cs.CL（2024-11-19）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
1 StreetviewLLM: Extracting Geographic Information Using a Chain-of-Thought Multimodal Large Language Model 提出StreetViewLLM，利用多模态大语言模型提取地理信息，提升城市环境分析精度。 large language model multimodal chain-of-thought
2 CUE-M: Contextual Understanding and Enhanced Search with Multimodal Large Language Model 提出CUE-M以解决多模态检索中的用户意图理解问题 large language model multimodal
3 Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models 通过预训练中的程序性知识驱动大型语言模型的推理能力 large language model
4 RedPajama: an Open Dataset for Training Large Language Models RedPajama：发布大规模开放数据集，促进透明、高性能大语言模型的发展 large language model
5 Exploring Iterative Controllable Summarization with Large Language Models 提出GTE框架，通过迭代自解释提升大语言模型在可控摘要生成中的性能 large language model
6 Evaluating the Prompt Steerability of Large Language Models 提出Prompt Steerability基准，评估大语言模型在提示下的角色可控性 large language model ✅
7 Evaluating Tokenizer Performance of Large Language Models Across Official Indian Languages 评估大型语言模型在印度官方语言上的分词器性能 large language model
8 Probing the Capacity of Language Model Agents to Operationalize Disparate Experiential Context Despite Distraction OEDD：评估语言模型Agent在干扰下整合复杂经验信息的能力 large language model chain-of-thought ✅
9 Signformer is all you need: Towards Edge AI for Sign Language Signformer：面向边缘AI的轻量级手语翻译Transformer large language model
10 Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI Combat 探索LLM头对头对比排序方法，提升模型选择的准确性和效率 large language model
11 Balancing Accuracy and Efficiency in Multi-Turn Intent Classification for LLM-Powered Dialog Systems in Production 针对LLM驱动的对话系统，提出Symbol Tuning和C-LARA以平衡准确率和效率。 large language model
12 Information Theory of Meaningful Communication 利用大型语言模型量化有意义叙事中的信息，以每子句的意义比特为单位。 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
13 GRL-Prompt: Towards Knowledge Graph based Prompt Optimization via Reinforcement Learning 提出GRL-Prompt，利用强化学习和知识图谱优化大语言模型提示词。 reinforcement learning reward shaping large language model
14 ACING: Actor-Critic for Instruction Learning in Black-Box LLMs ACING：用于黑盒LLM指令学习的Actor-Critic方法 reinforcement learning large language model chain-of-thought ✅
15 HNCSE: Advancing Sentence Embeddings via Hybrid Contrastive Learning with Hard Negatives HNCSE：通过混合对比学习与难负样本提升句子嵌入 representation learning contrastive learning
16 ProSec: Fortifying Code LLMs with Proactive Security Alignment ProSec：通过主动安全对齐增强代码大语言模型的安全性 preference learning large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
17 JuniperLiu at CoMeDi Shared Task: Models as Annotators in Lexical Semantics Disagreements 提出基于模型集成和异方性消除的词汇语义分歧预测方法 manipulation ✅

⬅️ 返回 cs.CL 首页 · 🏠 返回主页