arXiv AI July 22, 2026 By Brian Becker, Rui Chu, Yingjie Lao

Probabilistic Concept-Aware Steering for Trustworthy LLM Inference

arXiv:2607. 18259v1 Announce Type: new Abstract: Steering vectors (SVs), an inference-time intervention technique for large language models (LLMs), guide the generation process by adding a concept-specific direction vector to intermediate activations during inference.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Computation and Language

Sep 22

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

arXiv:2602.01654v2 Announce Type: replace Abstract: Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing...

By Jiaqian Li, Yanshu Li, Kuan-Hao Huang

llms fine-tuning

arXiv AI

Sep 10

Evaluating Steering Techniques using Human Similarity Judgments

arXiv:2505.19333v2 Announce Type: replace Abstract: Current evaluations of Large Language Model (LLM) steering techniques focus on task-specific performance, overlooking how well steered representati...

By Zach Studdiford, Timothy T. Rogers, Siddharth Suresh, Kushin Mukherjee

llms safety

arXiv AI

Jul 13

Multi-Attribute Steering of Language Models via Targeted Intervention

arXiv:2502. 12446v3 Announce Type: replace-cross Abstract: Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.

By Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal

llms nlp fine-tuning efficiency safety

arXiv Machine Learning

Jul 9

Towards Understanding Steering Strength

arXiv:2602. 02712v2 Announce Type: replace Abstract: A popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations.

By Magamed Taimeskhanov, Samuel Vaiter, Damien Garreau

llms

arXiv AI

Sep 17

Label-Confidence-Aware Uncertainty Estimation in Natural Language Generation

The paper introduces Label-Confidence-Aware Uncertainty Quantification (LCA-UQ), a method that uses Pointwise Kullback-Leibler divergence to align global entropy from multiple stochastic samples with the local confidence of a candidate answer. By bridging this gap, LCA-UQ improves the reliability and stability of uncertainty assessments in natural language generation. Experiments on popular LLMs and NLP datasets show that label sources significantly influence classification and that LCA-UQ outperforms existing uncertainty estimation approaches.

By Qinhong Lin, Yinglun Feng, Yuhao Zhang, Zhongliang Yang, Linna Zhou

llms nlp safety

arXiv AI

Jun 2

Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models

arXiv:2605. 04638v2 Announce Type: replace-cross Abstract: Uncertainty quantification (UQ) is an important technique for ensuring the trustworthiness of LLMs, given their tendency to hallucinate.

By Mingda Li, Rundong Lv, Xinyu Li, Weinan Zhang, Ting Liu

llms rag benchmarks

One email a morning, machine-written

Related stories

Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models

Evaluating Steering Techniques using Human Similarity Judgments

Multi-Attribute Steering of Language Models via Targeted Intervention

Towards Understanding Steering Strength

Label-Confidence-Aware Uncertainty Estimation in Natural Language Generation

Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large Language Models