Related papers: Beyond Majority Voting: Efficient Best-Of-N with R…

We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combines a lightweight draft model with a more powerful target…

Self-consistency has emerged as a powerful method for improving the accuracy of short answers generated by large language models. As previously defined, it only concerns the accuracy of a final answer parsed from generated text. In this…

It has long been recognized that it is not enough for a Recommender System (RS) to provide recommendations based only on their relevance to users. Among many other criteria, the set of recommendations may need to be diverse. Diversity is…

Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models (LLMs) by employing a fast draft model to propose candidate token sequences and a large target model to verify them in…

Learning with curriculum has shown great effectiveness in tasks where the data contains noisy (corrupted) labels, since the curriculum can be used to re-weight or filter out noisy samples via proper design. However, obtaining curriculum…

Scaling test-time computation with reinforcement learning (RL) has emerged as a reliable path to improve large language models (LLM) reasoning ability. Yet, outcome-based reward often incentivizes models to be overconfident, leading to…

Learning from negative samples holds great promise for improving Large Language Model (LLM) reasoning capability, yet existing methods treat all incorrect responses as equally informative, overlooking the crucial role of sample quality. To…

Large language models (LLMs) have achieved remarkable progress in the field of natural language processing (NLP), demonstrating remarkable abilities in producing text that resembles human language for various tasks. This opens up new…

While Large Language Models (LLMs) form the cornerstone of sequential decision-making agent development, they have inherent limitations in high-frequency decision tasks. Existing research mainly focuses on discrete embodied decision…

Recent advances in large language models (LLMs) have enabled zero-shot automated essay scoring (AES), providing a promising way to reduce the cost and effort of essay scoring in comparison with manual grading. However, most existing…

Large language models (LLMs) are increasingly used in applications requiring factual accuracy, yet their outputs often contain hallucinated responses. While fact-checking can mitigate these errors, existing methods typically retrieve…

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…

Convolutional sparse representation (CSR), shift-invariant model for inverse problems, has gained much attention in the fields of signal/image processing, machine learning and computer vision. The most challenging problems in CSR implies…

Scaling test-time compute brings substantial performance gains for large language models (LLMs). By sampling multiple answers and heuristically aggregate their answers (e.g., either through majority voting or using verifiers to rank the…

Aligning large language models (LLMs) with human preferences is essential for their applications. Recently, decoding-time alignment has emerged as an effective plug-and-play technique that avoids fine-tuning model parameters. This approach…

As large language models (LLMs) are deployed in consequential settings such as medical question answering and legal reasoning, the ability to estimate when their outputs are likely to be correct is essential for safe and reliable use,…

A Conversational Recommender System (CRS) offers increased transparency and control to users by enabling them to engage with the system through a real-time multi-turn dialogue. Recently, Large Language Models (LLMs) have exhibited an…

Content-based recommendation systems (CRSs) utilize content features to predict user-item interactions, serving as essential tools for helping users navigate information-rich web services. However, ensuring the effectiveness of CRSs…

RANSAC and its variants are widely used for robust estimation, however, they commonly follow a greedy approach to finding the highest scoring model while ignoring other model hypotheses. In contrast, Iteratively Reweighted Least Squares…

Inconsistent outputs and hallucinations from large language models (LLMs) are major obstacles to reliable AI systems. When different proprietary reasoning models (RMs), such as those by OpenAI, Google, Anthropic, DeepSeek, and xAI, are…