Improving large language models with concept-aware fine-tuning

Large language models (LLMs) have become the cornerstone of modern AI. However, the existing paradigm of next-token prediction fundamentally limits their ability to form coherent, high-level concepts, making it a critical barrier to human-like understanding and reasoning. Take the phrase "ribonucleic acid" as an example: an LLM will first decompose it into tokens, i.e., artificial text fragments ("rib", "on", ...), then learn each token sequentially, rather than grasping the phrase as a unified, coherent semantic entity. This fragmented representation hinders deeper conceptual understanding and, ultimately, the development of truly intelligent systems. In response, we introduce Concept-Aware Fine-Tuning (CAFT), a novel multi-token training method that redefines how LLMs are fine-tuned. By enabling the learning of sequences that span multiple tokens, this method fosters stronger concept-aware learning. Our experiments demonstrate significant improvements compared to conventional next-token finetuning methods across diverse tasks, including traditional applications like text summarization and domain-specific ones like de novo protein design. Multi-token prediction was previously only possible in the prohibitively expensive pretraining phase; CAFT, to our knowledge, is the first to bring the multi-token setting to the post-training phase, thus effectively democratizing its benefits for the broader community of practitioners and researchers. Finally, the unexpected effectiveness of our proposed method suggests wider implications for the machine learning research community. All code and data are available at https://github.com/michaelchen-lab/caft-llm

Towards Heterogeneous Continual Graph Learning via Meta-knowledge Distillation

Machine learning on heterogeneous graphs has experienced rapid advancement in recent years, driven by the inherently heterogeneous nature of real-world data. However, existing studies typically assume the graphs to be static, while real-world graphs are continuously expanding. This dynamic nature requires models to adapt to new data while preserving existing knowledge. To this end, this work addresses the challenge of continual learning on heterogeneous graphs by introducing the Meta-learning based Knowledge Distillation framework (MKD), designed to mitigate catastrophic forgetting in evolving heterogeneous graph structures. MKD combines rapid task adaptation through meta-learning on limited samples with knowledge distillation to achieve an optimal balance between incorporating new information and maintaining existing knowledge. To improve the efficiency and effectiveness of sample selection, MKD incorporates a novel sampling strategy that selects a small number of target-type nodes based on node diversity and maintains fixed-size buffers for other types. The strategy retrieves first-order neighbors along metapaths and selects important neighbors based on their structural relevance, enabling the sampled subgraphs to retain key topological and semantic information. In addition, MKD introduces a semantic-level distillation module that aligns the attention distributions over different metapaths between teacher and student models, encouraging semantic consistency beyond the logit level. Comprehensive evaluations across three benchmark datasets validate MKD's effectiveness in handling continual learning scenarios on expanding heterogeneous graphs.

Fairness in Graph Learning Augmented with Machine Learning: A Survey

Augmenting specialised machine learning techniques into traditional graph learning models has achieved notable success across various domains, including federated graph learning, dynamic graph learning, and graph transformers. However, the intricate mechanisms of these specialised techniques introduce significant challenges in maintaining model fairness, potentially resulting in discriminatory outcomes in high-stakes applications such as recommendation systems, disaster response, criminal justice, and loan approval. This paper systematically examines the unique fairness challenges posed by Graph Learning augmented with Machine Learning (GL-ML). It highlights the complex interplay between graph learning mechanisms and machine learning techniques, emphasising how the augmentation of machine learning both enhances and complicates fairness. Additionally, we explore four critical techniques frequently employed to improve fairness in GL-ML methods. By thoroughly investigating the root causes and broader implications of fairness challenges in this rapidly evolving field, this work establishes a robust foundation for future research and innovation in GL-ML fairness.

Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialogues

Cognitive Restructuring (CR) is a psychotherapeutic process aimed at identifying and restructuring an individual's negative thoughts, arising from mental health challenges, into more helpful and positive ones via multi-turn dialogues. Clinician shortage and stigma urge the development of human-LLM interactive psychotherapy for CR. Yet, existing efforts implement CR via simple text rewriting, fixed-pattern dialogues, or a one-shot CR workflow, failing to align with the psychotherapeutic process for effective CR. To address this gap, we propose CRDial, a novel framework for CR, which creates multi-turn dialogues with specifically designed identification and restructuring stages of negative thoughts, integrates sentence-level supportive conversation strategies, and adopts a multi-channel loop mechanism to enable iterative CR. With CRDial, we distill Crisp, a large-scale and high-quality bilingual dialogue dataset, from LLM. We then train Crispers, Crisp-based conversational LLMs for CR, at 7B and 14B scales. Extensive human studies show the superiority of Crispers in pointwise, pairwise, and intervention evaluations.

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization

Recent studies generally enhance MLLMs' reasoning capabilities via supervised fine-tuning on high-quality chain-of-thought reasoning data, which often leads models to merely imitate successful reasoning paths without understanding what the wrong reasoning paths are. In this work, we aim to enhance the MLLMs' reasoning ability beyond passively imitating positive reasoning paths. To this end, we design Step-wise Group Relative Policy Optimization (StepGRPO), a new online reinforcement learning framework that enables MLLMs to self-improve reasoning ability via simple, effective and dense step-wise rewarding. Specifically, StepGRPO introduces two novel rule-based reasoning rewards: Step-wise Reasoning Accuracy Reward (StepRAR) and Step-wise Reasoning Validity Reward (StepRVR). StepRAR rewards the reasoning paths that contain necessary intermediate reasoning steps via a soft key-step matching technique, while StepRAR rewards reasoning paths that follow a well-structured and logically consistent reasoning process through a reasoning completeness and logic evaluation strategy. With the proposed StepGRPO, we introduce R1-VL, a series of MLLMs with outstanding capabilities in step-by-step reasoning. Extensive experiments over 8 benchmarks demonstrate the superiority of our methods.

Benchmarking Reasoning Robustness in Large Language Models

Despite the recent success of large language models (LLMs) in reasoning such as DeepSeek, we for the first time identify a key dilemma in reasoning robustness and generalization: significant performance degradation on novel or incomplete data, suggesting a reliance on memorized patterns rather than systematic reasoning. Our closer examination reveals four key unique limitations underlying this issue:(1) Positional bias--models favor earlier queries in multi-query inputs but answering the wrong one in the latter (e.g., GPT-4o's accuracy drops from 75.8 percent to 72.8 percent); (2) Instruction sensitivity--performance declines by 5.0 to 7.5 percent in the Qwen2.5 Series and by 5.0 percent in DeepSeek-V3 with auxiliary guidance; (3) Numerical fragility--value substitution sharply reduces accuracy (e.g., GPT-4o drops from 97.5 percent to 82.5 percent, GPT-o1-mini drops from 97.5 percent to 92.5 percent); and (4) Memory dependence--models resort to guesswork when missing critical data. These findings further highlight the reliance on heuristic recall over rigorous logical inference, demonstrating challenges in reasoning robustness. To comprehensively investigate these robustness challenges, this paper introduces a novel benchmark, termed as Math-RoB, that exploits hallucinations triggered by missing information to expose reasoning gaps. This is achieved by an instruction-based approach to generate diverse datasets that closely resemble training distributions, facilitating a holistic robustness assessment and advancing the development of more robust reasoning frameworks. Bad character(s) in field Abstract.

JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models

Logical reasoning is a critical component of Large Language Models (LLMs), and substantial research efforts in recent years have aimed to enhance their deductive reasoning capabilities. However, existing deductive reasoning benchmarks, which are crucial for evaluating and advancing LLMs, are inadequate due to their lack of task complexity, presence of prior knowledge as a confounder, and superficial error analysis. To address these deficiencies, we introduce JustLogic, a synthetically generated deductive reasoning benchmark designed for rigorous evaluation of LLMs. JustLogic is (i) highly complex, capable of generating a diverse range of linguistic patterns, vocabulary, and argument structures; (ii) prior knowledge independent, eliminating the advantage of models possessing prior knowledge and ensuring that only deductive reasoning is used to answer questions; and (iii) capable of in-depth error analysis on the heterogeneous effects of reasoning depth and argument form on model accuracy. Our experimental results on JustLogic reveal that most state-of-the-art (SOTA) LLMs perform significantly worse than the human average, demonstrating substantial room for model improvement. All code and data are available at https://github.com/michaelchen-lab/JustLogic

How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunities

The cell is arguably the smallest unit of life and is central to understanding biology. Accurate modeling of cells is important for this understanding as well as for determining the root causes of disease. Recent advances in artificial intelligence (AI), combined with the ability to generate large-scale experimental data, present novel opportunities to model cells. Here we propose a vision of AI-powered Virtual Cells, where robust representations of cells and cellular systems under different conditions are directly learned from growing biological data across measurements and scales. We discuss desired capabilities of AI Virtual Cells, including generating universal representations of biological entities across scales, and facilitating interpretable in silico experiments to predict and understand their behavior using Virtual Instruments. We further address the challenges, opportunities and requirements to realize this vision including data needs, evaluation strategies, and community standards and engagement to ensure biological accuracy and broad utility. We envision a future where AI Virtual Cells help identify new drug targets, predict cellular responses to perturbations, as well as scale hypothesis exploration. With open science collaborations across the biomedical ecosystem that includes academia, philanthropy, and the biopharma and AI industries, a comprehensive predictive understanding of cell mechanisms and interactions is within reach.

Learning System Dynamics without Forgetting

Predicting the trajectories of systems with unknown dynamics (\textit{i.e.} the governing rules) is crucial in various research fields, including physics and biology. This challenge has gathered significant attention from diverse communities. Most existing works focus on learning fixed system dynamics within one single system. However, real-world applications often involve multiple systems with different types of dynamics or evolving systems with non-stationary dynamics (dynamics shifts). When data from those systems are continuously collected and sequentially fed to machine learning models for training, these models tend to be biased toward the most recently learned dynamics, leading to catastrophic forgetting of previously observed/learned system dynamics. To this end, we aim to learn system dynamics via continual learning. Specifically, we present a novel framework of Mode-switching Graph ODE (MS-GODE), which can continually learn varying dynamics and encode the system-specific dynamics into binary masks over the model parameters. During the inference stage, the model can select the most confident mask based on the observational data to identify the system and predict future trajectories accordingly. Empirically, we systematically investigate the task configurations and compare the proposed MS-GODE with state-of-the-art techniques. More importantly, we construct a novel benchmark of biological dynamic systems, featuring diverse systems with disparate dynamics and significantly enriching the research field of machine learning for dynamic systems.

Continual Learning on Graphs: Challenges, Solutions, and Opportunities

Continual learning on graph data has recently attracted paramount attention for its aim to resolve the catastrophic forgetting problem on existing tasks while adapting the sequentially updated model to newly emerged graph tasks. While there have been efforts to summarize progress on continual learning research over Euclidean data, e.g., images and texts, a systematic review of progress in continual learning on graphs, a.k.a, continual graph learning (CGL) or lifelong graph learning, is still demanding. Graph data are far more complex in terms of data structures and application scenarios, making CGL task settings, model designs, and applications extremely challenging. To bridge the gap, we provide a comprehensive review of existing continual graph learning (CGL) algorithms by elucidating the different task settings and categorizing the existing methods based on their characteristics. We compare the CGL methods with traditional continual learning techniques and analyze the applicability of the traditional continual learning techniques to CGL tasks. Additionally, we review the benchmark works that are crucial to CGL research. Finally, we discuss the remaining challenges and propose several future directions. We will maintain an up-to-date GitHub repository featuring a comprehensive list of CGL algorithms, accessible at https://github.com/UConn-DSIS/Survey-of-Continual-Learning-on-Graphs.