also make streaming gene…

View free PDFSource page
arxivcs.LGcs.AI2026-07-31

HERO: History-Enriched Rollout Training for Long-Horizon Autoregressive Neural Operators

Jiaquan Zhang, Shuxu Chen, Haifan Meng, Yi Lu, Zhihan Lyu, Fan Mo, et al.

Neural operators provide fast surrogates for time-dependent partial differential equations (PDEs) by applying a learned evolution operator recursively to its own predictions, but this autoregressive rollout feeds every prediction error back as input, so local errors accumulate. E…

View free PDFSource page
arxivcs.LGcs.AI2026-07-31

TFGformer: Multivariate Time Series Forecasting via Time-Frequency Graph Learning and Covariate Fusion

Yu Sun, Yuan Chang, Xiaohou Shi, Yan Sun

Large-scale multivariate time series from heterogeneous IoT sensors demand accurate long-term forecasting for resource scheduling and predictive maintenance. While recent time series foundation models exhibit strong generalization, they rely on static parametric knowledge and lac…

View free PDFSource page