Conceptual reasoning, the ability to reason in abstract and high-level perspectives, is key to generalization in human cognition. However, limited study has been done on large language models' capability to perform conceptual reasoning. In this work, we bridge this gap and propose a novel conceptualization framework that forces models to perform conceptual reasoning on abstract questions and generate solutions in a verifiable symbolic space. Using this framework as an analytical tool, we show that existing large language models fall short on conceptual reasoning, dropping 9% to 28% on various benchmarks compared to direct inference methods. We then discuss how models can improve since high-level abstract reasoning is key to unbiased and generalizable decision-making. We propose two techniques to add trustworthy induction signals by generating familiar questions with similar underlying reasoning paths and asking models to perform self-refinement. Experiments show that our proposed techniques improve models' conceptual reasoning performance by 8% to 11%, achieving a more robust reasoning system that relies less on inductive biases.

Humans excel at applying learned behavior to unlearned situations. A crucial component of this generalization behavior is our ability to compose/decompose a whole into reusable parts, an attribute known as compositionality. One of the fundamental questions in robotics concerns this characteristic. "How can linguistic compositionality be developed concomitantly with sensorimotor skills through associative learning, particularly when individuals only learn partial linguistic compositions and their corresponding sensorimotor patterns?" To address this question, we propose a brain-inspired neural network model that integrates vision, proprioception, and language into a framework of predictive coding and active inference, based on the free-energy principle. The effectiveness and capabilities of this model were assessed through various simulation experiments conducted with a robot arm. Our results show that generalization in learning to unlearned verb-noun compositions, is significantly enhanced when training variations of task composition are increased. We attribute this to self-organized compositional structures in linguistic latent state space being influenced significantly by sensorimotor learning. Ablation studies show that visual attention and working memory are essential to accurately generate visuo-motor sequences to achieve linguistically represented goals. These insights advance our understanding of mechanisms underlying development of compositionality through interactions of linguistic and sensorimotor experience.

Many public policies and medical interventions involve dynamics in their treatment assignments, where treatments are sequentially assigned to the same individuals across multiple stages, and the effect of treatment at each stage is usually heterogeneous with respect to the history of prior treatments and associated characteristics. We study statistical learning of optimal dynamic treatment regimes (DTRs) that guide the optimal treatment assignment for each individual at each stage based on the individual's history. We propose a step-wise doubly-robust approach to learn the optimal DTR using observational data under the assumption of sequential ignorability. The approach solves the sequential treatment assignment problem through backward induction, where, at each step, we combine estimators of propensity scores and action-value functions (Q-functions) to construct augmented inverse probability weighting estimators of values of policies for each stage. The approach consistently estimates the optimal DTR if either a propensity score or Q-function for each stage is consistently estimated. Furthermore, the resulting DTR can achieve the optimal convergence rate $n^{-1/2}$ of regret under mild conditions on the convergence rate for estimators of the nuisance parameters.

This paper deals with optimal policy learning (OPL) with observational data, i.e. data-driven optimal decision-making, in multi-action (or multi-arm) settings, where a finite set of decision options is available. It is organized in three parts, where I discuss respectively: estimation, risk preference, and potential failures. The first part provides a brief review of the key approaches to estimating the reward (or value) function and optimal policy within this context of analysis. Here, I delineate the identification assumptions and statistical properties related to offline optimal policy learning estimators. In the second part, I delve into the analysis of decision risk. This analysis reveals that the optimal choice can be influenced by the decision maker's attitude towards risks, specifically in terms of the trade-off between reward conditional mean and conditional variance. Here, I present an application of the proposed model to real data, illustrating that the average regret of a policy with multi-valued treatment is contingent on the decision-maker's attitude towards risk. The third part of the paper discusses the limitations of optimal data-driven decision-making by highlighting conditions under which decision-making can falter. This aspect is linked to the failure of the two fundamental assumptions essential for identifying the optimal choice: (i) overlapping, and (ii) unconfoundedness. Some conclusions end the paper.

In this paper, we introduce a new functional point of view on bilevel optimization problems for machine learning, where the inner objective is minimized over a function space. These types of problems are most often solved by using methods developed in the parametric setting, where the inner objective is strongly convex with respect to the parameters of the prediction function. The functional point of view does not rely on this assumption and notably allows using over-parameterized neural networks as the inner prediction function. We propose scalable and efficient algorithms for the functional bilevel optimization problem and illustrate the benefits of our approach on instrumental regression and reinforcement learning tasks, which admit natural functional bilevel structures.

This story about intelligence testing in schools was produced by the Hechinger Report, a nonprofit, independent news organization focused on inequality and innovation in education. Even before her son started kindergarten, Ashley Meier Barlow realized that she might have to fight for his education. Her son has Down syndrome; when he was in prekindergarten, school officials in Fort Thomas, Kentucky, told Barlow that he wouldn't be going to the neighborhood school, with some special education accommodations, as she had assumed. Instead, the educators told Barlow that they wanted her son to attend a classroom across town meant for children who are profoundly impacted by their disabilities. Barlow immediately resisted because she knew the curriculum would likely focus on life skills, and her son might never be taught much reading beyond learning the shape of common, functional words like stop and exit.

As the range of applications for Large Language Models (LLMs) continues to grow, the demand for effective serving solutions becomes increasingly critical. Despite the versatility of LLMs, no single model can optimally address all tasks and applications, particularly when balancing performance with cost. This limitation has led to the development of LLM routing systems, which combine the strengths of various models to overcome the constraints of individual LLMs. Yet, the absence of a standardized benchmark for evaluating the performance of LLM routers hinders progress in this area. To bridge this gap, we present RouterBench, a novel evaluation framework designed to systematically assess the efficacy of LLM routing systems, along with a comprehensive dataset comprising over 405k inference outcomes from representative LLMs to support the development of routing strategies. We further propose a theoretical framework for LLM routing, and deliver a comparative analysis of various routing approaches through RouterBench, highlighting their potentials and limitations within our evaluation framework. This work not only formalizes and advances the development of LLM routing systems but also sets a standard for their assessment, paving the way for more accessible and economically viable LLM deployments. The code and data are available at https://github.com/withmartian/routerbench.

Knowledge distillation from LLMs is essential for the efficient deployment of language models. Prior works have proposed data generation using LLMs for preparing distilled models. We argue that generating data with LLMs is prone to sampling mainly from the center of original content distribution. This limitation hinders the distilled model from learning the true underlying data distribution and to forget the tails of the distributions (samples with lower probability). To this end, we propose GOLD, a task-agnostic data generation and knowledge distillation framework, which employs an iterative out-of-distribution-guided feedback mechanism for the LLM. As a result, the generated data improves the generalizability of distilled models. An energy-based OOD evaluation approach is also introduced to deal with noisy generated data. Our extensive experiments on 10 different classification and sequence-to-sequence tasks in NLP show that GOLD respectively outperforms prior arts and the LLM with an average improvement of 5% and 14%. We will also show that the proposed method is applicable to less explored and novel tasks. The code is available.

This study investigates the efficacy of six major Generative AI (GenAI) text detectors when confronted with machine-generated content that has been modified using techniques designed to evade detection by these tools (n=805). The results demonstrate that the detectors' already low accuracy rates (39.5%) show major reductions in accuracy (17.4%) when faced with manipulated content, with some techniques proving more effective than others in evading detection. The accuracy limitations and the potential for false accusations demonstrate that these tools cannot currently be recommended for determining whether violations of academic integrity have occurred, underscoring the challenges educators face in maintaining inclusive and fair assessment practices. However, they may have a role in supporting student learning and maintaining academic integrity when used in a non-punitive manner. These results underscore the need for a combined approach to addressing the challenges posed by GenAI in academia to promote the responsible and equitable use of these emerging technologies. The study concludes that the current limitations of AI text detectors require a critical approach for any possible implementation in HE and highlight possible alternatives to AI assessment strategies.

Sampling critical testing scenarios is an essential step in intelligence testing for Automated Vehicles (AVs). However, due to the lack of prior knowledge on the distribution of critical scenarios in sampling space, we can hardly efficiently find the critical scenarios or accurately evaluate the intelligence of AVs. To solve this problem, we formulate the testing as a continuous optimization process which iteratively generates potential critical scenarios and meanwhile evaluates these scenarios. A bi-level loop is proposed for such life-long learning and testing. In the outer loop, we iteratively learn space knowledge by evaluating AV in the already sampled scenarios and then sample new scenarios based on the retained knowledge. Outer loop stops when all generated samples cover the whole space. While to maximize the coverage of the space in each outer loop, we set an inner loop which receives newly generated samples in outer loop and outputs the updated positions of these samples. We assume that points in a small sphere-like subspace can be covered (or represented) by the point in the center of this sphere. Therefore, we can apply a multi-rounds heuristic strategy to move and pack these spheres in space to find the best covering solution. The simulation results show that faster and more accurate evaluation of AVs can be achieved with more critical scenarios.