Related papers: Monotonic Paraphrasing Improves Generalization of …
Large language models (LLMs) showcase increasingly impressive English benchmark scores, however their performance profiles remain inconsistent across multilingual settings. To address this gap, we introduce PolyPrompt, a novel,…
Prompt compression condenses contexts while maintaining their informativeness for different usage scenarios. It not only shortens the inference time and reduces computational costs during the usage of large language models, but also lowers…
In recent years, the growing interest in Large Language Models (LLMs) has significantly advanced prompt engineering, transitioning from manual design to model-based optimization. Prompts for LLMs generally comprise two components: the…
Large language models (LLMs), such as GPT series and Llama series have demonstrated strong capabilities in natural language processing, contextual understanding, and text generation. In recent years, researchers are trying to enhance the…
While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a…
When adapting large language models (LLMs) to a specific downstream task, two primary approaches are commonly employed: (1) prompt engineering, often with in-context few-shot learning, leveraging the model's inherent generalization…
Prompting is used to guide or steer a language model in generating an appropriate response that is consistent with the desired outcome. Chaining is a strategy used to decompose complex tasks into smaller, manageable components. In this…
Large Language Models (LLMs) have been shown to be able to learn different tasks without explicit finetuning when given many input-output examples / demonstrations through In-Context Learning (ICL). Increasing the number of examples, called…
Decoding with autoregressive large language models (LLMs) traditionally occurs sequentially, generating one token after another. An emerging line of work explored parallel decoding by identifying and simultaneously generating semantically…
Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize…
Recent advancements in large language models (LLMs) have demonstrated remarkable reasoning capabilities. However, single-shot inference often yields unreliable results for complex reasoning tasks, leading researchers to explore multiple…
Multimodal Large Language Models (MLLMs) demonstrate remarkable performance across a wide range of domains, with increasing emphasis on enhancing their zero-shot generalization capabilities for unseen tasks across various modalities.…
Large Language Models (LLMs) are highly vulnerable to input perturbations, as even a small prompt change may result in a substantially different output. Existing methods to enhance LLM robustness are primarily focused on perturbed data…
Prompt learning approaches have made waves in natural language processing by inducing better few-shot performance while they still follow a parametric-based learning paradigm; the oblivion and rote memorization problems in learning may…
Large Language Models (LLMs) have demonstrated remarkable proficiency across diverse tasks, exhibiting emergent properties such as semantic prompt comprehension, In-Context Learning (ICL), and Chain-of-Thought (CoT) reasoning. Despite their…
Prompting a language model (LM) is an increasingly important research topic for better utilization of large language models (LLMs). While simple prompting is effective for single-step questions, it fails to activate the correct knowledge…
How can we extend a pre-trained model to many language understanding tasks, without labeled or additional unlabeled data? Pre-trained language models (PLMs) have been effective for a wide range of NLP tasks. However, existing approaches…
Utilizing large language models (LLMs) for zero-shot document ranking is done in one of two ways: (1) prompt-based re-ranking methods, which require no further training but are only feasible for re-ranking a handful of candidate documents…
Recent advances in prompt optimization have notably enhanced the performance of pre-trained language models (PLMs) on downstream tasks. However, the potential of optimized prompts on domain generalization has been under-explored. To explore…
Large language models (LLMs) are increasingly utilized in various complex reasoning tasks due to their excellent instruction following capability. However, the model's performance is highly dependent on the open-ended characteristics of the…