Related papers: Full Stage Learning to Rank: A Unified Framework f…

Recommender systems are tasked to infer users' evolving preferences and rank items aligned with their intents, which calls for in-depth reasoning beyond pattern-based scoring. Recent efforts start to leverage large language models (LLMs)…

Recently, generative retrieval-based recommendation systems have emerged as a promising paradigm. However, most modern recommender systems adopt a retrieve-and-rank strategy, where the generative model functions only as a selector during…

While Retrieval-Augmented Generation (RAG) has exhibited promise in utilizing external knowledge, its generation process heavily depends on the quality and accuracy of the retrieved context. Large language models (LLMs) struggle to evaluate…

Hierarchical multi-label classification (HMC) has gained considerable attention in recent decades. A seminal line of HMC research addresses the problem in two stages: first, training individual classifiers for each class, then integrating…

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

Sequential decision making, commonly formalized as optimization of a Markov Decision Process, is a key challenge in artificial intelligence. Two successful approaches to MDP optimization are reinforcement learning and planning, which both…

Selecting a solution algorithm for the Facility Layout Problem (FLP), an NP-hard optimization problem with multiobjective trade-off, is a complex task that requires deep expert knowledge. The performance of a given algorithm depends on the…

Retrieval-Augmented Generation (RAG) systems typically rely on a single fixed retriever, despite growing evidence that no single retriever performs optimally across all query types. In this paper, we explore a query routing approach that…

Ensuring AI models align with human values is essential for their safety and functionality. Reinforcement learning from human feedback (RLHF) leverages human preferences to achieve this alignment. However, when preferences are sourced from…

Cutting plane methods play a significant role in modern solvers for tackling mixed-integer programming (MIP) problems. Proper selection of cuts would remove infeasible solutions in the early stage, thus largely reducing the computational…

The Rank Pricing Problem (RPP) is a challenging bilevel optimization problem with binary variables whose objective is to determine the optimal pricing strategy for a set of products to maximize the total benefit, given that customer…

Counterfactual learning to rank (CLTR) can be risky and, in various circumstances, can produce sub-optimal models that hurt performance when deployed. Safe CLTR was introduced to mitigate these risks when using inverse propensity scoring to…

The Retrieval-Augmented Generation (RAG) framework introduces a retrieval module to dynamically inject retrieved information into the input context of large language models (LLMs), and has demonstrated significant success in various NLP…

Ranking entities such as algorithms, devices, methods, or models based on their performances, while accounting for application-specific preferences, is a challenge. To address this challenge, we establish the foundations of a universal…

Most popular deep models for action recognition split video sequences into short sub-sequences consisting of a few frames; frame-based features are then pooled for recognizing the activity. Usually, this pooling step discards the temporal…

Iterative data generation and model re-training can effectively align large language models(LLMs) to human preferences. The process of data sampling is crucial, as it significantly influences the success of policy improvement. Repeated…

Theoretical frameworks like the Probability Ranking Principle and its more recent Interactive Information Retrieval variant have guided the development of ranking and retrieval algorithms for decades, yet they are not capable of helping us…

Inference-time alignment methods have gained significant attention for their efficiency and effectiveness in aligning large language models (LLMs) with human preferences. However, existing dominant approaches using reward-guided search…

Offline evaluation of information retrieval and recommendation has traditionally focused on distilling the quality of a ranking into a scalar metric such as average precision or normalized discounted cumulative gain. We can use this metric…

Preference-based optimization algorithms are iterative procedures that seek the optimal calibration of a decision vector based only on comparisons between couples of different tunings. At each iteration, a human decision-maker expresses a…