cs.CL（2024-12-24）

📊 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) (16 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (16 篇)

#题目一句话要点标签🔗⭐
1 Multi-Agents Based on Large Language Models for Knowledge-based Visual Question Answering 提出基于大语言模型的多智能体投票框架，提升知识型视觉问答性能。 large language model
2 M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models 提出M-Ped：一种多提示集成解码方法，提升大型语言模型的生成质量。 large language model
3 Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation 提出Amar框架，通过自适应多方面检索增强提升大语言模型在知识图谱问答中的表现。 large language model
4 Neuron-Level Differentiation of Memorization and Generalization in Large Language Models 揭示大语言模型神经元层面的记忆与泛化差异，实现行为干预 large language model
5 Is Large Language Model Good at Triple Set Prediction? An Empirical Study 探索LLM在三元组集合预测任务中的能力与局限性 large language model
6 Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study 探索大型语言模型在代码漏洞检测中的应用与性能 large language model ✅
7 Ensuring Consistency for In-Image Translation 提出HCIIT框架，解决图像内翻译中翻译一致性和图像生成一致性问题 large language model multimodal chain-of-thought
8 LSAQ: Layer-Specific Adaptive Quantization for Large Language Model Deployment LSAQ：针对大语言模型部署的层级自适应量化方法 large language model
9 Molly: Making Large Language Model Agents Solve Python Problem More Logically 提出Molly智能体，增强大语言模型在Python编程问题上的逻辑推理能力 large language model
10 AgreeMate: Teaching LLMs to Haggle AgreeMate：利用大型语言模型进行自然语言议价策略训练 large language model chain-of-thought
11 Token-Budget-Aware LLM Reasoning 提出Token-Budget-Aware框架，在保证LLM推理性能的同时降低token使用成本。 large language model chain-of-thought ✅
12 DynaGRAG | Exploring the Topology of Information for Advancing Language Understanding and Generation in Graph Retrieval-Augmented Generation DynaGRAG：探索信息拓扑结构，提升图检索增强生成中的语言理解与生成能力 large language model
13 GenAI Content Detection Task 2: AI vs. Human -- Academic Essay Authenticity Challenge 学术论文真伪鉴别挑战赛：利用GenAI检测AI生成与人类撰写的学术论文 large language model
14 On the Applicability of Zero-Shot Cross-Lingual Transfer Learning for Sentiment Classification in Distant Language Pairs 利用XLM-R探索零样本跨语言迁移学习在远距离语言情感分类中的适用性 zero-shot transfer
15 Improving Factuality with Explicit Working Memory 提出EWE：通过显式工作记忆提升长文本生成的事实准确性 large language model
16 Lla-VAP: LSTM Ensemble of Llama and VAP for Turn-Taking Prediction Lla-VAP：结合LLM与VAP的LSTM集成模型用于预测对话轮替 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
17 Distilling Fine-grained Sentiment Understanding from Large Language Models 提出一种基于知识蒸馏的细粒度情感分析方法，提升小模型性能并降低推理成本。 distillation large language model ✅
18 Exploring Embedding Priors in Prompt-Tuning for Improved Interpretability and Control 探索Prompt-Tuning中的嵌入先验，提升可解释性和控制性 distillation large language model chain-of-thought
19 Multilingual Mathematical Reasoning: Advancing Open-Source LLMs in Hindi and English 提出多语言数学推理方法，提升开源LLM在印地语和英语上的数学能力。 curriculum learning large language model chain-of-thought

⬅️ 返回 cs.CL 首页 · 🏠 返回主页