arXiv:2409.07055v3 Announce Type: replace-cross Abstract: Legal judgment prediction (LJP), which enables litigants and their lawyers to forecast judgment outcomes and refine litigation strategies, has emerged as a crucial legal NLP task. Existing studies typically utilize legal facts, i.e., facts that have been established by evidence and determined by the judge, to predict the judgment. However, […]
FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction
arXiv:2510.02578v3 Announce Type: replace Abstract: We present FLOWR:root, an equivariant flow-matching model for pocket-aware 3D ligand generation with joint binding affinity prediction and confidence estimation. The model supports de novo generation, pharmacophore-conditional sampling, fragment elaboration, and multi-endpoint affinity prediction (pIC50, pKi, pKd, pEC50). Training combines large-scale ligand libraries with mixed-fidelity protein-ligand complexes, followed by refinement […]
Are language models aware of the road not taken? Token-level uncertainty and hidden state dynamics
arXiv:2511.04527v1 Announce Type: cross Abstract: When a language model generates text, the selection of individual tokens might lead it down very different reasoning paths, making uncertainty difficult to quantify. In this work, we consider whether reasoning language models represent the alternate paths that they could take during generation. To test this hypothesis, we use hidden […]
MusRec: Zero-Shot Text-to-Music Editing via Rectified Flow and Diffusion Transformers
arXiv:2511.04376v1 Announce Type: cross Abstract: Music editing has emerged as an important and practical area of artificial intelligence, with applications ranging from video game and film music production to personalizing existing tracks according to user preferences. However, existing models face significant limitations, such as being restricted to editing synthesized music generated by their own models, […]
Ground-Truth Subgraphs for Better Training and Evaluation of Knowledge Graph Augmented LLMs
arXiv:2511.04473v1 Announce Type: cross Abstract: Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various solutions have been proposed, a comparison of methods is difficult due to the lack of challenging QA datasets with ground-truth targets for graph retrieval. We present SynthKGQA, a framework for generating […]
“Let’s Agree to Disagree”: Investigating the Disagreement Problem in Explainable AI for Text Summarization
arXiv:2410.18560v2 Announce Type: replace Abstract: Explainable Artificial Intelligence (XAI) methods in text summarization are essential for understanding the model behavior and fostering trust in model-generated summaries. Despite the effectiveness of XAI methods, recent studies have highlighted a key challenge in this area known as the “disagreement problem”. This problem occurs when different XAI methods yield […]
LA-MARRVEL: A Knowledge-Grounded and Language-Aware LLM Reranker for AI-MARRVEL in Rare Disease Diagnosis
arXiv:2511.02263v3 Announce Type: replace Abstract: Diagnosing rare diseases requires linking gene findings with often unstructured reference text. Current pipelines collect many candidate genes, but clinicians still spend a lot of time filtering false positives and combining evidence from papers and databases. A key challenge is language: phenotype descriptions and inheritance patterns are written in prose, […]
How Memory in Optimization Algorithms Implicitly Modifies the Loss
arXiv:2502.02132v2 Announce Type: replace-cross Abstract: In modern optimization methods used in deep learning, each update depends on the history of previous iterations, often referred to as memory, and this dependence decays fast as the iterates go further into the past. For example, gradient descent with momentum has exponentially decaying memory through exponentially averaged past gradients. […]
Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
arXiv:2505.23062v3 Announce Type: replace-cross Abstract: Incorporating pre-collected offline data from a source environment can significantly improve the sample efficiency of reinforcement learning (RL), but this benefit is often challenged by discrepancies between the transition dynamics of the source and target environments. Existing methods typically address this issue by penalizing or filtering out source transitions in […]
Memorization in Large Language Models in Medicine: Prevalence, Characteristics, and Implications
arXiv:2509.08604v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated significant potential in medicine. To date, LLMs have been widely applied to tasks such as diagnostic assistance, medical question answering, and clinical information synthesis. However, a key open question remains: to what extent do LLMs memorize medical training data. In this study, we present […]