RL-based techniques can be employed to search for prompts that, when fed into a target language model, maximize a set of user-specified reward ***, in many target applications, the natural reward functions are in tens...
详细信息
Leading models for the text-to-SQL task heavily rely on proprietary Large language Models (LLMs), posing concerns over data *** the performance gap between small open-source models and large proprietary models is cruc...
详细信息
Gender-fair language, an evolving German linguistic variation, fosters inclusion by addressing all genders or using neutral forms. Nevertheless, there is a significant lack of resources to assess the impact of this li...
详细信息
The advent of large language models (LLMs) like GPT-4 has catalyzed the exploration of multi-task learning (MTL), in which a single model demonstrates proficiency across diverse tasks. Task arithmetic has emerged as a...
详细信息
Having been trained on massive pretraining data, large language models have shown excellent performance on many knowledge-intensive tasks. However, pretraining data tends to contain misleading and even conflicting inf...
详细信息
Recent advances in machine learning have significantly impacted the field of information extraction, with language Models (LMs) playing a pivotal role in extracting structured information from unstructured text. Prior...
详细信息
Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) even if not being trained explicitly for translation. Yet, they still struggle with translating l...
详细信息
Large language Model (LLM) has demonstrated significant ability in various naturallanguageprocessing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on...
详细信息
ISBN:
(纸本)9798891760608
Large language Model (LLM) has demonstrated significant ability in various naturallanguageprocessing tasks. However, their effectiveness is highly dependent on the phrasing of the task prompt, leading to research on automatic prompt optimization using labeled task data. We reveal that these prompt optimization techniques are vulnerable to distribution shifts such as subpopulation shifts, which are common for LLMs in real-world scenarios such as customer reviews analysis. In this light, we propose a new problem of robust prompt optimization for LLMs against distribution shifts, which requires the prompt optimized over the labeled source group can simultaneously generalize to an unlabeled target group. To solve this problem, we propose Generalized Prompt Optimization framework, which incorporates the unlabeled data from the target group into prompt optimization. Extensive experimental results demonstrate the effectiveness of the proposed framework with significant performance improvement on the target group and comparable performance on the source group.
Large language Models (LLMs) have succeeded considerably in In-Context-Learning (ICL) based summarization. However, saliency is subject to the users' specific preference histories. Hence, we need reliable In-Conte...
详细信息
The high power consumption and latency-sensitive deployments of large language models (LLMs) have motivated efficiency techniques like quantization and *** sparsity, where the sparsity pattern is input-dependent, is c...
详细信息
暂无评论