arXiv Computation and Language
Language Steering for Multilingual In-Context Learning
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Sep 1
Cross-lingual Functional Vectors for Emotion Detection in Large Language Models
arXiv:2608.29613v1 Announce Type: cross Abstract: Function vectors (FVs) have recently emerged as a promising mechanism for steering the behavior of large language models (LLMs) by injecting task-spe...
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.
arXiv Machine Learning
Oct 7
Two Vectors Replace In-Context Demos: Structured Task Adaptation via Embeddings
arXiv:2610.07572v1 Announce Type: cross Abstract: In-context learning (ICL) adapts frozen large multimodal models (LMMs) to new tasks from a few demonstrations (demos), but re-encodes them at every q...
arXiv AI
Jun 17
When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning
arXiv:2606. 18033v1 Announce Type: cross Abstract: Cross-lingual transfer in multilingual NLP has been widely explored in supervised fine-tuning contexts, where factors like data availability and linguistic similarity largely determine transfer quality.
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...
arXiv Machine Learning
Sep 15
TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals
TwinICL is a procedurally generated benchmark that pairs matched text and image versions of tasks to enable controlled comparison of in‑context learning (ICL) across modalities. Experiments on six open‑weight models and 38 tasks show that multimodal ICL consistently underperforms text‑only ICL, with varying gaps by task family. Interventions targeting visual access, task framing, and reasoning can recover strong multimodal performance on a diagnostic subset, yet a modality gap remains even when explicit task instructions are provided, highlighting the dual role of demonstrations as context and evidence.