Related papers: A Single Revision Step Improves Token-Efficient LL…

While large language models (LLMs) such as ChatGPT and PaLM have demonstrated remarkable performance in various language understanding and generation tasks, their capabilities in complex reasoning and intricate knowledge utilization still…

Peer prediction mechanisms motivate high-quality feedback with provable guarantees. However, current methods only apply to rather simple reports, like multiple-choice or scalar numbers. We aim to broaden these techniques to the larger…

Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…

Multimodal Large Language Models (MLLMs) have emerged to tackle the challenges of Visual Question Answering (VQA), sparking a new research focus on conducting objective evaluations of these models. Existing evaluation methods face…

Large Multimodal Models (LMMs) are increasingly applied to scientific research, yet it remains unclear whether they can reliably understand and reason over the multimodal complexity of papers. A central challenge lies in detecting and…

Despite their success in many natural language tasks, solving math problems remains a significant challenge for large language models (LLMs). A large gap exists between LLMs' pass-at-one and pass-at-N performance in solving math problems,…

The advent of large language models (LLMs) offers unprecedented opportunities to reimagine peer review beyond the constraints of traditional workflows. Despite these opportunities, prior efforts have largely focused on replicating…

Recent advances in large language models (LLMs) have made it increasingly difficult to distinguish human-written text from AI-generated content. Many existing detectors train supervised neural classifiers that achieve strong in-distribution…

There is intense interest in investigating how inference time compute (ITC) (e.g. repeated sampling, refinements, etc) can improve large language model (LLM) capabilities. At the same time, recent breakthroughs in reasoning models, such as…

Mathematical reasoning in large language models has improved substantially with reinforcement learning using verifiable rewards, where final answers can be checked automatically and converted into reliable training signals. Most such…

Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often…

Process supervision, using a trained verifier to evaluate the intermediate steps generated by a reasoner, has demonstrated significant improvements in multi-step problem solving. In this paper, to avoid the expensive effort of human…

Large language models have demonstrated impressive performance across a variety of reasoning tasks. However, their problem-solving ability often declines on more complex tasks due to hallucinations and the accumulation of errors within…

We introduce PARSE (PArallel pRefix Speculative Engine), a speculative generation framework that accelerates large language model (LLM) inference by parallelizing prefix verification on a semantic level. Existing speculative decoding…

We introduce TASER (Translation Assessment via Systematic Evaluation and Reasoning), a metric that uses Large Reasoning Models (LRMs) for automated translation quality assessment. TASER harnesses the explicit reasoning capabilities of LRMs…

New Large Language Models (LLMs) become available every few weeks, and modern application developers confronted with the unenviable task of having to decide if they should switch to a new model. While human evaluation remains the gold…

Large language models (LLMs) achieve strong average performance yet remain unreliable at the instance level, with frequent hallucinations, brittle failures, and poorly calibrated confidence. We study reliability through the lens of…

Harnessing the reasoning power of Large Language Models (LLMs) for recommender systems is hindered by two fundamental challenges. First, current approaches lack a mechanism for automated, data-driven discovery of effective reasoning…

Despite the strong reasoning ability of large language models~(LLMs), they are prone to errors and hallucinations. As a result, how to check their outputs effectively and efficiently has become a critical problem in their applications.…

While Large Language Models (LLMs) have shown significant potential in assisting peer review, current methods often struggle to generate thorough and insightful reviews while maintaining efficiency. In this paper, we propose TreeReview, a…