This paper addresses domain adaptation in graph-structured data under chronological splits. We consider transductive semi-supervised node classification (SSNC), in which labels of historical nodes are used to predict labels of more recent nodes. Temporal dependencies in graph connectivity induce distribution shifts acr...
Joo Young Park, Sejun Park, Hyunwoo Park· 0 citations
Large language models have become increasingly popular and demonstrated remarkable performance in various natural language processing (NLP) tasks. However, these models are typically computationally expensive and difficult to be deployed in resource-constrained environments. In this paper, we propose LLMR, a novel know...
Pairwise difference learning (PDL) has recently been introduced as a new meta-learning technique for regression. Instead of learning a mapping from instances to outcomes in the standard way, the key idea is to learn a function that takes two instances as input and predicts the difference between the respective outcomes...
Mohamed Karim Belaid, Maximilian Rabus, Eyke H\"ullermeier· 0 citations
Digital note-taking is gaining popularity, offering a durable, editable, and easily indexable way of storing notes in a vectorized form, known as digital ink. However, a substantial gap remains between this way of note-taking and traditional pen-and-paper note-taking, a practice that is still favored by a vast majority...
Blagoj Mitrevski, Arina Rak, Julian Schnitzler et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Building explainable machine learning models is crucial for human users to be able to interpret the proposed statistical relationship obtained from the training data. Mixed-integer optimization formulations are often used to train such models with explicit sparsity constraints, aiming to strike the right trade-off betw...
Sanjeeb Dash, Soumyadip Ghosh, Joao Goncalves et al.· 0 citations
Legal reasoning requires identifying which version of a statute applies to a case, typically based on when the legally relevant events occurred rather than when the case is adjudicated. Yet whether large language models (LLMs) can reliably perform such temporal legal reasoning remains largely unexplored. We formalize t...
Yiqian Huang, Yang Zhou, Qianying Liu et al.· 0 citations
As AI systems proliferate in consumer facing applications, questions about liability for AI related harms remain unresolved. This working paper examines whether India's Consumer Protection Act, 2019, adequately addresses harm caused by defective AI products and services, and whether it proportionately allocates liabili...
Omir Kumar, Sriya Sridhar, Vibhav Mithal et al.· 0 citations
Alignment from human feedback uses human judgments about model outputs to steer the behavior of language models after pretraining. When those judgments reflect conflicting views of desirable behavior, the learned objective becomes an aggregate determination of what the model should prefer. We survey recent work that ha...
Daniel Halpern, Evi Micha, Ariel D. Procaccia et al.· 0 citations
Decentralized deployment of LLM agents with diverse capabilities motivates infrastructure for knowledge sharing across heterogeneous agent populations. Just as search engines index human-generated artifacts for human problem solving, retrieval systems can organize agent-generated artifacts for reuse across agents, exte...
To Eun Kim, Xuhong He, Dishank Jain et al.· 0 citations
Large language models (LLMs) are used for technical troubleshooting, where problem descriptions are often incomplete and multiple causes can explain the same symptoms. Effective diagnosis requires acquiring discriminative evidence and selecting the explanation best supported by it. Yet reasoning or interaction alone ma...
Small language models (1.5B-4B parameters) offer low-cost, low-latency tool use but often produce plausible plans that fail during execution due to unavailable tools, missing arguments, or broken dependencies. We introduce EvoFlux, an inference-time search method that repairs tool plans through an evolutionary loop ove...
Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko et al.· 0 citations
Large skill libraries are now standard equipment for LLM agents, and which subset reaches the prompt decides what the agent can do. Enumeration and top-$K$ embedding retrieval both treat skills as independent documents, assuming relevance is a property of one skill at a time. It is not: skills depend on, conflict with,...
Tong Bai, Zhenglin Wan, Pengfei Zhou et al.· 0 citations
