conftrace_

instruction-tuning data

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

instruction tuning (2) ideological manipulation (1) bias generalization (1) reference-level feedback (1) action policy (1) large language model (1) poisoned training data (1) ideological bia (1) visual instruction (1) vision-language-action model (1)

Papers

Beyond Sample-Level Feedback: Using Reference-Level Feedback to Guide Data Synthesis EACL 2026 LLaRA: Supercharging Robot Learning Data for Vision-Language Policy ICLR 2025 How Susceptible are Large Language Models to Ideological Manipulation? EMNLP 2024 VIGC: Visual Instruction Generation and Correction AAAI 2024