cs.CL（2023-12-21）

📊 共 19 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (17 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (17 篇)

#	题目	一句话要点	标签	🔗	⭐
1	T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step	T-Eval：一种逐步评估大语言模型工具利用能力的新基准	large language model instruction following	✅
2	Large Language Models are Miscalibrated In-Context Learners	揭示大语言模型上下文学习的校准问题，并提出自集成方法提升校准度	large language model instruction following
3	Speech Translation with Large Language Models: An Industrial Practice	提出LLM-ST：一种基于大型语言模型的语音翻译工业实践方案	large language model chain-of-thought	✅
4	From Bytes to Biases: Investigating the Cultural Self-Perception of Large Language Models	研究揭示大型语言模型文化价值观偏向，主要受英语国家和经济发达国家影响	large language model
5	Deep de Finetti: Recovering Topic Distributions from Large Language Models	Deep de Finetti：从大型语言模型中恢复主题分布	large language model
6	Typhoon: Thai Large Language Models	Typhoon：为泰语设计的开源大型语言模型，性能媲美GPT-3.5。	large language model
7	Experimenting with Large Language Models and vector embeddings in NASA SciX	NASA SciX利用大语言模型和向量嵌入改进信息检索，降低幻觉	large language model
8	Shai: A large language model for asset management	提出面向资产管理行业的10B级大语言模型Shai，提升领域任务性能。	large language model
9	Illuminating the Black Box: A Psychometric Investigation into the Multifaceted Nature of Large Language Models	利用心理测量学方法探索大语言模型的多面人格特性	large language model
10	Developing Interactive Tourism Planning: A Dialogue Robot System Powered by a Large Language Model	提出基于大语言模型的交互式旅游规划对话机器人系统，提升旅行规划效率。	large language model
11	Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models	提出BIPIA基准测试集，评估并防御大语言模型中的间接提示注入攻击	large language model
12	Context-aware Decoding Reduces Hallucination in Query-focused Summarization	提出上下文感知解码以减少查询导向摘要中的幻觉问题	large language model	✅
13	Parameter Efficient Tuning Allows Scalable Personalization of LLMs for Text Entry: A Case Study on Abbreviation Expansion	参数高效微调实现LLM在文本输入中的可扩展个性化：以缩写扩展为例	large language model
14	ChatGPT as a commenter to the news: can LLMs generate human-like opinions?	评估ChatGPT生成类人新闻评论的能力：区分机器与人类评论仍具挑战	large language model
15	Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisations	系统性评测面向任务型对话系统：综述评估指标、结构及其操作化方法	large language model
16	SimLM: Can Language Models Infer Parameters of Physical Systems?	SimLM：探究大语言模型在物理系统参数推断中的能力与局限性	large language model
17	L-TUNING: Synchronized Label Tuning for Prompt and Prefix in LLMs	L-Tuning：一种面向LLM提示和前缀同步标签调优方法，提升NLI任务效率与精度。	large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
18	Towards More Faithful Natural Language Explanation Using Multi-Level Contrastive Learning in VQA	提出基于多层次对比学习的VQA自然语言解释模型，提升解释的忠实性	contrastive learning
19	How to Prune Your Language Model: Recovering Accuracy on the "Sparsity May Cry'' Benchmark	针对BERT模型，提出剪枝调优策略，显著提升Sparsity May Cry基准上的精度。	distillation large language model

⬅️ 返回 cs.CL 首页 · 🏠 返回主页