DAFT models attention as a dynamical system to make neural networks more interpretable.
problem Uninterpretable features learned by neural networks without human priors.
method DAFT models attention as a continuous dynamical system using neural ODEs.
result DAFT reduces the number of reasoning steps while maintaining similar performance.
New benchmark for causal reasoning from human video descriptions.
problem Lack of diversity in event types and natural language descriptions, and differences from human judgments.
method Iterative event cloze task and data augmentation techniques.
result Improved data collection efficiency and diverse causal judgments.
A framework helps reinforcement learning agents understand and decompose tasks from human demonstrations.
problem Sparse-reward tasks where demonstrations are used as sources of causal knowledge.
method Develops causal models through observation and reasons from this knowledge to decompose tasks.
result A basic implementation of Reasoning from Demonstration (RfD) is effective in sparse-reward tasks.
FinHEAR combines LLMs with human expertise for better financial decision-making.
problem Challenges in financial decision-making for language models.
method Multi-agent framework with specialized LLMs for historical analysis, event interpretation, and expert retrieval.
result FinHEAR outperforms baselines in financial tasks with higher accuracy and risk-adjusted returns.
LLMs struggle with financial reasoning but can outperform the market with human oversight.
problem Financial reasoning failures in LLM-generated stock market predictions.
method Evaluated four LLMs using three prompting strategies and compared to human oversight.
result LLMs require human oversight to fully realize their potential in financial markets.
Benchmark for math reasoning models from human proofs.
problem Measuring and accelerating machine learning models in high-level mathematical reasoning.
method Built a non-synthetic dataset from theorem prover proofs, defined a task for model to fill in missing propositions, used hierarchical transformer to improve performance.
result Neural models can capture non-trivial mathematical reasoning, hierarchical transformer outperforms baseline.
The AI2 Reasoning Challenge (ARC), a new benchmark dataset for question answering (QA) has been recently released. ARC only contains natural science questions authored for human exams, which are hard to answer and require advanced logic reasoning. On the ARC Challenge Set, existing state-of-the-art QA systems fail to s…
New technique reduces language biases in large language models.
problem Gap between language and thought in large language models.
method Proposes Language-of-Thoughts (LoT) technique to adjust order and tokens.
result Significantly reduces language biases and improves reasoning tasks.
ALPODS AI diagnoses high-dimensional biomedical data with human-understandable explanations.
problem AI decisions in high-dimensional biomedical data are not explainable to humans.
method ALPODS method classifies data based on clusters and generates fuzzy reasoning rules.
result ALPODS provides understandable explanations for AI diagnoses.
TRR detects stock portfolio crashes by simulating human reasoning.
problem Detecting stock portfolio crashes with limited historical data.
method Temporal Relational Reasoning (TRR) framework.
result TRR outperforms state-of-the-art techniques in detecting stock portfolio crashes.
Robots learn conservatively from human corrections, avoiding unintended changes to their objectives.
problem Robots learn from human corrections but may not align with the intended objectives due to misspecified hypothesis spaces.
method Robots reason in real-time about the relevance of human corrections to their hypothesis space, learning more conservatively.
result Robots can avoid unintended learning from human corrections, improving alignment with intended objectives.
Few-shot visual reasoning model learns analogical relationships from small data.
problem Training deep models on few samples for visual reasoning tasks.
method Meta-analogical contrastive learning to enforce structural similarity between training and test samples.
result Method outperforms state-of-the-art on RAVEN dataset with scarce training data.
The paper offers a checklist for comparing human and machine visual perception.
problem Comparing human and machine visual perception.
method Designing, conducting, and interpreting experiments to investigate mechanisms.
result Feedback mechanisms may not be necessary for visual reasoning tasks.
Study of sentence representations in AI shows parallels to human learning.
problem Understanding how AI systems learn and generalize from training data.
method Diagnostic tests, performance analysis, training distribution effects, representation changes with augmentations.
result AI systems can learn abstract rules and generalize under certain conditions, similar to human zero-shot reasoning.
Paper addresses hypothesis space misspecification in learning from human demonstrations and corrections.
problem Hypothesis space misspecification in learning from human demonstrations and corrections.
method Reason explicitly about how well the robot can explain human inputs given its hypothesis space.
result Demonstrates method on a 7 DOF robot manipulator.
ShapleyBO explains BO's decisions, enhancing human-AI collaboration in robotics.
problem Lack of explainability in BO's black box nature, especially in human-in-the-loop applications.
method Uses game-theoretic Shapley values to quantify and interpret BO's parameter contributions.
result ShapleyBO identifies exploration and exploitation contributions, disentangling aleatoric and epistemic uncertainty.
Machine learning automates proof generation in Coq proof assistant.
problem Automating proof construction in proof assistants.
method Developed ASTactic, a deep learning model generating tactics as ASTs.
result ASTactic can generate effective tactics and prove new theorems.
Variational Proximal Policy Optimization improves reinforcement learning from human feedback.
problem Policy mode collapse and brittle exploration loops in reinforcement learning.
method Particle-based variational inference framework with Mixture-of-Experts architecture.
result Significant improvements in complex reasoning benchmarks.
Paper introduces PR2 framework for multi-agent RL, improving recursive reasoning.
problem Improving recursive reasoning in multi-agent reinforcement learning.
method Probabilistic recursive reasoning (PR2) framework using variational Bayes methods.
result PR2 framework improves multi-agent RL performance, especially in complex games.
While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these systems lack is a "relational inductive bias": a capacity for reasoning about inter-object relations…
New approach to counterfactual reasoning in AI and psychology.
problem Challenges to conventional counterfactual reasoning in AI and psychology.
method Formalizes a backtracking approach to counterfactuals within the SCM framework.
result First general account and algorithmisation of backtracking counterfactuals.
DeepRole learns to play hidden role games like Avalon.
problem Learning cooperation in uncertain multi-agent settings.
method Combines CFR and deep learning with deductive reasoning.
result DeepRole outperforms other agents and humans in Avalon.
Novel approach trains LLMs for inductive reasoning using probabilistic programs.
problem Training LLMs for inductive reasoning with sparse, ambiguous data.
method Program-based Posterior Training (PPT) using probabilistic inference.
result Significant improvement in estimation accuracy and alignment with human judgments.
Develops game theory framework for UAS integration into NAS.
problem Predicting outcomes of UAS integration into NAS.
method Game theory, reinforcement learning, level-k reasoning.
result Proposes a modeling framework for human pilot behavior.
PerSense assesses personality traits from text for commonsense reasoning.
problem Estimating human personality traits from text for mental health analysis.
method Aggregated Probability Density Functions (PDF) and Machine Learning (ML) models.
result PerSense algorithms achieve comparable results to ground truth data, with high accuracy for personality assessment and commonsense prediction.
New benchmark PVR tests neural network reasoning about indirection.
problem Understanding neural network generalization limits.
method Introducing Pointer Value Retrieval (PVR) benchmark.
result Large variations in performance across different conditions.
The paper brings order to the diverse cognitive fallacies.
problem The proliferation of cognitive fallacies in human reasoning.
method Formally establishing implication relationships (IRs) between fallacies.
result A systematic approach to categorize and understand cognitive fallacies.
Paper proposes Unification Networks to learn invariants from examples.
problem Learning to recognize common underlying principles across examples.
method End-to-end differentiable neural network approach with soft unification.
result Learning invariants improves performance on various datasets.
The paper addresses human-like decision-making in multi-agent systems using bounded risk-sensitive Markov Games.
problem Modeling human-like decision-making in multi-agent systems with risk-seeking and loss-aversion behaviors.
method Forward policy design and inverse reward learning with iterative reasoning and cumulative prospect theory.
result The proposed algorithms demonstrate both risk-averse and risk-seeking behaviors in multi-agent systems.
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
problem Inability of concept-based models to provide transparent decision processes.
method DCR uses neural networks to build syntactic rule structures using concept embeddings and executes these rules on concept truth degrees.
result DCR improves interpretability by up to 25% on challenging benchmarks and discovers meaningful logic rules.
Geometric framework detects concept frustration between human concepts and machine representations.
problem Aligning human concepts with machine learning representations.
method Geometric framework and similarity measures for detecting concept frustration.
result Concept frustration affects machine learning model performance and reorganizes learned concept representations.
Neuro-symbolic system tackles conversational AI's need for natural, broad-ranging dialogue.
problem Understanding unstated presumptions in conversational AI commands.
method Neuro-symbolic theorem prover for multi-hop reasoning.
result Extracts multi-hop reasoning chains from natural language commands.
Program synthesis struggles with complex spatial relationships in image classification.
problem Challenges in solving Synthetic Visual Reasoning Test problems.
method Quantitative reanalysis of human and machine performance, improved program synthesis classifier, categorization of SVRT problems.
result Program synthesis is constrained by spatial relationships in images, not just shape specification.
CliMB-DC combines human guidance and data-centric tools to improve ML for non-technical experts.
problem Lack of data-centric handling in LLM co-pilots for non-technical users.
method Human-guided, data-centric framework combining advanced tools and LLM reasoning.
result Significantly outperforms existing co-pilot baselines for data-centric challenges.
Study shows GPT's earnings forecasts are human-like but not always accurate.
problem Information friction in AI-generated financial analysis.
method Examined GPT's earnings forecasts following corporate earnings releases and proposed a diagnostic framework.
result GPT's narrative attention is consistent and human-like but not always associated with higher forecast accuracy.
Neural model predicts object states and physical parameters from visual observations.
problem Computational models struggle with physical reasoning and adapting to new environments.
method Visual prior predicts particle-based system from visual observations; inference module refines estimates subject to dynamics constraints.
result Model can infer physical properties within a few observations and adapt to unseen scenarios.
Hybrid framework injects TSLM insights into GRLM for robust time-series reasoning.
problem Lack of domain-specific knowledge in large language models for time-series reasoning.
method Hybrid knowledge-injection framework combining RLVR for efficient knowledge transfer.
result Consistently outperforms existing models by 7.9%-26.1% on multivariate time-series benchmarks.
MXGNet tackles visual reasoning tasks using graph neural networks.
problem Abstract reasoning, especially in the visual domain, is challenging for AI.
method Combines object-level representations, graph neural networks, and multiplex graphs.
result Achieves state-of-the-art accuracy on Euler Diagram Syllogisms and outperforms state-of-the-art models on RPM datasets.
Deep learning models generate languages that lack abstract reasoning.
problem Lack of abstract reasoning in deep learning-generated languages.
method Analyzed emergent language from two multi-agent games with compositional measures.
result Deep learning solutions often fail to generalize to out-of-training examples.
Variance-Calibrated Modulation (VCM) addresses the likelihood trap in LLMs by reshaping the probability distribution before truncation.
problem LLMs fall into the likelihood trap, leading to repetitive degeneration and vocabulary dullness.
method VCM reshapes the probability distribution before truncation through Contextual Searchlight and Adaptive Self-Debiasing.
result VCM mitigates the likelihood trap across open-ended generation, factual QA, and mathematical reasoning.
FinTradeBench benchmarks LLMs for financial reasoning combining company fundamentals and market signals.
problem Challenges in evaluating financial reasoning models for LLMs.
method Developed a benchmark integrating company fundamentals and trading signals, using a calibration-then-scaling framework.
result Clear performance gap between LLMs, retrieval improves reasoning over textual fundamentals but not trading signals.
Survey on automating geometry problem solving with large models.
problem Automating geometric problem solving with spatial understanding and logical reasoning.
method Synthesizes GPS advancements through benchmark construction, parsing, and reasoning paradigms.
result Unified analytical paradigm and emerging opportunities identified.
Transparency, user trust, and human comprehension are popular ethical motivations for interpretable machine learning. In support of these goals, researchers evaluate model explanation performance using humans and real world applications. This alone presents a challenge in many areas of artificial intelligence. In this …
Survey on discovering causal relationships from data.
problem Discover causal relationships from data.
method Modern, continuous optimization methods for structure learning.
result Survey of methods and resources for structure discovery.
The paper fine-tunes language models using human preferences for natural language tasks.
problem Applying reinforcement learning to natural language tasks with human-defined rewards.
method Fine-tuning language models using reward learning techniques, leveraging generative pretraining.
result The approach achieves good results in natural language tasks like text continuation and summarization.
Deep COACH learns complex tasks from human feedback in Minecraft.
problem Learning complex behaviors from human feedback efficiently.
method Deep reinforcement learning with policy updates based on human critiques.
result Demonstrated effectiveness in Minecraft with reduced sample complexity.
AGENTICAITA uses AI agents to autonomously trade markets without human intervention.
problem Inability of traditional trading systems to adapt to market complexity.
method Introduces an agentic AI framework with specialized LLM agents reasoning, negotiating, and acting.
result Demonstrated operational correctness and non-trivial inter-agent negotiation in live market conditions.
We consider the problem of learning object arrangements in a 3D scene. The key idea here is to learn how objects relate to human poses based on their affordances, ease of use and reachability. In contrast to modeling object-object relationships, modeling human-object relationships scales linearly in the number of objec…