| 1 |
Prompt Sketching for Large Language Models |
提出提示草图以解决大语言模型生成过程中的连贯性问题 |
large language model chain-of-thought |
|
|
| 2 |
Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models |
提出GBLM-Pruner以优化大语言模型的剪枝决策 |
large language model |
✅ |
|
| 3 |
Massive Editing for Large Language Models via Meta Learning |
提出MAhmen以解决大语言模型知识更新问题 |
large language model |
✅ |
|
| 4 |
LongQLoRA: Efficient and Effective Method to Extend Context Length of Large Language Models |
提出LongQLoRA以高效扩展大语言模型的上下文长度 |
large language model |
✅ |
|
| 5 |
TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models |
提出TEAL以解决多模态大语言模型的交互建模问题 |
large language model |
|
|
| 6 |
First Tragedy, then Parse: History Repeats Itself in the New Era of Large Language Models |
探讨大语言模型时代下NLP研究的持续贡献与挑战 |
large language model |
|
|
| 7 |
On the steerability of large language models toward data-driven personas |
提出数据驱动的人格定义以增强大语言模型的可控性 |
large language model |
|
|
| 8 |
How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure |
探讨大型语言模型在论元结构中的语言泛化能力 |
large language model |
✅ |
|
| 9 |
Rethinking Benchmark and Contamination for Language Models with Rephrased Samples |
提出基于LLM的去污染方法以解决语言模型基准污染问题 |
large language model |
✅ |
|
| 10 |
Pre-training LLMs using human-like development data corpus |
提出使用类人发展数据语料库进行大规模语言模型预训练 |
large language model |
|
|
| 11 |
Large-scale study of human memory for meaningful narratives |
利用大型语言模型研究人类记忆的叙事理解 |
large language model |
|
|
| 12 |
Evaluating Generative Ad Hoc Information Retrieval |
提出新评估方法以解决生成式信息检索的评估挑战 |
large language model |
|
|
| 13 |
Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection |
提出多标签多目标采样策略以优化计算态度检测的标注质量 |
large language model |
|
|