跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+1680新增论文
+1333其中 AI 相关
+187已有论文修订
+59新增 AI 导读

arXiv 最近完成扫描:2026-11-18 04:28 · 全站最近入库:2026-11-17 23:35各信源进度 →

统计口径与数据新鲜度

统计 2026-11-17 05:40 — 2026-11-18 05:40(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-18 04:28最近发现新增版本:2026-11-17 23:35库内论文最新更新时间:2026-11-17 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

25,786 已收录论文21,491 AI 相关7,725 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 3 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-18 04:27(北京时间)
版本更新 · v3arXiv:2605.09159

Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas

Nils A. Herrmann, Leander Girrbach, Kirill Bykov, Zeynep Akata

原文摘要

Recent work shows that large language models (LLMs) encode behavioural traits ("personas") as linear directions in activation space, often called "persona vectors". Prior work has used such directions as static handles for behavioural steering. We instead treat them as dynamic signals: probes we can monitor and intervene on as reasoning unfolds. We use the term polylogue to denote the time series of alignments between persona vectors and hidden activations over the course of generation. Experiments across four open-weight models show that polylogue features predict correctness on MMLU-Pro on par with low-dimensional activation baselines, while remaining interpretable through their associated persona directions. They also suggest concrete steering targets, namely which latent directions to modulate at different stages of a response. We instantiate this as a simple paragraph-conditioned intervention that improves accuracy on three of four models but degrades the fourth, suggesting that stage-aware latent steering is possible but not yet robust. Together, this positions the polylogue as an interpretable tool for reasoning-time monitoring and intervention.

cs.AI

新论文 · v1arXiv:2611.12869

对齐在哪里出现,又意味着什么?对柏拉图表示假说的进一步审视

Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis

Julia Herbst, Simon Roschmann, Quentin Bouniot, Zeynep Akata

AI 速读 基于摘要

该研究考察单模态模型层间与表示维度上的对齐出现位置,检验柏拉图表示假说在新模型上的能力-对齐趋势,并用单模态与多模态基线重新解读跨模态对齐。

cs.LG

查看原文摘要

The Platonic Representation Hypothesis (PRH) suggests that neural networks are converging toward similar representation spaces. As language models become more capable, their representations are aligning with those of vision models. However, recent work has questioned whether this trend continues to hold for newer language models. Moreover, it has been shown that representation similarity metrics can be confounded by model depth and width, requiring appropriate baselines for interpretation. In this work, we first investigate where alignment emerges between unimodal models across model layers and representation dimensions. Next, we find that the PRH capability-alignment trend persists for newer models as long as the captions are sufficiently clean and informative. Finally, we contextualize cross-modal alignment, introducing unimodal and multimodal baselines on various datasets. Our results show that the cross-modal representational alignment of unimodal models can surpass that of explicitly aligned vision-language models, but remains substantially behind the alignment observed for models of the same modality. Code is available at https://github.com/ExplainableML/prh-closer-look.

新论文 · v1arXiv:2610.38547

Detecting Fine-Grained Differences between Image Datasets

Leander Girrbach, Alexander von Recum, Kirill Bykov, Zeynep Akata

原文摘要

Detecting whether and in particular how two data distributions differ is a fundamental statistical problem. For example, we might be interested in which concepts (expressed in natural language) differ between two classes, the outputs of different generative models, or the same model with different prompt specifications. When working with large and complex image datasets, we intuitively think that first selecting concepts from a broad list using fine-grained patch embeddings, and then optimizing the concepts to better fit the data is an effective workflow. However, prior work instead uses MLLMs to propose concepts and image-level embeddings to select them. Therefore, we systematically compare these techniques and find that selecting concepts from broad lists can replace MLLM-proposals at obviously lower cost. MLLM inference can then be spent on optimizing selected concepts instead to achieve substantial improvements. Additionally, by designing a new benchmark that focuses on low-prevalence and multi-concept distinctions, we find that selecting nonredundant concepts instead of only the most distinguishing concepts matters, and we introduce techniques for how to effectively do this. Finally, we show how our methods address important problems like detecting spurious correlations and biases. Overall, our work presents a fundamental perspective shift on how we analyze interpretable distributional differences between datasets.

cs.CV