Dynamic Uncertainty Ranking: Enhancing In-Context Learning for Long-Tail Knowledge in LLMs
원문 초록
Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models' memorization. Prior work has shown that in-context learning (ICL) with retriever augmentation can help LLMs better capture long-tail knowledge, reducing their reliance on pre-trained data. Despite these advances, we observe that LLM predictions for long-tail questions remain uncertain to variations in retrieved samples. To take advantage of the uncertainty in ICL for guiding LLM predictions toward correct answers on long-tail samples, we propose a reinforcement learning-based dynamic uncertainty ranking method for ICL that accounts for the varying impact of each retrieved sample on LLM predictions. Our approach prioritizes more informative and stable samples while demoting misleading ones, updating rankings based on the feedback from the LLM w.r.t. each retrieved sample. To enhance training efficiency and reduce query costs, we introduce a learnable dynamic ranking threshold, adjusted when the model encounters negative prediction shifts. Experimental results on various question-answering datasets from different domains show that our method outperforms the best baseline by $2.76\%$, with a notable $5.96\%$ boost in accuracy on long-tail questions that elude zero-shot inference.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Evolving Prompts In-Context: An Open-ended, Self-replicating Perspective
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
SMMILE: An Expert-Driven Benchmark for Multimodal Medical In-Context Learning
SV-LLM: An Agentic Approach for SoC Security Verification using Large Language Models
In-Context Learning Strategies Emerge Rationally
Provoking Multi-modal Few-Shot LVLM via Exploration-Exploitation In-Context Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.