Search Results for author:
Found 45 papers, 12 papers with code
Context Attribution with Multi-Armed Bandit Optimization
Each context segment is treated as a bandit arm, and we employ Combinatorial Thompson Sampling (CTS) to efficiently explore the exponentially large space of context subsets under a limited query budget.
AutoData: A Multi-Agent System for Open Web Data Collection
To address these challenges, we propose AutoData, a novel multi-agent system for Automated web Data collection, that requires minimal human intervention, i. e., only necessitating a natural language instruction specifying the desired dataset.
EfficientLLM: Efficiency in Large Language Models
Large Language Models (LLMs) have driven significant progress, yet their growing parameter counts and context windows incur prohibitive compute, energy, and monetary costs.
PEEL the Layers and Find Yourself: Revisiting Inference-time Data Leakage for Residual Neural Networks
By formulating inference-time data leakage as a constrained optimization problem, we propose a novel backward feature inversion method, \textbf{PEEL}, which can effectively recover block-wise input features from the intermediate output of residual NNs.
Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations
Large Language Models (LLMs) are often asked to explain their outputs to enhance accuracy and transparency.
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
It aims to minimize privacy risks by ensuring that users (sender) disclose only information that is both relevant and necessary for achieving their intended goals when interacting with LLMs (untrusted receivers).
NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional Reasoning
On the other hand, while large language models (LLMs), a popular solution for this task, demonstrate strong reasoning abilities, they struggle with the domain-specific complexities of personalized healthy dietary reasoning, and existing benchmarks fail to capture these challenges.
MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation
The prevalence of unhealthy eating habits has become an increasingly concerning issue in the United States.
Granite Guardian
We introduce the Granite Guardian models, a suite of safeguards designed to provide risk detection for prompts and responses, enabling safe and responsible use in combination with any large language model (LLM).
Combinatorial Multi-armed Bandits: Arm Selection via Group Testing
Under a general separability assumption on the reward function, the proposed algorithm reduces the complexity of the super-arm-selection oracle to be logarithmic in the number of base arms while achieving the same regret order as the state-of-the-art algorithms that use exact oracles.
Towards Aligning Language Models with Textual Feedback
We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text.
CTBench: A Comprehensive Benchmark for Evaluating Language Model Capabilities in Clinical Trial Design
Given study-specific metadata, CTBench evaluates AI models' ability to determine the baseline features of a clinical trial (CT), which include demographic and relevant features collected at the trial's start from all participants.
STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models
In this work, we introduce an interactive environment for self-supervised RL, STARLING, for text-based games that bootstraps the text-based RL agents with automatically generated games (based on the seed set of game ideas) to boost the performance and generalization capabilities to reach a goal of the target environment.
Facilitating Human-LLM Collaboration through Factuality Scores and Source Attributions
To address this issue, we conducted a scenario-based study (N=104) to systematically compare the impact of various design strategies for communicating factuality and source attribution on participants' ratings of trust, preferences, and ease in validating response accuracy.
SF-DQN: Provable Knowledge Transfer using Successor Feature for Deep Reinforcement Learning
This paper studies the transfer reinforcement learning (RL) problem where multiple RL problems have different reward functions but share the same underlying transition dynamics.
On the Effects of Fine-tuning Language Models for Text-Based Reinforcement Learning
Moreover, we describe the occurrence of semantic degeneration as a consequence of inappropriate fine-tuning of language models in text-based reinforcement learning (TBRL).
EXPLORER: Exploration-guided Reasoning for Textual Reinforcement Learning
To tackle these issues, in this paper, we present EXPLORER which is an exploration-guided reasoning agent for textual reinforcement learning.
Detectors for Safe and Reliable LLMs: Implementations, Uses, and Limitations
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
Language Guided Exploration for RL Agents in Text Environments
Real-world sequential decision making is characterized by sparse rewards and large decision spaces, posing significant difficulty for experiential learning systems like $\textit{tabula rasa}$ reinforcement learning (RL) agents.
On the Prospects of Incorporating Large Language Models (LLMs) in Automated Planning and Scheduling (APS)
Automated Planning and Scheduling is among the growing areas in Artificial Intelligence (AI) where mention of LLMs has gained popularity.
On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $ε$-Greedy Exploration
This paper provides the first theoretical convergence and sample complexity analysis of the practical setting of DQNs with $\epsilon$-greedy policy.
Value-based Fast and Slow AI Nudging
Values that are relevant to a specific decision scenario are used to decide when and how to use each of these nudging modalities.
Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning
Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games.
MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types
In this work, we propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts.
Understanding the Capabilities of Large Language Models for Automated Planning
Firstly, we want to understand the extent to which LLMs can be used for plan generation.
Fast and Slow Planning
The concept of Artificial Intelligence has gained a lot of attention over the last decade.
Plansformer: Generating Symbolic Plans using Transformers
Large Language Models (LLMs) have been the subject of active research, significantly advancing the field of Natural Language Processing (NLP).
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach
Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them.
Targeted Advertising on Social Networks Using Online Variational Tensor Regression
The proposed framework is designed to accommodate any number of feature vectors in the form of multi-mode tensor, thereby enabling to capture the heterogeneity that may exist over user preferences, products, and campaign strategies in a unified manner.
Auto-Transfer: Learning to Route Transferrable Representations
Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labeled data can be difficult to obtain in many applications.
A Hybrid Neuro-Symbolic approach for Text-Based Games using Inductive Logic Programming
These rules are learned in an online manner and applied with an ASP solver to predict an action for the agent.
Inductive logic programming
Natural Language Understanding
+2
Case-based Reasoning for Better Generalization in Textual Reinforcement Learning
Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency.
Deep Reinforcement Learning
Out-of-Distribution Generalization
+3
Auto-Transfer: Learning to Route Transferable Representations
Knowledge transfer between heterogeneous source and target networks and tasks has received a lot of attention in recent times as large amounts of quality labelled data can be difficult to obtain in many applications.
Efficient Text-based Reinforcement Learning by Jointly Leveraging State and Commonsense Graph Representations
Text-based games (TBGs) have emerged as useful benchmarks for evaluating progress at the intersection of grounded language understanding and reinforcement learning (RL).
Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents
This improves the agent's overall understanding of the game 'scene' and objects' relationships to the world around them, and the variety of visual representations on offer allow the agent to generate a better generalization of a relationship.
Thinking Fast and Slow in AI
This paper proposes a research direction to advance AI which draws inspiration from cognitive theories of human decision making.
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Baselines
Text-based games have emerged as an important test-bed for Reinforcement Learning (RL) research, requiring RL agents to combine grounded language understanding with sequential decision making.
Ranked #1 on
Commonsense Reasoning for RL
on commonsense-rl
Text-based RL Agents with Commonsense Knowledge: New Challenges, Environments and Approaches
We introduce a number of RL agents that combine the sequential context with a dynamic graph representation of their beliefs of the world and commonsense knowledge from ConceptNet in different ways.
Enhancing Text-based Reinforcement Learning Agents with Commonsense Knowledge
In this paper, we consider the recent trend of evaluating progress on reinforcement learning technology by using text-based environments and games as evaluation environments.
Lifelong Learning with Output Kernels
Lifelong learning poses considerable challenges in terms of effectiveness (minimizing prediction errors for all tasks) and overall computational tractability for real-time performance.
Active Learning from Peers
This paper addresses the challenge of learning from peers in an online multitask setting.
Co-Clustering for Multitask Learning
This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters.
Self-Paced Multitask Learning with Shared Knowledge
This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning.
Adaptive Smoothed Online Multi-Task Learning
This paper addresses the challenge of jointly learning both the per-task model parameters and the inter-task relationships in a multi-task online learning setting.
Multi-Task Multiple Kernel Relationship Learning
The problem is formulated as a regularization-based approach called \textit{Multi-Task Multiple Kernel Relationship Learning} (\textit{MK-MTRL}), which models the task relationship matrix from the weights learned from latent feature spaces of task-specific base kernels.
