paper-with-me

홈 › Papers

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models

2026-01-07 · Nikhil Anand, Shwetha Somasundaram, Anirudh Phukan, Apoorv Saxena, Koyel Mukherjee arxiv

Large Language Models (LLMs) encode vast amounts of parametric knowledge during pre-training. As world knowledge evolves, effective deployment increasingly depends on their ability to faithfully follow externally retrieved context. When such evidence conflicts with the model's internal knowledge, LLMs often default to memorized facts, producing unfaithful outputs. In this work, we introduce ContextFocus, a lightweight activation steering approach that improves context faithfulness in such knowledge-conflict settings while preserving fluency and efficiency. Unlike prior approaches, our solution requires no model finetuning and incurs minimal inference-time overhead, making it highly efficient. We evaluate ContextFocus on the ConFiQA benchmark, comparing it against strong baselines including ContextDPO, COIECD, and prompting-based methods. Furthermore, we show that our method is complementary to prompting strategies and remains effective on larger models. Extensive experiments show that ContextFocus significantly improves contextual-faithfulness. Our results highlight the effectiveness, robustness, and efficiency of ContextFocus in improving contextual-faithfulness of LLM outputs.

📄 PDF Abstract BibTeX arXiv:2601.04131

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Contextual Linear Activation Steering of Language Models

2026-04-27 · Brandon Hsu, Daniel Beaglehole, Adityanarayanan Radhakrishnan, Mikhail Belkin arxiv

Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effective, existing methods often apply a fixed …

Activation Scaling for Steering and Interpreting Language Models

2024-10-07 · Niklas Stoehr, Kevin Du, Vésteinn Snæbjarnarson, Robert West 외

Given the prompt "Rome is in", can we steer a language model to flip its prediction of an incorrect token "France" to a correct token "Italy" by only multiplying a few relevant activation vectors with scalars? We argue t…

Language ModelingLanguage Modelling

Steering MoE LLMs via Expert (De)Activation

2025-09-11 · Mohsen Fayyaz, Ali Modarressi, Hanieh Deilamsalehy, Franck Dernoncourt 외 arxiv

Mixture-of-Experts (MoE) in Large Language Models (LLMs) routes each token through a subset of specialized Feed-Forward Networks (FFN), known as experts. We present SteerMoE, a framework to steer MoE models by detecting …

Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering

2024-09-16 · Qingru Zhang, Xiaodong Yu, Chandan Singh, Xiaodong Liu 외

Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize their input contexts, resulting in responses…

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders

2026-01-06 · Ruikang Zhang, Shuo Wang, Qi Su arxiv

Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal feature…