相关论文: LLM-guided Plan and Retrieval: A Strategic Alignme…
Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine logical preference consistency…
Large language models (LLMs) excel at general-purpose tasks, yet adapting their responses to individual users remains challenging. Retrieval augmentation provides a lightweight alternative to fine-tuning by conditioning LLMs on user history…
Recently, there has been growing interest within the community regarding whether large language models are capable of planning or executing plans. However, most prior studies use LLMs to generate high-level plans for simplified scenarios…
Large language models (LLMs) have shown impressive capabilities across a wide range of language tasks. However, their reasoning process is primarily guided by statistical patterns in training data, which limits their ability to handle novel…
Large Language Models (LLMs) have been widely applied across multiple domains for their broad knowledge and strong reasoning capabilities. However, applying them to recommendation systems is challenging since it is hard for LLMs to extract…
As Retrieval-Augmented Generation (RAG) systems evolve toward more sophisticated architectures, ensuring their trustworthiness through explainable and robust evaluation becomes critical. Existing scalar metrics suffer from limited…
Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical…
Personalized retrieval-augmented generation (RAG) aims to produce user-tailored responses by incorporating retrieved user profiles alongside the input query. Existing methods primarily focus on improving retrieval and rely on large language…
Evaluation is crucial in the development process of task-oriented dialogue systems. As an evaluation method, user simulation allows us to tackle issues such as scalability and cost-efficiency, making it a viable choice for large-scale…
Large Language Models (LLMs) have shown improved generation performance through retrieval-augmented generation (RAG) following the retriever-reader paradigm, which supplements model inputs with externally retrieved knowledge. However, prior…
Search-augmented large language models (LLMs) have advanced information-seeking tasks by integrating retrieval into generation, reducing users' cognitive burden compared to traditional search systems. Yet they remain insufficient for fully…
Product search is a crucial component of modern e-commerce platforms, with billions of user queries every day. In product search systems, first-stage retrieval should achieve high recall while ensuring efficient online deployment. Sparse…
Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed…
The increasing demand for personalized interactions with large language models (LLMs) calls for methodologies capable of accurately and efficiently identifying user opinions and preferences. Retrieval augmentation emerges as an effective…
The Retrieval-Augmented Language Model (RALM) has shown remarkable performance on knowledge-intensive tasks by incorporating external knowledge during inference, which mitigates the factual hallucinations inherited in large language models…
We tackle the challenge of integrating large language models (LLMs) with external recommender systems to enhance domain expertise in conversational recommendation (CRS). Current LLM-based CRS approaches primarily rely on zero/few-shot…
Retrieval-Augmented Generation (RAG) systems for Large Language Models (LLMs) hold promise in knowledge-intensive tasks but face limitations in complex multi-step reasoning. While recent methods have integrated RAG with chain-of-thought…
Event extraction has gained extensive research attention due to its broad range of applications. However, the current mainstream evaluation method for event extraction relies on token-level exact match, which misjudges numerous…
Large language models can recognize when they are being evaluated (evaluation awareness) and behave differently because of that, which undermines the validity of safety and alignment benchmarks. We propose LURE (Live-Usage Replay…
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…