Related papers: In-Context Learning for Pure Exploration

Related papers

In-Context Learning for Pure Exploration in Continuous Spaces [26.001092687873125]
In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information.<n>We introduce C-ICPE-TS, an algorithm that meta-trains deep neural policies to map observation histories to the next continuous query action.<n>At inference time, C-ICPE-TS actively gathers evidence on previously unseen tasks and infers the true hypothesis without parameter updates or explicit hand-crafted information models.
arXiv Detail & Related papers (2026-02-20T04:20:47Z)
Adaptive Retrieval helps Reasoning in LLMs -- but mostly if it's not used [19.370220750406755]
Large Language Models (LLMs) often falter in complex reasoning tasks due to their static, parametric knowledge.<n>This work explores a fundamental principle for enhancing generative models: treating retrieval as a form of dynamic in-context learning.
arXiv Detail & Related papers (2026-02-06T21:48:26Z)
Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
arXiv Detail & Related papers (2025-12-23T08:14:44Z)
FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation [0.0]
We introduce FAIR-RAG, a novel agentic framework that transforms the standard RAG pipeline into a dynamic, evidence-driven reasoning process.<n>We conduct experiments on challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, and MusiQue.<n>Our work demonstrates that a structured, evidence-driven refinement process with explicit gap analysis is crucial for unlocking reliable and accurate reasoning in advanced RAG systems.
arXiv Detail & Related papers (2025-10-25T15:59:33Z)
Uncovering Bias Paths with LLM-guided Causal Discovery: An Active Learning and Dynamic Scoring Approach [1.5498930424110338]
Large Language Models (LLMs) offer a promising complement to statistical Causal Discovery (CD) approaches.<n> Ensuring fairness in machine learning requires understanding how sensitive attributes causally influence outcomes.<n>We propose a hybrid LLM-based framework for CD that extends a breadth-first search (BFS) strategy with active learning and dynamic scoring.
arXiv Detail & Related papers (2025-06-13T21:04:03Z)
Chain-of-Retrieval Augmented Generation [91.02950964802454]
This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
arXiv Detail & Related papers (2025-01-24T09:12:52Z)
Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning [0.0]
We study the training dynamics of a single-layer GAN model from the perspective of subspace learning. By bridging our analysis to the realm of subspace learning, we systematically compare the efficacy of GAN-based methods against conventional approaches.
arXiv Detail & Related papers (2024-11-01T10:21:12Z)
EVOLvE: Evaluating and Optimizing LLMs For In-Context Exploration [76.66831821738927]
Large language models (LLMs) remain under-studied in scenarios requiring optimal decision-making under uncertainty.<n>We measure LLMs' (in)ability to make optimal decisions in bandits, a state-less reinforcement learning setting relevant to many applications.<n>Motivated by the existence of optimal exploration algorithms, we propose efficient ways to integrate this algorithmic knowledge into LLMs.
arXiv Detail & Related papers (2024-10-08T17:54:03Z)
Causality-Aware Transformer Networks for Robotic Navigation [13.719643934968367]
Current research in Visual Navigation reveals opportunities for improvement. Direct adoption of RNNs and Transformers often overlooks the specific differences between Embodied AI and traditional sequential data modelling. We propose Causality-Aware Transformer (CAT) Networks for Navigation, featuring a Causal Understanding Module.
arXiv Detail & Related papers (2024-09-04T12:53:26Z)
Detecting and Identifying Selection Structure in Sequential Data [53.24493902162797]
We argue that the selective inclusion of data points based on latent objectives is common in practical situations, such as music sequences. We show that selection structure is identifiable without any parametric assumptions or interventional experiments. We also propose a provably correct algorithm to detect and identify selection structures as well as other types of dependencies.
arXiv Detail & Related papers (2024-06-29T20:56:34Z)
Understanding active learning of molecular docking and its applications [0.6554326244334868]
We investigate how active learning methodologies effectively predict docking scores using only 2D structures. Our findings suggest that surrogate models tend to memorize structural patterns prevalent in high docking scored compounds. Our comprehensive analysis underscores the reliability and potential applicability of active learning methodologies in virtual screening campaigns.
arXiv Detail & Related papers (2024-06-14T05:43:42Z)
C-ICL: Contrastive In-context Learning for Information Extraction [54.39470114243744]
c-ICL is a novel few-shot technique that leverages both correct and incorrect sample constructions to create in-context learning demonstrations. Our experiments on various datasets indicate that c-ICL outperforms previous few-shot in-context learning methods.
arXiv Detail & Related papers (2024-02-17T11:28:08Z)
RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
arXiv Detail & Related papers (2023-11-21T21:05:21Z)
Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors [58.340159346749964]
We propose a new neural-symbolic method to support end-to-end learning using complex queries with provable reasoning capability. We develop a new dataset containing ten new types of queries with features that have never been considered. Our method outperforms previous methods significantly in the new dataset and also surpasses previous methods in the existing dataset at the same time.
arXiv Detail & Related papers (2023-04-14T11:35:35Z)
Human-Inspired Framework to Accelerate Reinforcement Learning [1.6317061277457001]
Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency. This paper introduces a novel human-inspired framework to enhance RL algorithm sample efficiency.
arXiv Detail & Related papers (2023-02-28T13:15:04Z)
Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration [17.27164535440641]
Posterior sampling is a promising approach, but it requires Bayesian inference and dynamic programming. We show that even though partial models exclude relevant information from the environment, they can nevertheless lead to good policies.
arXiv Detail & Related papers (2023-02-08T18:35:24Z)
Scalable PAC-Bayesian Meta-Learning via the PAC-Optimal Hyper-Posterior: From Theory to Practice [54.03076395748459]
A central question in the meta-learning literature is how to regularize to ensure generalization to unseen tasks. We present a generalization bound for meta-learning, which was first derived by Rothfuss et al. We provide a theoretical analysis and empirical case study under which conditions and to what extent these guarantees for meta-learning improve upon PAC-Bayesian per-task learning bounds.
arXiv Detail & Related papers (2022-11-14T08:51:04Z)
Aggregating Pairwise Semantic Differences for Few-Shot Claim Veracity Classification [21.842139093124512]
We introduce SEED, a novel vector-based method to claim veracity classification. We build on the hypothesis that we can simulate class representative vectors that capture average semantic differences for claim-evidence pairs in a class. Experiments conducted on the FEVER and SCIFACT datasets show consistent improvements over competitive baselines in few-shot settings.
arXiv Detail & Related papers (2022-05-11T17:23:37Z)
A New Score for Adaptive Tests in Bayesian and Credal Networks [64.80185026979883]
A test is adaptive when its sequence and number of questions is dynamically tuned on the basis of the estimated skills of the taker. We present an alternative family of scores, based on the mode of the posterior probabilities, and hence easier to explain.
arXiv Detail & Related papers (2021-05-25T20:35:42Z)
DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation [57.358212277226315]
In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms. This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk. We propose a more data-efficient IfO algorithm
arXiv Detail & Related papers (2021-03-31T23:46:32Z)
Learning Dexterous Manipulation from Suboptimal Experts [69.8017067648129]
Relative Entropy Q-Learning (REQ) is a simple policy algorithm that combines ideas from successful offline and conventional RL algorithms. We show how REQ is also effective for general off-policy RL, offline RL, and RL from demonstrations.
arXiv Detail & Related papers (2020-10-16T18:48:49Z)
Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning [61.32992639292889]
Fine-tuning of pre-trained transformer models has become the standard approach for solving common NLP tasks. We introduce a new scoring method that casts a plausibility ranking task in a full-text format. We show that our method provides a much more stable training phase across random restarts.
arXiv Detail & Related papers (2020-04-29T10:54:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.