ReOPD uses pre-collected teacher trajectories to distill knowledge from multi-turn interactions.
problem The cost of fully online on-policy distillation for multi-turn interactions.
method ReOPD, an off-environment alternative that reuses pre-collected teacher trajectories as replayed prefixes, addressing the prefix trap and distribution shift.
result ReOPD preserves or improves OPD-level accuracy, uses zero tool calls, and is at least 4imes faster per training step. In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to multi-turn dialogue by modifying the state-of-the-art hredGAN architecture. To achieve this, we introduce an additional input modality into the encoder and decoder of hredGAN to capture other attributes such a…
Efficient algorithm for learning from indirect feedback in complex decision-making scenarios.
problem Learning from indirect feedback in realistic scenarios with personalized mechanisms.
method IGW algorithm for policy optimization, extending reward-estimator construction from single-step to multi-step.
result Achieves sublinear regret guarantee for contextual episodic MDPs with personalized feedback.
Enhances math problem-solving models with multi-turn preference learning.
problem Improving mathematical problem-solving capabilities of large language models.
method Introduces a multi-turn direct preference learning framework for tool-integrated mathematical reasoning tasks.
result Significant performance improvements in model accuracy on math datasets.
Most existing text-to-image synthesis tasks are static single-turn generation, based on pre-defined textual descriptions of images. To explore more practical and interactive real-life applications, we introduce a new task - Interactive Image Editing, where users can guide an agent to edit images via multi-turn textual …
This study compares hierarchical and non-hierarchical models for open-domain multi-turn dialog generation.
problem Which kind of models (hierarchical or non-hierarchical) is better for open-domain multi-turn dialog generation?
method Systematically compared nearly all representative hierarchical and non-hierarchical models over the same experimental settings.
result Nearly all hierarchical models are worse than non-hierarchical models in open-domain multi-turn dialog generation, except for HRAN.
Unified pipeline detects multi-turn deception using geometric signals.
problem Detecting multi-turn deceptive interactions in LLMs.
method Geometric signaturization via genetic prompt optimization.
result Compact geometric model achieves high recall and F1 scores.
Foundation models struggle with multi-turn exploration but can learn through regular summaries.
problem Foundation models struggle with multi-turn exploration in dynamic environments.
method Implemented a text-based version of the Alchemy environment to test multi-trial learning. Prompting models to summarize their observations at regular intervals enabled them to improve across trials and adapt to changes.
result Foundation models can improve through regular summaries, enabling multi-trial learning and adaptation.
In this paper, we extend the persona-based sequence-to-sequence (Seq2Seq) neural network conversation model to a multi-turn dialogue scenario by modifying the state-of-the-art hredGAN architecture to simultaneously capture utterance attributes such as speaker identity, dialogue topic, speaker sentiments and so on. The …
Meena is a chatbot trained on social media data, achieving human-like conversation quality.
problem Creating a chatbot that can have human-like conversations in an open-domain setting.
method End-to-end training of a 2.6B parameter neural network on social media data, using perplexity and a human evaluation metric (SSA) to assess quality.
result Meena achieves a high human-like conversation quality (79% SSA) when compared to existing chatbots.
We propose an adversarial learning approach for generating multi-turn dialogue responses. Our proposed framework, hredGAN, is based on conditional generative adversarial networks (GANs). The GAN's generator is a modified hierarchical recurrent encoder-decoder network (HRED) and the discriminator is a word-level bidirec…
BED-LLM uses Bayesian experimental design to improve LLMs' information gathering.
problem Improving LLMs' ability to gather information adaptively.
method Iteratively choosing questions to maximize expected information gain using a probabilistic model.
result BED-LLM achieves substantial performance gains compared to other adaptive design strategies.
Neural dialogue models, despite their successes, still suffer from lack of relevance, diversity, and in many cases coherence in their generated responses. These issues can attributed to reasons including (1) short-range model architectures that capture limited temporal dependencies, (2) limitations of the maximum likel…
Prior work in visual dialog has focused on training deep neural models on VisDial in isolation. Instead, we present an approach to leverage pretraining on related vision-language datasets before transferring to visual dialog. We adapt the recently proposed ViLBERT (Lu et al., 2019) model for multi-turn visually-grounde…
StableLM 2 1.6B is a new language model series with detailed evaluations and performance metrics.
problem Improving language models with smaller sizes and better performance.
method Detailed data and training procedure for StableLM 2 1.6B, including zero- and few-shot benchmarks and multilingual evaluations.
result StableLM 2 1.6B is the state-of-the-art open model under 2B parameters.
An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction use limited feature sets and employ annotation schemes with limit…
An automated metric to evaluate dialogue quality is vital for optimizing data driven dialogue management. The common approach of relying on explicit user feedback during a conversation is intrusive and sparse. Current models to estimate user satisfaction use limited feature sets and rely on annotation schemes with low …
HabitatAgent offers a multi-agent system for transparent housing consultation.
problem Opaque reasoning and brittle multi-constraint handling in housing recommendation systems.
method HabitatAgent is a multi-agent architecture with specialized roles for memory, retrieval, generation, and validation.
result HabitatAgent achieves 95% accuracy in real user consultation scenarios, significantly outperforming a strong baseline.
Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin by converting conversation history to a symbolic object referred to as belief sta…
Surrogate-based analysis of interactions via local effect smooths
problem Detecting and characterizing feature interactions in machine learning models
method Surrogate-based analysis using generalized additive models
result Empirical validation of effectiveness for pairwise interactions
Factorization Machine (FM) is a widely used supervised learning approach by effectively modeling of feature interactions. Despite the successful application of FM and its many deep learning variants, treating every feature interaction fairly may degrade the performance. For example, the interactions of a useless featur…
A new method detects interactions in neural networks using topological analysis.
problem Detecting interactions between input features in neural networks.
method Topological analysis of neural network connectivity to quantify interaction strength.
result The PID algorithm outperforms state-of-the-art baselines in interaction detection tasks.
iKF method uncovers complex variable interactions for scientific discovery.
problem Limited interpretability of existing models in decision-making applications.
method Iterative Kings' Forests (iKF) method to uncover multi-order interactions.
result iKF provides strong interpretive power for explainable modeling.
A graph neural network detects beneficial feature interactions for recommender systems.
problem Feature interactions are crucial but not all are beneficial for recommendation accuracy.
method Graph neural network with L0 activation regularization for edge prediction.
result The model outperforms baselines and automatically identifies beneficial feature interactions.
We describe and extract time-ordered multibody interactions from complex systems.
problem Complex systems with temporal and multibody dependencies.
method Decompose multivariate Markov chains into time-ordered multibody interactions. Algorithm to extract interactions from data. Measure complexity of interaction ensembles.
result Robust and efficient algorithm to infer time-ordered multibody interactions from data.
Dropout regularizes against high-order interactions by canceling interaction rates.
problem Overfitting to high-order interactions in neural networks.
method Analyzes Dropout through the lens of interaction effects, showing how it effectively cancels out the probability of surviving interactions of different orders.
result Dropout regularizes against high-order interactions by effectively canceling out the probability of surviving interactions of different orders.
Understanding how features interact with each other is of paramount importance in many scientific discoveries and contemporary applications. Yet interaction identification becomes challenging even for a moderate number of covariates. In this paper, we suggest an efficient and flexible procedure, called the interaction …
Multitask Gaussian process (MTGP) is powerful for joint learning of multiple tasks with complicated correlation patterns. However, due to the assembling of additive independent latent functions, all current MTGPs including the salient linear model of coregionalization (LMC) and convolution frameworks cannot effectively…
SocialInteractionGAN generates realistic human interactions from low-dimensional data.
problem Generating realistic human interactions from limited data.
method Adversarial architecture with a recurrent encoder-decoder generator and dual-stream discriminator.
result SocialInteractionGAN produces high-quality action sequences of interacting people.
A new method detects interactions in machine learning models.
problem Interpreting non-linear and interaction effects in machine learning models.
method Regional effect plots with implicit interaction detection.
result The method quantifies and interprets feature effects reliably, less confounded by interactions.
xDeepInt learns both vector-wise and bit-wise feature interactions.
problem Learning feature interactions for CTR prediction and recommendation.
method Polynomial Interaction Network (PIN) architecture with subspace-crossing mechanism.
result xDeepInt outperforms state-of-the-art models in CTR prediction and recommendation.
In this work, we aim to predict the future motion of vehicles in a traffic scene by explicitly modeling their pairwise interactions. Specifically, we propose a graph neural network that jointly predicts the discrete interaction modes and 5-second future trajectories for all agents in the scene. Our model infers an inte…
Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convo…
This study explores how feature graphs enhance GNNs' performance in modeling interactions.
problem Improving GNNs' ability to model feature interactions effectively.
method Investigates feature graphs and their importance in GNNs, using experiments and theoretical support.
result Edges between interacting features are crucial for GNNs, while non-interaction edges can degrade performance.
Interpreting neural networks is a crucial and challenging task in machine learning. In this paper, we develop a novel framework for detecting statistical interactions captured by a feedforward multilayer neural network by directly interpreting its learned weights. Depending on the desired interactions, our method can a…
We introduce interactive structure discovery, a generic framework that encompasses many interactive learning settings, including active learning, top-k item identification, interactive drug discovery, and others. We adapt a recently developed active learning algorithm of Tosh and Dasgupta (2017) for interactive structu…
Paper introduces IC-index to evaluate interaction prediction methods.
problem Evaluate interaction prediction methods using IC-index.
method IC-index measures interaction direction prediction performance.
result IC-index complements existing prediction performance estimators.
This paper uses Gaussian mixtures to mimic interactions in large language models.
problem Simulating interactions in large language models (LLMs) is computationally expensive.
method Developed an interacting Gaussian mixture model (GMM) system to mimic LLM interactions.
result The interacting Gaussian mixture model system can generate, exchange, and update data and parameters efficiently.
Study reveals self-attention's role in learning and generalizing interactions.
problem Understanding self-attention's theoretical role in neural architectures.
method Interacting entities analysis, including multi-agent RL and genetic sequences.
result Self-attention efficiently represents, learns, and generalizes pairwise interactions.
Archipelago provides interpretable explanations of feature interactions in machine learning models.
problem Interpreting the impact of feature interactions on predictions in machine learning models.
method Archipelago is a novel framework for extracting and attributing feature interactions in a scalable and interpretable manner.
result Archipelago provides significantly more interpretable explanations of feature interactions than comparable methods.
Automated tests detect interactions in unstructured data.
problem Detecting interactions between latent variables in low-dimensional systems.
method Derive two interaction tests based on pairwise interventions and integrate them into an active learning pipeline.
result Tests can identify more known biological interactions than random search and standard active learning baselines.
We study the power of interactivity in local differential privacy. First, we focus on the difference between fully interactive and sequentially interactive protocols. Sequentially interactive protocols may query users adaptively in sequence, but they cannot return to previously queried users. The vast majority of exist…
PIN models feature interactions using a neural network that mimics decision trees.
problem Modeling feature interactions in tabular data for predictive modeling.
method Tree-like Pairwise Interaction Network (PIN) architecture that captures pairwise feature interactions through a shared feed-forward neural network.
result PIN outperforms traditional and modern neural networks benchmarks in predictive accuracy.
The paper explains DNNs by quantifying interactions among input variables.
problem Understanding and explaining the complex behavior of deep neural networks.
method The paper defines and quantifies the significance of interactions among multiple input variables using the Shapley value.
result The proposed method effectively explains the behavior of DNNs by assigning attribution values to input variables.
Modeling continuous movement of entities in latent space for interaction timing.
problem Analyzing timing and frequency of instantaneous interactions.
method Latent position model with continuous trajectories.
result Individual trajectories estimated from interaction data.
The paper improves dropout's utility by reducing interactions in deep neural networks.
problem Over-fitting problem in deep learning.
method Game-theoretic interactions analysis and interaction loss.
result Interaction loss improves dropout's utility and boosts DNN performance.
New model quantifies interactions' role in real-world phenomena.
problem Understanding the role of interactions in real-world phenomena.
method Interactive Mixed Membership Stochastic Block Model (IMMSBM).
result Interactions significantly improve model predictive power.
MEI model improves knowledge graph completion by efficiently modeling interactions between embeddings.
problem Efficiently modeling interactions between knowledge graph embeddings to predict missing links.
method MEI divides embeddings into partitions and uses Tucker and block term formats to model interactions efficiently.
result Achieves state-of-the-art performance on link prediction tasks.