cs.CL（2024-06-04）

📊 共 25 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (23 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (23 篇)

#题目一句话要点标签🔗⭐
1 Discrete Multimodal Transformers with a Pretrained Large Language Model for Mixed-Supervision Speech Processing 提出基于预训练LLM的离散多模态Transformer，用于混合监督语音处理 large language model multimodal
2 Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding 提出TCELongBench基准，利用大语言模型分析时序复杂事件，解决长文本理解难题。 large language model TAMP
3 Break the Chain: Large Language Models Can be Shortcut Reasoners 提出“打破链条”策略，提升大语言模型在复杂推理任务中的效率与泛化性 large language model chain-of-thought
4 Chain of Agents: Large Language Models Collaborating on Long-Context Tasks 提出Chain-of-Agents框架，通过多智能体协作解决长文本处理中的信息聚合与推理难题。 large language model
5 Disentangling Logic: The Role of Context in Large Language Model Reasoning Capabilities 解耦逻辑推理：探究上下文对大语言模型推理能力的影响 large language model ✅
6 Mitigate Position Bias in Large Language Models via Scaling a Single Dimension 通过缩放单维度隐藏状态，缓解大语言模型中的位置偏差问题 large language model
7 Large Language Models as Carriers of Hidden Messages 提出UTF攻击与UTFC防御，揭示并缓解大语言模型隐藏信息泄露风险 large language model
8 Large Language Models Make Sample-Efficient Recommender Systems 提出Laser框架，验证大语言模型提升推荐系统在小样本学习场景下的性能 large language model
9 Prompting Large Language Models with Human Error Markings for Self-Correcting Machine Translation 利用人工标注错误提示的大语言模型进行机器翻译自校正 large language model
10 Synergetic Event Understanding: A Collaborative Approach to Cross-Document Event Coreference Resolution with Large Language Models 提出协同事件理解方法，利用大语言模型与小语言模型解决跨文档事件共指消解问题。 large language model
11 Reinforcement Tuning for Detecting Stances and Debunking Rumors Jointly with Large Language Models 提出基于强化学习微调的大语言模型框架JSDRV，联合检测立场并证伪谣言 large language model
12 The current status of large language models in summarizing radiology report impressions 评估大型语言模型在放射报告印象总结中的能力与局限性 large language model
13 Diver: Large Language Model Decoding with Span-Level Mutual Information Verification Diver：提出基于跨度互信息验证的大语言模型解码方法，提升输出与输入的符合度。 large language model
14 TopViewRS: Vision-Language Models as Top-View Spatial Reasoners 提出TopViewRS数据集，评估视觉-语言模型在鸟瞰视角下的空间推理能力 multimodal chain-of-thought
15 mCoT: Multilingual Instruction Tuning for Reasoning Consistency in Language Models 提出mCoT，通过多语言指令微调提升语言模型在多语言推理任务中的一致性 large language model chain-of-thought
16 RATT: A Thought Structure for Coherent and Correct LLM Reasoning RATT：一种用于连贯且正确的大语言模型推理的思维结构 large language model
17 Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller SelfControl：通过梯度压缩实现大语言模型行为的无监督自控 large language model
18 SpecExec: Massively Parallel Speculative Decoding for Interactive LLM Inference on Consumer Devices SpecExec：面向消费级设备的LLM大规模并行推测解码 large language model
19 Scalable MatMul-free Language Modeling 提出无矩阵乘法的语言模型，在保持性能的同时显著降低计算和内存需求 large language model
20 CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks CheckEmbed：有效验证LLM在开放任务中的解决方案，提升准确性和可扩展性 large language model
21 Order-Independence Without Fine Tuning 提出Set-Based Prompting，解决LLM对输入顺序的依赖问题，无需微调。 large language model
22 Technical Language Processing for Telecommunications Specifications 针对电信规范，提出技术语言处理方法以提升领域LLM性能。 large language model
23 FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models FedMKT：联邦互知识迁移框架，用于协同增强大小语言模型 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🔗⭐
24 Aligning Large Language Models via Fine-grained Supervision 提出基于细粒度监督的LLM对齐方法，提升模型与用户期望的一致性。 reinforcement learning PPO RLHF
25 Textless Acoustic Model with Self-Supervised Distillation for Noise-Robust Expressive Speech-to-Speech Translation 提出基于自监督蒸馏的无文本声学模型，提升噪声环境下表现语音到语音翻译的鲁棒性。 distillation

⬅️ 返回 cs.CL 首页 · 🏠 返回主页