ConfTuner: Training Large Language Models to Express Their Confidence Verbally

Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as science, law, and healthcare, where accurate expressions of uncertainty are essential for reliability and trust. However, current LLMs are often observed to generate incorrect answers with high confidence, a phenomenon known as "overconfidence". Recent efforts have focused on calibrating LLMs' verbalized confidence: i.e., their expressions of confidence in text form, such as "I am 80% confident that...". Existing approaches either rely on prompt engineering or fine-tuning with heuristically generated uncertainty estimates, both of which have limited effectiveness and generalizability. Motivated by the notion of proper scoring rules for calibration in classical machine learning models, we introduce ConfTuner, a simple and efficient fine-tuning method that introduces minimal overhead and does not require ground-truth confidence scores or proxy confidence estimates. ConfTuner relies on a new loss function, tokenized Brier score, which we theoretically prove to be a proper scoring rule, intuitively meaning that it "correctly incentivizes the model to report its true probability of being correct". ConfTuner improves calibration across diverse reasoning tasks and generalizes to black-box models such as GPT-4o. Our results further show that better-calibrated confidence enables downstream gains in self-correction and model cascade, advancing the development of trustworthy LLM systems. The code is available at https://github.com/liushiliushi/ConfTuner.

MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research

Recent advancements in AI agents have demonstrated their growing potential to drive and support scientific discovery. In this work, we introduce MLR-Bench, a comprehensive benchmark for evaluating AI agents on open-ended machine learning research. MLR-Bench includes three key components: (1) 201 research tasks sourced from NeurIPS, ICLR, and ICML workshops covering diverse ML topics; (2) MLR-Judge, an automated evaluation framework combining LLM-based reviewers with carefully designed review rubrics to assess research quality; and (3) MLR-Agent, a modular agent scaffold capable of completing research tasks through four stages: idea generation, proposal formulation, experimentation, and paper writing. Our framework supports both stepwise assessment across these distinct research stages, and end-to-end evaluation of the final research paper. We then use MLR-Bench to evaluate six frontier LLMs and an advanced coding agent, finding that while LLMs are effective at generating coherent ideas and well-structured papers, current coding agents frequently (e.g., in 80% of the cases) produce fabricated or invalidated experimental results--posing a major barrier to scientific reliability. We validate MLR-Judge through human evaluation, showing high agreement with expert reviewers, supporting its potential as a scalable tool for research evaluation. We open-source MLR-Bench to help the community benchmark, diagnose, and improve AI research agents toward trustworthy and transparent scientific discovery.

FineMolTex: Towards Fine-grained Molecular Graph-Text Pre-training

Understanding molecular structure and related knowledge is crucial for scientific research. Recent studies integrate molecular graphs with their textual descriptions to enhance molecular representation learning. However, they focus on the whole molecular graph and neglect frequently occurring subgraphs, known as motifs,which are essential for determining molecular properties. Without such fine-grained knowledge, these models struggle to generalize to unseen molecules and tasks that require motif-level insights. To bridge this gap, we propose FineMolTex, a novel Fine-grained Molecular graph-Text pre-training framework to jointly learn coarse-grained molecule-level knowledge and fine-grained motif-level knowledge. Specifically, FineMolTex consists of two pre-training tasks: a contrastive alignment task for coarse-grained matching and a masked multi-modal modeling task for fine-grained matching. In particular, the latter predicts the labels of masked motifs and words, leveraging insights from each other, thereby enabling FineMolTex to understand the fine-grained matching between motifs and words. Finally, we conduct extensive experiments across three downstream tasks, achieving up to 230% improvement in the text-based molecule editing task. Additionally, our case studies reveal that FineMolTex successfully captures fine-grained knowledge, potentially offering valuable insights for drug discovery and catalyst design.

Less is More: on the Over-Globalizing Problem in Graph Transformers

Graph Transformer, due to its global attention mechanism, has emerged as a new tool in dealing with graph-structured data. It is well recognized that the global attention mechanism considers a wider receptive field in a fully connected graph, leading many to believe that useful information can be extracted from all the nodes. In this paper, we challenge this belief: does the globalizing property always benefit Graph Transformers? We reveal the over-globalizing problem in Graph Transformer by presenting both empirical evidence and theoretical analysis, i.e., the current attention mechanism overly focuses on those distant nodes, while the near nodes, which actually contain most of the useful information, are relatively weakened. Then we propose a novel Bi-Level Global Graph Transformer with Collaborative Training (CoBFormer), including the inter-cluster and intra-cluster Transformers, to prevent the over-globalizing problem while keeping the ability to extract valuable information from distant nodes. Moreover, the collaborative training is proposed to improve the model's generalization ability with a theoretical guarantee. Extensive experiments on various graphs well validate the effectiveness of our proposed CoBFormer.

Graph Fairness Learning under Distribution Shifts

Graph neural networks (GNNs) have achieved remarkable performance on graph-structured data. However, GNNs may inherit prejudice from the training data and make discriminatory predictions based on sensitive attributes, such as gender and race. Recently, there has been an increasing interest in ensuring fairness on GNNs, but all of them are under the assumption that the training and testing data are under the same distribution, i.e., training data and testing data are from the same graph. Will graph fairness performance decrease under distribution shifts? How does distribution shifts affect graph fairness learning? All these open questions are largely unexplored from a theoretical perspective. To answer these questions, we first theoretically identify the factors that determine bias on a graph. Subsequently, we explore the factors influencing fairness on testing graphs, with a noteworthy factor being the representation distances of certain groups between the training and testing graph. Motivated by our theoretical analysis, we propose our framework FatraGNN. Specifically, to guarantee fairness performance on unknown testing graphs, we propose a graph generator to produce numerous graphs with significant bias and under different distributions. Then we minimize the representation distances for each certain group between the training graph and generated graphs. This empowers our model to achieve high classification and fairness performance even on generated graphs with significant bias, thereby effectively handling unknown testing graphs. Experiments on real-world and semi-synthetic datasets demonstrate the effectiveness of our model in terms of both accuracy and fairness.

A Generalized Neural Diffusion Framework on Graphs

Recent studies reveal the connection between GNNs and the diffusion process, which motivates many diffusion-based GNNs to be proposed. However, since these two mechanisms are closely related, one fundamental question naturally arises: Is there a general diffusion framework that can formally unify these GNNs? The answer to this question can not only deepen our understanding of the learning process of GNNs, but also may open a new door to design a broad new class of GNNs. In this paper, we propose a general diffusion equation framework with the fidelity term, which formally establishes the relationship between the diffusion process with more GNNs. Meanwhile, with this framework, we identify one characteristic of graph diffusion networks, i.e., the current neural diffusion process only corresponds to the first-order diffusion equation. However, by an experimental investigation, we show that the labels of high-order neighbors actually exhibit monophily property, which induces the similarity based on labels among high-order neighbors without requiring the similarity among first-order neighbors. This discovery motives to design a new high-order neighbor-aware diffusion equation, and derive a new type of graph diffusion network (HiD-Net) based on the framework. With the high-order diffusion equation, HiD-Net is more robust against attacks and works on both homophily and heterophily graphs. We not only theoretically analyze the relation between HiD-Net with high-order random walk, but also provide a theoretical convergence guarantee. Extensive experimental results well demonstrate the effectiveness of HiD-Net over state-of-the-art graph diffusion networks.

Towards Graph Foundation Models: A Survey and Beyond

Emerging as fundamental building blocks for diverse artificial intelligence applications, foundation models have achieved notable success across natural language processing and many other domains. Parallelly, graph machine learning has witnessed a transformative shift, with shallow methods giving way to deep learning approaches. The emergence and homogenization capabilities of foundation models have piqued the interest of graph machine learning researchers, sparking discussions about developing the next graph learning paradigm that is pre-trained on broad graph data and can be adapted to a wide range of downstream graph tasks. However, there is currently no clear definition and systematic analysis for this type of work. In this article, we propose the concept of graph foundation models (GFMs), and provide the first comprehensive elucidation on their key characteristics and technologies. Following that, we categorize existing works towards GFMs into three categories based on their reliance on graph neural networks and large language models. Beyond providing a comprehensive overview of the current landscape of graph foundation models, this article also discusses potential research directions for this evolving field.

Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling

Table structure recognition aims to extract the logical and physical structure of unstructured table images into a machine-readable format. The latest end-to-end image-to-text approaches simultaneously predict the two structures by two decoders, where the prediction of the physical structure (the bounding boxes of the cells) is based on the representation of the logical structure. However, the previous methods struggle with imprecise bounding boxes as the logical representation lacks local visual information. To address this issue, we propose an end-to-end sequential modeling framework for table structure recognition called VAST. It contains a novel coordinate sequence decoder triggered by the representation of the non-empty cell from the logical structure decoder. In the coordinate sequence decoder, we model the bounding box coordinates as a language sequence, where the left, top, right and bottom coordinates are decoded sequentially to leverage the inter-coordinate dependency. Furthermore, we propose an auxiliary visual-alignment loss to enforce the logical representation of the non-empty cells to contain more local visual details, which helps produce better cell bounding boxes. Extensive experiments demonstrate that our proposed method can achieve state-of-the-art results in both logical and physical structure recognition. The ablation study also validates that the proposed coordinate sequence decoder and the visual-alignment loss are the keys to the success of our method.

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios. Besides, in the research community of HGNNs, implementing and evaluating various tasks still need much human effort. To mitigate these issues, we first propose a unified framework covering most HGNNs, consisting of three components: heterogeneous linear transformation, heterogeneous graph transformation, and heterogeneous message passing layer. Then we build a platform Space4HGNN by defining a design space for HGNNs based on the unified framework, which offers modularized components, reproducible implementations, and standardized evaluation for HGNNs. Finally, we conduct experiments to analyze the effect of different designs. With the insights found, we distill a condensed design space and verify its effectiveness.

Automatic Description Construction for Math Expression via Topic Relation Graph

Math expressions are important parts of scientific and educational documents, but some of them may be challenging for junior scholars or students to understand. Nevertheless, constructing textual descriptions for math expressions is nontrivial. In this paper, we explore the feasibility to automatically construct descriptions for math expressions. But there are two challenges that need to be addressed: 1) finding relevant documents since a math equation understanding usually requires several topics, but these topics are often explained in different documents. 2) the sparsity of the collected relevant documents making it difficult to extract reasonable descriptions. Different documents mainly focus on different topics which makes model hard to extract salient information and organize them to form a description of math expressions. To address these issues, we propose a hybrid model (MathDes) which contains two important modules: Selector and Summarizer. In the Selector, a Topic Relation Graph (TRG) is proposed to obtain the relevant documents which contain the comprehensive information of math expressions. TRG is a graph built according to the citations between expressions. In the Summarizer, a summarization model under the Integer Linear Programming (ILP) framework is proposed. This module constructs the final description with the help of a timeline that is extracted from TRG. The experimental results demonstrate that our methods are promising for this task and outperform the baselines in all aspects.