Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2410.23605 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929703208615936 |
|---|---|
| author | Yu, Shuyang Bao, Runxue Bhatia, Parminder Kass-Hout, Taha Zhou, Jiayu Xiao, Cao |
| author_facet | Yu, Shuyang Bao, Runxue Bhatia, Parminder Kass-Hout, Taha Zhou, Jiayu Xiao, Cao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23605 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs Yu, Shuyang Bao, Runxue Bhatia, Parminder Kass-Hout, Taha Zhou, Jiayu Xiao, Cao Computation and Language 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. |
| title | Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2410.23605 |