Related papers: DecompressionLM: Deterministic, Diagnostic, and Ze…

Large Language Models (LLMs) apply uniform computation to all tokens, despite language exhibiting highly non-uniform information density. This token-uniform regime wastes capacity on locally predictable spans while under-allocating…

Large Language Models (LLMs) are capable of performing zero-shot closed-book question answering tasks, based on their internal knowledge stored in parameters during pre-training. However, such internalized knowledge might be insufficient…

In-context learning has established itself as an important learning paradigm for Large Language Models (LLMs). In this paper, we demonstrate that LLMs can learn encoding keys in-context and perform analysis directly on encoded…

Few-shot prompting is a surprisingly powerful way to use Large Language Models (LLMs) to solve various tasks. However, this approach struggles as the task complexity increases or when the individual reasoning steps of the task themselves…

We present DetToolChain, a novel prompting paradigm, to unleash the zero-shot object detection ability of multimodal large language models (MLLMs), such as GPT-4V and Gemini. Our approach consists of a detection prompting toolkit inspired…

While Large Language Models (LLMs) excel in zero-shot Question Answering (QA), they tend to expose biases in their internal knowledge when faced with socially sensitive questions, leading to a degradation in performance. Existing zero-shot…

Knowledge-Enhanced Pre-trained Language Models (KEPLMs) are pre-trained models with relation triples injecting from knowledge graphs to improve language understanding abilities. To guarantee effective knowledge injection, previous studies…

Vision-Language Models (VLMs), such as CLIP, have significantly advanced zero-shot image recognition. However, their performance remains limited by suboptimal prompt engineering and poor adaptability to target classes. While recent methods…

This paper investigates automated skill decomposition using Large Language Models (LLMs) and proposes a rigorous, ontology-grounded evaluation framework. Our framework standardizes the pipeline from prompting and generation to normalization…

Probing the multilingual knowledge of linguistic structure in LLMs, often characterized as sequence labeling, faces challenges with maintaining output templates in current text-to-text prompting strategies. To solve this, we introduce a…

In the current digitalization era, capturing and effectively representing knowledge is crucial in most real-world scenarios. In this context, knowledge graphs represent a potent tool for retrieving and organizing a vast amount of…

Zero-shot visual question answering (ZS-VQA), an emerged critical research area, intends to answer visual questions without providing training samples. Existing research in ZS-VQA has proposed to leverage knowledge graphs or large language…

This paper studies the problem of predicting missing relationships between entities in knowledge graphs through learning their representations. Currently, the majority of existing link prediction models employ simple but intuitive scoring…

(Renyi Qu's Master's Thesis) Recent advancements in interpretable models for vision-language tasks have achieved competitive performance; however, their interpretability often suffers due to the reliance on unstructured text outputs from…

Vision-language models (VLMs), such as CLIP, have demonstrated impressive zero-shot capabilities for various downstream tasks. Their performance can be further enhanced through few-shot prompt tuning methods. However, current studies…

We explore the use of large language models (LLMs) for zero-shot semantic parsing. Semantic parsing involves mapping natural language utterances to task-specific meaning representations. Language models are generally trained on the publicly…

Large Language Models (LLMs) have been increasingly employed for query expansion. However, their generative nature often undermines performance on complex multi-hop retrieval tasks by introducing irrelevant or noisy information. To address…

Recent advances in search-augmented large reasoning models (LRMs) enable the retrieval of external knowledge to reduce hallucinations in multistep reasoning. However, their ability to operate on graph-structured data, prevalent in domains…

Large language models (LLMs) have demonstrated impressive performance in mathematical and commonsense reasoning tasks using chain-of-thought (CoT) prompting techniques. But can they perform emotional reasoning by concatenating `Let's think…

Large language models (LLMs) pre-trained on massive corpora have demonstrated impressive few-shot learning capability on many NLP tasks. Recasting an NLP task into a text-to-text generation task is a common practice so that generative LLMs…