Related papers: Select Smarter, Not More: Prompt-Aware Evaluation …
Cross-topic automated essay scoring (AES) aims to develop a transferable model capable of effectively evaluating essays on a target topic. A significant challenge in this domain arises from the inherent discrepancies between topics. While…
Existing reinforcement learning approaches for Large Language Models typically perform policy optimization at the granularity of individual tokens or entire response sequences. However, such formulations often misalign with the natural…
When a large language model under reinforcement learning commits a wrong reasoning step early in a trajectory, standard algorithms force it to keep generating until the maximum horizon, spending compute on tokens that never receive positive…
Proximal Policy Optimization (PPO) is a popular deep policy gradient algorithm. In standard implementations, PPO regularizes policy updates with clipped probability ratios, and parameterizes policies with either continuous Gaussian…
Policy optimization for large language models often suffers from sparse reward signals in multi-step reasoning tasks. Critic-free methods like GRPO assign a single normalized outcome reward to all tokens, providing limited guidance for…
Prompting is fundamental to unlocking the full potential of large language models. To automate and enhance this process, automatic prompt optimization (APO) has been developed, demonstrating effectiveness primarily in text-only input…
Though CLIP-based prompt tuning significantly enhances pre-trained Vision-Language Models, existing research focuses on reconstructing the model architecture, e.g., additional loss calculation and meta-networks. These approaches generally…
High-Performance Computing (HPC) schedulers must balance user performance with facility-wide resource constraints. The task boils down to selecting the optimal number of nodes for a given job. We present a surrogate-assisted multi-objective…
Modern operating system schedulers employ a single, static policy, which struggles to deliver optimal performance across the diverse and dynamic workloads of contemporary systems. This "one-policy-fits-all" approach leads to significant…
Optimization is fundamental across numerous disciplines, typically following an iterative process of refining an initial solution to enhance performance. This principle is equally critical in prompt engineering, where designing effective…
Most prompt-optimization methods refine a single static template, making them ineffective in complex and dynamic user scenarios. Existing query-dependent approaches rely on unstable textual feedback or black-box reward models, providing…
The performance of Large Language Models (LLMs) depends heavily on the chosen prompting strategy, yet static approaches such as Zero-Shot, Few-Shot, or Chain-of-Thought (CoT) impose a rigid efficiency-accuracy trade-off. Highly accurate…
Generative models are increasingly powerful, yet users struggle to guide them through prompts. The generative process is difficult to control and unpredictable, and user instructions may be ambiguous or under-specified. Prior prompt…
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.…
Generative AI can now synthesize strikingly realistic images from text, yet output quality remains highly sensitive to how prompts are phrased. Direct Preference Optimization (DPO) offers a lightweight, off-policy alternative to RL for…
Despite all the benefits of automated hyperparameter optimization (HPO), most modern HPO algorithms are black-boxes themselves. This makes it difficult to understand the decision process which leads to the selected configuration, reduces…
A growing number of service providers are exploring methods to improve server utilization and reduce power consumption by co-scheduling high-priority latency-critical workloads with best-effort workloads. This practice requires strict…
Large language models (LLMs) have recently reshaped Automated Essay Scoring (AES), yet prior studies typically examine individual techniques in isolation, limiting understanding of their relative merits for English as a Second Language (L2)…
Soft prompt tuning techniques have recently gained traction as an effective strategy for the parameter-efficient tuning of pretrained language models, particularly minimizing the required adjustment of model parameters. Despite their…
Subset selection with cost constraints aims to select a subset from a ground set to maximize a monotone objective function without exceeding a given budget, which has various applications such as influence maximization and maximum coverage.…