Related papers: SAGE: Scalable Automated Robustness Augmentation f…

Test-time scaling for code generation commonly relies on Best-of-N selection, in which multiple candidate solutions are sampled from a base model, and the best one is selected by an LLM judge. However, training reliable LLM judges is…

We present WaferSAGE, a framework for wafer defect visual question answering using small vision-language models. To address data scarcity in semiconductor manufacturing, we propose a three-stage synthesis pipeline incorporating structured…

Large Language Models (LLMs) are predominantly evaluated on Standard American English (SAE), often overlooking the diversity of global English varieties. This narrow focus may raise fairness concerns as degraded performance on non-standard…

Large language models (LLMs) have shown impressive capability to understand and develop code. However, their capability to rigorously reason about and prove code correctness remains in question. This paper offers a comprehensive study of…

Recent advancements in the field of reasoning using Large Language Models (LLMs) have created new possibilities for more complex and automatic Hardware Assertion Generation techniques. This paper introduces SANGAM, a SystemVerilog Assertion…

Retrieval-augmented generation (RAG) generally enhances large language models' (LLMs) ability to solve knowledge-intensive tasks. But RAG may also lead to performance degradation due to imperfect retrieval and the model's limited ability to…

We introduce Learning to Self-Evolve (LSE), a reinforcement learning framework that trains large language models (LLMs) to improve their own contexts at test time. We situate LSE in the setting of test-time self-evolution, where a model…

Large Language Models (LLMs) have been widely adopted in conversational applications. However, their reliance on parametric knowledge limits reliability in real-world scenarios that require dynamic or domain-specific information.…

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet exhibit critical limitations in knowledge-intensive tasks, often generating hallucinations when faced with questions requiring…

Assessing and enhancing human learning through question-answering is vital, yet automating this process remains challenging. While large language models (LLMs) excel at summarization and query responses, their ability to generate meaningful…

Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting,…

While logical reasoning evaluation of Large Language Models (LLMs) has attracted significant attention, existing benchmarks predominantly rely on multiple-choice formats that are vulnerable to random guessing, leading to overestimated…

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable…

Despite the advancements made in Vision Large Language Models (VLLMs), like text Large Language Models (LLMs), they have limitations in addressing questions that require real-time information or are knowledge-intensive. Indiscriminately…

The swift advancement in the scales and capabilities of Large Language Models (LLMs) positions them as promising tools for a variety of downstream tasks. In addition to the pursuit of better performance and the avoidance of violent feedback…

In various natural language processing (NLP) tasks, fine-tuning Pre-trained Language Models (PLMs) often leads to the issue of spurious correlations, which negatively impacts performance, particularly when dealing with out-of-distribution…

Despite notable advancements in Retrieval-Augmented Generation (RAG) systems that expand large language model (LLM) capabilities through external retrieval, these systems often struggle to meet the complex and diverse needs of real-world…

Large Language Models (LLMs) exhibit strong potential in mathematical reasoning, yet their effectiveness is often limited by a shortage of high-quality queries. This limitation necessitates scaling up computational responses through…

Diffusion models manifest evident benefits across diverse domains, yet their high sampling cost, requiring dozens of sequential model evaluations, remains a major limitation. Prior efforts mainly accelerate sampling via optimized solvers or…

The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data contamination and saturation, leading to inflated or misleading…