arXiv AI September 24, 2026 By Pei-lin Li, Qingle Liu, Junyang Feng, Siyu Li, Sunqi Fan, Xin-Sheng Chen, Shuojin Yang

When Context Misleads: In-context Learning with Jurisdiction in Large Language Models

The paper "When Context Misleads: In-context Learning with Jurisdiction in Large Language Models" introduces FakeContextBench, a benchmark of pseudoscientific claims across seven domains to test large language models’ ability to judge whether contextual information should dictate the answer. Experiments show that both commercial and open‑source models struggle with context authority and that standard ICL fine‑tuning can worsen susceptibility to misleading context. The authors propose Jurisdiction In‑Context Learning (J‑ICL), a post‑training framework that adds context validation to the objective, which improves benchmark scores and reality accuracy by significant margins over baseline models.

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.

Hugging Face Trending Papers

Sep 23

When Context Misleads: In-context Learning with Jurisdiction in Large Language Models

In-Context Learning (ICL) has become a cornerstone of modern LLM deployment. However, existing ICL post-training methods have a critical blind spot: they excel at extracting patterns from demonstratio...

llms fine-tuning benchmarks

arXiv AI

Jul 7

Context Tuning for In-Context Optimization

arXiv:2507. 04221v3 Announce Type: replace-cross Abstract: We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates.

By Jack Lu, Ryan Teehan, Zhenbang Yang, Mengye Ren

llms benchmarks

arXiv AI

Oct 16

Language Models Struggle to Use Representations Learned In-Context

The article examines whether large language models (LLMs) can effectively use representations they learn in-context to perform downstream tasks. Experiments with open‑weight LLMs on next‑token prediction and a new adaptive world modeling task reveal that these models struggle to deploy novel semantics defined in-context, even when such semantics are encoded in their latent representations. The study also shows that state‑of‑the‑art closed‑source reasoning models similarly fail to reliably leverage in‑context patterns, highlighting a gap in flexible representation usage.

By Michael A. Lepori, Tal Linzen, Ann Yuan, Katja Filippova

llms benchmarks

arXiv AI

Oct 2

Capturing In-Context Learning Dynamics with Task Operators

arXiv:2610.01054v1 Announce Type: cross Abstract: In-context learning (ICL) enables language models to perform new tasks from demonstrations without weight updates. However, every ICL inference requi...

By Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Wenqian Ye, Aidong Zhang

llms

arXiv Computation and Language

Sep 2

Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning

arXiv:2609.00759v1 Announce Type: new Abstract: Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output s...

By Jinhu Qi, Minda Hu, Wentao Zhang, Weiqiang Jin, Yanyu Chen, Junli Wang, Irwin King

llms agents reinforcement-learning benchmarks

arXiv AI

Jul 28

How Context Attribution Handles What the Model Already Knows

arXiv:2607. 23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response.

By Quoc-Huy Trinh, Lin Zhu, Sebastian Szyller

llms benchmarks

One email a morning, machine-written

Related stories

When Context Misleads: In-context Learning with Jurisdiction in Large Language Models

Context Tuning for In-Context Optimization

Language Models Struggle to Use Representations Learned In-Context

Capturing In-Context Learning Dynamics with Task Operators

Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning

How Context Attribution Handles What the Model Already Knows