Related papers: LLM Routing with Dueling Feedback

While recent advances in large language models (LLMs) have significantly enhanced performance across diverse natural language tasks, the high computational and financial costs associated with their deployment remain substantial barriers.…

In-context learning (ICL) and supervised fine-tuning (SFT) are two common strategies for improving the performance of modern large language models (LLMs) on specific tasks. Despite their different natures, these strategies often lead to…

In-context Learning (ICL) utilizes structured demonstration-query inputs to induce few-shot learning on Language Models (LMs), which are not originally pre-trained on ICL-style data. To bridge the gap between ICL and pre-training, some…

Large language models (LLMs) such as GPT-4o and Claude Sonnet 4.5 have demonstrated strong capabilities in open-ended reasoning and generative language tasks, leading to their widespread adoption across a broad range of NLP applications.…

Large language models (LLMs) show amazing performance on many domain-specific tasks after fine-tuning with some appropriate data. However, many domain-specific data are privately distributed across multiple owners. Thus, this dilemma raises…

Despite the strong performance of large language models (LLMs) across a wide range of tasks, they still have reliability issues. Previous studies indicate that strong LLMs like GPT-4-turbo excel in evaluating the reliability of responses…

We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). We call our method BanditRank as it treats ranking as a contextual bandit problem. In…

Large Language Models (LLMs) process millions of queries daily, making efficient response caching a compelling optimization for reducing cost and latency. However, preserving relevance to user queries using this approach proves difficult…

We introduce efficient algorithms which achieve nearly optimal regrets for the problem of stochastic online shortest path routing with end-to-end feedback. The setting is a natural application of the combinatorial stochastic bandits…

LLM routers aim to balance quality and cost of generation by classifying queries and routing them to a cheaper or more expensive LLM depending on their complexity. Routers represent one type of what we call LLM control planes: systems that…

Fine-tuning Large Language Models (LLMs) adapts a trained model to specific downstream tasks, significantly improving task-specific performance. Supervised Fine-Tuning (SFT) is a common approach, where an LLM is trained to produce desired…

We study methods for efficiently aligning large language models (LLMs) with human preferences given budgeted online feedback. We first formulate the LLM alignment problem in the frame of contextual dueling bandits. This formulation,…

We present LLM-KT, a flexible framework designed to enhance collaborative filtering (CF) models by seamlessly integrating LLM (Large Language Model)-generated features. Unlike existing methods that rely on passing LLM-generated features as…

In recent years, instruction fine-tuning (IFT) on large language models (LLMs) has garnered considerable attention to enhance model performance on unseen tasks. Attempts have been made on automatic construction and effective selection for…

Personalization is a crucial aspect of many online experiences. In particular, content ranking is often a key component in delivering sophisticated personalization results. Commonly, supervised learning-to-rank methods are applied, which…

The contextual duelling bandit problem models adaptive recommender systems, where the algorithm presents a set of items to the user, and the user's choice reveals their preference. This setup is well suited for implicit choices users make…

Understanding real-world videos with complex semantics and long temporal dependencies remains a fundamental challenge in computer vision. Recent progress in multimodal large language models (MLLMs) has demonstrated strong capabilities in…

Recent advances in large language models (LLMs) have significantly improved the alignment of models with general human preferences. However, a major challenge remains in adapting LLMs to individual preferences, which are not only diverse…

The availability of large pre-trained models is changing the landscape of Machine Learning research and practice, moving from a training-from-scratch to a fine-tuning paradigm. While in some applications the goal is to "nudge" the…

Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the existing literature overlooks a property of LLM-generated responses: they conflate world…