Related papers: RAZOR: Sharpening Knowledge by Cutting Bias with U…

Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

Accurate prediction of resource consumption and runtime for cloud workflow jobs is critical for scheduling efficiency, yet remains challenging due to the semi-structured nature of job configurations -- comprising shell commands,…

Large Language Models (LLMs) have exhibited strong mathematical reasoning prowess, tackling tasks ranging from basic arithmetic to advanced competition-level problems. However, frequently occurring subtle yet critical errors, such as…

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount…

Despite the large progress in supervised learning with neural networks, there are significant challenges in obtaining high-quality, large-scale and accurately labelled datasets. In such a context, how to learn in the presence of noisy…

Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations, including evaluator bias and detection failures arising from model homogeneity, which collectively undermine the robustness of risk…

When recurrent neural network transducers (RNNTs) are trained using the typical maximum likelihood criterion, the prediction network is trained only on ground truth label sequences. This leads to a mismatch during inference, known as…

Self-evolving Large Language Models (LLMs) offer a scalable path toward super-intelligence by autonomously generating, refining, and learning from their own experiences. However, existing methods for training such models still rely heavily…

Manual RTL design and optimization remains prevalent across the semiconductor industry because commercial logic and high-level synthesis tools are unable to match human designs. Our experience in industrial datapath design demonstrates that…

Large language models (LLMs) empowered by chain-of-thought reasoning have achieved impressive accuracy on complex tasks but suffer from excessive inference costs and latency when applied uniformly to all problems. We propose SABER…

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…

Implicit feedback, such as user clicks, serves as the primary data source for modern recommender systems. However, click interactions inherently contain substantial noise, including accidental clicks, clickbait-induced interactions, and…

Language models (LMs) risk inadvertently memorizing and divulging sensitive or personally identifiable information (PII) seen in training data, causing privacy concerns. Current approaches to address this issue involve costly dataset…

Through reinforcement learning (RL) with outcome correctness rewards, large reasoning models (LRMs) with scaled inference computation have demonstrated substantial success on complex reasoning tasks. However, the one-sided reward, focused…

Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains. However, this knowledge is inherently…

One year ago, we open-sourced DocETL, a declarative system for LLM-powered data processing that, as of March 2026, has 3.7K GitHub stars and users across domains (e.g., journalism, law, medicine, policy, finance, and urban planning). In…

Large Language Models (LLMs) have shown strong capabilities in document re-ranking, a key component in modern Information Retrieval (IR) systems. However, existing LLM-based approaches face notable limitations, including ranking…

Recent studies show that the reasoning capabilities of Large Language Models (LLMs) can be improved by applying Reinforcement Learning (RL) to question-answering (QA) tasks in areas such as math and coding. With a long context length, LLMs…

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Implicit feedback (e.g., clicks, dwell times, etc.) is an abundant source of data in human-interactive systems. While implicit feedback has many advantages (e.g., it is inexpensive to collect, user centric, and timely), its inherent biases…