PulseAugur
中
实时 16:58:13

新研究探讨大语言模型推理、概念发现和知识处理

近期研究探索了大语言模型(LLMs)的内部工作机制和推理能力。研究正在调查LLMs如何处理超越线性假设的信息,检查内部概率与口头表达概率之间的耦合,并开发解释推理轨迹的框架。此外,研究人员正在评估LLMs处理多值关系的能力、它们对外部指导的选择性依赖以及它们对所有权概念的理解。 AI

影响 这些研究为LLM的可解释性、推理和知识处理提供了更深入的见解,可能指导未来的模型开发和应用。

排序理由 该集群包含多篇在arXiv上发表的学术论文。

在 Hugging Face Daily Papers 阅读 →

AI 生成摘要 · Google Gemini · 来自 20 个来源。 我们如何撰写摘要 →

新研究探讨大语言模型推理、概念发现和知识处理

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
该集群包含多篇在arXiv上发表的学术论文。
Source corroboration
20 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
50 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+4 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [20]

  1. arXiv cs.CL TIER_1 English(EN) · Shivam Shukla, Jihye Kim, Shubham Gaur, Mahnaz Roshanaei, Magy Seif El-Nasr ·

    RELATE:一个用于衡量大型语言模型关系导向的评估框架

    arXiv:2610.09569v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for emotional support, raising concern that sustained use may draw users away from their real-world relationships. Yet existing evaluations primarily focus on the safety, empathy, o…

  2. arXiv cs.AI TIER_1 English(EN) · Everett Rush, David J. Icove, Ari Kim, Byung H. Park, Michael A. Langston ·

    利用大型语言模型克服解释结构建模的挑战

    arXiv:2610.02254v1 Announce Type: cross Abstract: Interpretive Structural Modeling (ISM) is a well-known process for multi-criteria decision making. The success of ISM over other methodologies is its ability to model causal relationships, the binary scale of factors, and resultin…

  3. arXiv cs.CL TIER_1 English(EN) · Lihu Chen ·

    大型语言模型中知识可及性的几何学

    arXiv:2610.03052v1 Announce Type: new Abstract: Large language models (LLMs) contain broad knowledge, but they cannot access all of it reliably. We study this problem through knowledge accessibility, which describes whether the knowledge needed for a query can be recalled from th…

  4. arXiv cs.LG TIER_1 English(EN) · Tido Specht, Elias Benedict Krey, Nils Neukirch, Nils Strodthoff ·

    超越线性概念:大型语言模型中非线性概念流形的发现与对齐

    arXiv:2610.01821v1 Announce Type: new Abstract: Understanding information processing in large language models (LLMs) requires dissecting the geometric organization of their internal token representations. While existing mechanistic interpretability (MI) methods seek to extract co…

  5. arXiv cs.AI TIER_1 English(EN) · Sinead Williamson, Jiaxuan Li, Nick Foti, Russ Webb, Masha Fedzechkina ·

    大型语言模型中的口头和内部概率是耦合的

    arXiv:2610.00827v1 Announce Type: cross Abstract: Large language models carry an internal notion of uncertainty in their sampling distribution, i.e., the probabilities they place on generating one answer rather than another. They can also be asked to state a confidence, in words …

  6. arXiv cs.AI TIER_1 English(EN) · Barproda Halder, Qiuyi Zhang, Sanghamitra Dutta ·

    通过部分信息分解解读大语言模型的推理

    arXiv:2610.00571v1 Announce Type: cross Abstract: Large reasoning models (LRMs) have achieved substantial improvements in solving complex mathematical problems, but often produce lengthy, repetitive, or erroneous reasoning trajectories. In this work, we introduce a new interpreta…

  7. arXiv cs.AI TIER_1 English(EN) · Xizhi Xiao, Yue Wu, Shan Xu, Jia Liu ·

    谁拥有它?评估大型语言模型中的所有权直觉

    arXiv:2609.39483v1 Announce Type: new Abstract: Ownership establishes rights over the use, control, and transfer of objects. Understanding these relations is essential for AI systems to interact appropriately with people and their resources. Yet how large language models (LLMs) a…

  8. arXiv cs.CL TIER_1 English(EN) · Lukas Thede, Yash Kumar Atri, David Chen, Danielle Bitterman, Matthias Bethge, Tom Hartvigsen, Zeynep Akata ·

    MedKIT:评估大型语言模型中的知识整合与泛化能力

    arXiv:2609.38543v1 Announce Type: new Abstract: Constantly evolving real-world knowledge necessitates models to be updated continuously. Especially in medicine, as clinical evidence changes over time, outdated knowledge can pose safety risks. Existing evaluations of knowledge int…

  9. arXiv cs.CL TIER_1 English(EN) · Siyu Song, Rui Xu, Jia Lin, Kai Liu, Weifang Wang ·

    CORE:面向可验证语言模型搜索的冲突导向推理消除

    arXiv:2609.39069v1 Announce Type: new Abstract: Test-time reasoning systems often respond to failure by restarting or revising the latest step, even when an earlier decision caused the error. We introduce CORE, a search controller that requests a certified conflict core from a ve…

  10. arXiv cs.CL TIER_1 English(EN) · Minghan Wang, Boyuan Wang, Jinhang Zuo, Yuxin Tao, Fang kong ·

    跳出思维定势:语言模型能否选择性地依赖外部指导?

    arXiv:2609.39578v1 Announce Type: new Abstract: Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly constrain their execution. We call the ability to benefit from useful guidance while …

  11. arXiv cs.AI TIER_1 English(EN) · Nishchal Prasad, Eric Gaussier, Emilie Devijver, Alexander Obeid Guzman, Armen Aghasaryan, Gregor G\"ossler ·

    使用语言模型推断事件序列间的因果关系

    arXiv:2609.39406v1 Announce Type: new Abstract: Causal AI is a branch of Artificial Intelligence which helps understand and reason about cause and effect relationships, not just patterns or correlations. Causal discovery aims to infer elements of the underlying causal structure--…

  12. arXiv cs.CL TIER_1 English(EN) · Timo Pierre Schrader, Annemarie Friedrich, Simon Razniewski, Lukas Lange ·

    规范顺序问题:当大型语言模型成为多值关系不可靠的知识库

    arXiv:2609.36209v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as knowledge bases (KBs) due to the vast amount of knowledge they acquire during pre-training. While many works focus on extracting single relational triples, most real-world relati…

  13. arXiv cs.AI TIER_1 English(EN) · Huaman Sun, Dingcheng Wang, Jason Hartline, Jessica Hullman ·

    大型语言模型中概率推理的诊断与改进

    arXiv:2609.38005v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. We propose a decision-theoretic framework that decomposes LLMs' d…

  14. arXiv cs.LG TIER_1 English(EN) · Yundaichuan Zhan, Weishi Wang, Wenbiao Liu, Daniel Dahlmeier, Chengwei Qin, Juncheng Li, Fredrik D. Johansson, Zhongqi Yue ·

    Dyad:为大型语言模型扩展原生类型化决策能力

    arXiv:2609.36116v1 Announce Type: new Abstract: We study how to build more capable general-purpose agents by extending large language models (LLMs) with native typed decision-making. We introduce Dyad, an architecture that augments a pretrained LLM with an environment-conditioned…

  15. Hugging Face Daily Papers TIER_1 English(EN) ·

    跳出思维定势:语言模型能否选择性地依赖外部指导?

    Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly constrain their execution. We call the ability to benefit from useful guidance while overriding unreliable guidance thinking outside …

  16. Hugging Face Daily Papers TIER_1 English(EN) ·

    大型语言模型中概率推理的诊断与改进

    Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. We propose a decision-theoretic framework that decomposes LLMs' decision loss into two components: forming accura…

  17. Hugging Face Daily Papers TIER_1 (CA) ·

    上下文语言模型

    We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted updates to this file. This allows the model to learn what is most important to main…

  18. arXiv cs.AI TIER_1 English(EN) · Xiangwei Wang, Wei Wang, Ken Chen, Nanduni Nimalsiri, Sachith Seneviratne, Saman Halgamuge ·

    大型语言模型推理中的分步内在奖励

    arXiv:2602.01034v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a widely used paradigm for improving the reasoning abilities of large language models (LLMs) and Vision-language models (VLMs). Sparse binary outcome rewards, however, score only final corr…

  19. Hugging Face Daily Papers TIER_1 English(EN) ·

    SeLMRoute:用于大型语言模型路由的概率语义证据

    Large language model (LLM) routing aims to select the most suitable model for each incoming query. Most existing routers learn this decision directly from query embeddings, model representations, preference data, or clusters of similar examples. Such approaches can be effective, …

  20. arXiv cs.CV TIER_1 English(EN) · Jinchang Zhang, Guoyu Lu ·

    能看、能说,但不能用:从可报告的空间事实到多模态大语言模型中的可用状态

    arXiv:2610.02876v1 Announce Type: new Abstract: A multimodal large language model that correctly reports a spatial fact does not necessarily use that fact in subsequent reasoning. To study this distinction, we introduce \textsc{SpaceConflict}, a benchmark of 23{,}196 inputs for t…