Related papers: Toward Regulatory Compliance: A few-shot Learning …

Model training requires significantly more memory, compared with inference. Parameter efficient fine-tuning (PEFT) methods provide a means of adapting large models to downstream tasks using less memory. However, existing methods such as…

Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles…

Automated test case generation from natural language requirements remains a challenging problem in software engineering due to the ambiguity of requirements and the need to produce structured, executable test artifacts. Recent advances in…

General-purpose robots require diverse repertoires of behaviors to complete challenging tasks in real-world unstructured environments. To address this issue, goal-conditioned reinforcement learning aims to acquire policies that can reach…

Organizations need to manage numerous business processes for delivering their services and products to customers. One important consideration thereby lies in the adherence to regulations such as laws, guidelines, or industry standards. In…

Stricter data protection regulations and the poor application of privacy protection techniques have resulted in a requirement for data-driven companies to adopt new methods of analysing sensitive user data. The RAPPOR (Randomized…

In recent years, multi-task prompt tuning has garnered considerable attention for its inherent modularity and potential to enhance parameter-efficient transfer learning across diverse tasks. This paper aims to analyze and improve the…

We investigated whether large language models (LLMs) can develop data validation tests. We considered 96 conditions each for both GPT-3.5 and GPT-4, examining different prompt scenarios, learning modes, temperature settings, and roles. The…

Low-rank Adaptation (LoRA) has gained popularity as a fine-tuning approach for Large Language Models (LLMs) due to its low resource requirements and good performance. While a plethora of work has investigated improving LoRA serving…

Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples. However, in opinion summarization, large annotated datasets of reviews…

Batch prompting is a common technique in large language models (LLMs) used to process multiple inputs simultaneously, aiming to improve computational efficiency. However, as batch sizes increase, performance degradation often occurs due to…

Capturing the workload of a database and replaying this workload for a new version of the database can be an effective approach for regression testing. However, false positive errors caused by many factors such as data privacy limitations,…

Compliance testing in highly regulated domains is crucial but largely manual, requiring domain experts to translate complex regulations into executable test cases. While large language models (LLMs) show promise for automation, their…

Reinforcement Learning with Human Feedback (RLHF) has revolutionized language modeling by aligning models with human preferences. However, the RL stage, Proximal Policy Optimization (PPO), requires over 3x the memory of Supervised…

Research to improve Automated Short Answer Grading has recently focused on Large Language Models (LLMs) with prompt engineering and no- or few-shot prompting to achieve best results. This is in contrast to the fine-tuning approach, which…

Large language model (LLM) personalization aims to adapt general-purpose models to individual users. Most existing methods, however, are developed under data-rich and resource-abundant settings, often incurring privacy risks. In contrast,…

What kinds of instructional prompts are easier to follow for Language Models (LMs)? We study this question by conducting extensive empirical analysis that shed light on important features of successful instructional prompts. Specifically,…

Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which incurs significant computational overhead during the…

We address the relatively unexplored problem of hyper-parameter optimization (HPO) for federated learning (FL-HPO). We introduce Federated Loss SuRface Aggregation (FLoRA), a general FL-HPO solution framework that can address use cases of…

As reinforcement learning (RL) has achieved great success and been even adopted in safety-critical domains such as autonomous vehicles, a range of empirical studies have been conducted to improve its robustness against adversarial attacks.…