ContextFocus: Making AI Stick to the Evidence

Kari Jaaskelainen

08 Jan 2026 — 1 min read

LLMs often stick to what they “remember,” even when you show them better, up‑to‑date evidence. ContextFocus offers a fix.

It’s a lightweight “activation steering” technique that nudges models to follow the provided context over their internal guesses—no finetuning required and minimal slowdown at inference.

Improves contextual faithfulness in knowledge-conflict cases, preserving fluency.
Plug-and-play: apply at inference; effective on larger models.
Complementary to prompting and retrieval strategies.
Validated on the ConFiQA benchmark, outperforming strong baselines like ContextDPO, COIECD, and prompting-only setups.

Bottom line: if you rely on LLMs to answer with provided, up-to-date sources, ContextFocus helps them stick to the evidence—efficiently and robustly.

Paper: https://arxiv.org/abs/2601.04131v1

Register: https://www.AiFeta.com

#AI #LLM #NLP #MachineLearning #RAG #ActivationSteering #TrustworthyAI #ContextFocus #AIEthics

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added