| 1 |
Recursive Chain-of-Feedback Prevents Performance Degradation from Redundant Prompting |
提出递归反馈链方法以解决冗余提示导致的性能下降问题 |
large language model |
|
|
| 2 |
RACER: An LLM-powered Methodology for Scalable Analysis of Semi-structured Mental Health Interviews |
提出RACER以解决半结构化心理健康访谈分析效率低下问题 |
large language model |
|
|
| 3 |
Unified Hallucination Detection for Multimodal Large Language Models |
提出统一的多模态幻觉检测框架以解决MLLMs中的幻觉问题 |
large language model multimodal |
|
|
| 4 |
MULTI: Multimodal Understanding Leaderboard with Text and Images |
提出MULTI数据集以评估多模态大语言模型的真实能力 |
large language model multimodal |
|
|
| 5 |
Nevermind: Instruction Override and Moderation in Large Language Models |
提出指令覆盖与调节机制以提升大语言模型的指令遵循能力 |
large language model instruction following |
|
|
| 6 |
Large Language Models are Geographically Biased |
研究大型语言模型的地理偏见以提升公平性与准确性 |
large language model foundation model |
✅ |
|
| 7 |
Enhancing textual textbook question answering with large language models and retrieval augmented generation |
提出PLRTQA框架以解决文本教科书问答中的推理不足问题 |
large language model multimodal |
✅ |
|
| 8 |
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models |
提出不确定性思维算法以增强大语言模型的信息获取能力 |
large language model |
✅ |
|
| 9 |
Multi-Lingual Malaysian Embedding: Leveraging Large Language Models for Semantic Representations |
提出多语言马来西亚嵌入模型以提升语义表示能力 |
large language model |
✅ |
|
| 10 |
EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models |
提出EasyInstruct框架以解决指令处理标准化问题 |
large language model |
✅ |
|
| 11 |
How do Large Language Models Learn In-Context? Query and Key Matrices of In-Context Heads are Two Towers for Metric Learning |
提出新假设以解释大语言模型的上下文学习机制 |
large language model |
|
|
| 12 |
Psychological Assessments with Large Language Models: A Privacy-Focused and Cost-Effective Approach |
提出基于大型语言模型的心理评估方法以提高隐私性与成本效益 |
large language model |
|
|
| 13 |
LB-KBQA: Large-language-model and BERT based Knowledge-Based Question and Answering System |
提出基于大语言模型和BERT的知识问答系统以解决意图识别问题 |
large language model |
|
|
| 14 |
UniMem: Towards a Unified View of Long-Context Large Language Models |
提出UniMem框架以统一长上下文大语言模型的处理方法 |
large language model |
|
|
| 15 |
LLM Agents in Interaction: Measuring Personality Consistency and Linguistic Alignment in Interacting Populations of Large Language Models |
提出个性化对话模型以提升LLM代理的一致性与语言对齐 |
large language model |
|
|
| 16 |
Best Practices for Text Annotation with Large Language Models |
提出文本注释最佳实践以解决LLM应用中的质量问题 |
large language model |
|
|
| 17 |
CIDAR: Culturally Relevant Instruction Dataset For Arabic |
提出CIDAR以解决阿拉伯文化相关指令数据集不足问题 |
large language model |
✅ |
|
| 18 |
Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases |
提出基于意图的提示校准方法以优化大语言模型的提示工程 |
large language model |
✅ |
|
| 19 |
PanGu-$π$ Pro:Rethinking Optimization and Architecture for Tiny Language Models |
提出PanGu-$π$ Pro以优化小型语言模型的架构与训练策略 |
large language model |
✅ |
|
| 20 |
KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache |
提出KIVI以解决KV缓存量化问题 |
large language model |
✅ |
|
| 21 |
SWAG: Storytelling With Action Guidance |
提出SWAG以解决自动化故事生成的参与度不足问题 |
large language model |
|
|
| 22 |
JOBSKAPE: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching |
提出JobSkape框架以解决技能匹配中的合成数据不足问题 |
large language model |
|
|
| 23 |
English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts |
提出使用英语提示改善非英语文本的情感分类 |
large language model |
|
|