相关论文: Arjun: An Efficient Independent Support Computatio…

Sampling-based search, a simple paradigm for utilizing test-time compute, involves generating multiple candidate responses and selecting the best one -- typically by having models self-verify each response for correctness. In this paper, we…

Automated decision support systems promise to help human experts solve multiclass classification tasks more efficiently and accurately. However, existing systems typically require experts to understand when to cede agency to the system or…

We present an extension-based approach for computing and verifying preferences in an abstract argumentation system. Although numerous argumentation semantics have been developed previously for identifying acceptable sets of arguments from…

Independent component analysis provides a principled framework for unsupervised representation learning, with solid theory on the identifiability of the latent code that generated the data, given only observations of mixtures thereof.…

Boolean formulae compactly encode huge, constrained search spaces. Thus, variability-intensive systems are often encoded with Boolean formulae. The search space of a variability-intensive system is usually too large to explore without…

Independent Component Analysis (ICA) is a classical method for recovering latent variables with useful identifiability properties. For independent variables, cumulant tensors are diagonal; relaxing independence yields tensors whose zero…

Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard questions remain under-explored. We propose Uncertainty-Aware Budget Allocation (UAB),…

We consider the problem of collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific distributions. In particular, we…

In this paper, we propose an incremental abstraction method for dynamically over-approximating nonlinear systems in a bounded domain by solving a sequence of linear programs, resulting in a sequence of affine upper and lower hyperplanes…

We present and evaluate a technique for computing path-sensitive interference conditions during abstract interpretation of concurrent programs. In lieu of fixed point computation, we use prime event structures to compactly represent causal…

Approximations during program analysis are a necessary evil, as they ensure essential properties, such as soundness and termination of the analysis, but they also imply not always producing useful results. Automatic techniques have been…

Most work in algorithmic fairness to date has focused on discrete outcomes, such as deciding whether to grant someone a loan or not. In these classification settings, group fairness criteria such as independence, separation and sufficiency…

The Abstraction and Reasoning Corpus remains one of the most compelling and challenging benchmarks for tracking progress toward achieving Artificial General Intelligence. In contrast to other evaluation datasets designed to assess an…

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for enhancing LLMs in scenarios that demand extensive factual knowledge. However, current RAG evaluations concentrate primarily on correctness, which may not…

Prior work has commonly defined argument retrieval from heterogeneous document collections as a sentence-level classification task. Consequently, argument retrieval suffers both from low recall and from sentence segmentation errors making…

Inspired by the concept of active learning, we propose active inference$\unicode{x2013}$a methodology for statistical inference with machine-learning-assisted data collection. Assuming a budget on the number of labels that can be collected,…

To assist humans in efficiently validating RAG-generated content, developing a fine-grained attribution mechanism that provides supporting evidence from retrieved documents for every answer span is essential. Existing fine-grained…

This paper develops a unified identification framework for counterfactual analysis in incomplete models characterized by support and moment restrictions. I demonstrate that identifying structural parameters and conducting counterfactual…

Project-specific code completion is a critical task that leverages context from a project to generate accurate code. State-of-the-art methods use retrieval-augmented generation (RAG) with large language models (LLMs) and project information…

Recent advances in probabilistic modelling have led to a large number of simulation-based inference algorithms which do not require numerical evaluation of likelihoods. However, a public benchmark with appropriate performance metrics for…