Related papers: FT2Ra: A Fine-Tuning-Inspired Approach to Retrieva…

Large Language Models (LLMs) show strong reasoning abilities, often amplified by Chain-of-Thought (CoT) prompting and reinforcement learning (RL). Although RL algorithms can substantially improve reasoning, they struggle to expand reasoning…

We propose Confidence-guided Refinement Reasoning (C2R), a novel training-free framework applicable to question-answering (QA) tasks across text, image, and video domains. C2R strategically constructs and refines sub-questions and their…

Developing efficient GPU kernels is essential for scaling modern AI systems, yet it remains a complex task due to intricate hardware architectures and the need for specialized optimization expertise. Although Large Language Models (LLMs)…

Foundation models excel across diverse tasks, but adapting them to specialized applications often requires fine-tuning, an approach that is memory and compute-intensive. Parameter-efficient fine-tuning (PEFT) methods mitigate this by…

Chain-of-thought (CoT) prompting has become central to mathematical reasoning in large language models, yet models remain brittle to early errors: a single arithmetic slip or unjustified inference typically propagates uncorrected to an…

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieved from a knowledge base. However, its effectiveness is fundamentally constrained by the reliability of both the retriever…

Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that…

Scaling data and model size has been proven effective for boosting the performance of large language models. In addition to training-time scaling, recent studies have revealed that increasing test-time computational resources can further…

Large Language Models (LLMs) have proven highly effective in automating software engineering tasks, bridging natural language and code semantics to achieve notable results in code generation and summarization. However, their scale incurs…

Recent advancements highlight the success of instruction tuning with large language models (LLMs) utilizing Chain-of-Thought (CoT) data for mathematical reasoning tasks. Despite the fine-tuned LLMs, challenges persist, such as incorrect,…

Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate the generation modules…

Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of…

Large Language Models (LLMs) are increasingly adopted for complex scientific text generation tasks, yet they often suffer from limitations in accuracy, consistency, and hallucination control. This thesis introduces a Parameter-Efficient…

Retrieval Augmented Generation (RAG) is a common method for integrating external knowledge into pretrained Large Language Models (LLMs) to enhance accuracy and relevancy in question answering (QA) tasks. However, prompt engineering and…

Test-time finetuning (TTFT) is a rapidly evolving paradigm that adapts a language model to each prompt by retrieving related sequences, updating the model on them, and then evaluating the prompt. However, TTFT is only practical if it is…

Advancements in Large Language Models (LLMs) have extended their input context length, yet they still struggle with retrieval and reasoning in long-context inputs. Existing methods propose to utilize the prompt strategy and retrieval head…

Large language models (LLMs) have exhibited impressive reasoning abilities on a wide range of complex tasks. However, enhancing these capabilities through post-training remains resource intensive, particularly in terms of data and…

Retrieving relevant evidence from visually rich documents such as textbooks, technical reports, and manuals is challenging due to long context, complex layouts, and weak lexical overlap between user questions and supporting pages. We…

Column Type Annotation (CTA) is a fundamental step towards enabling schema alignment and semantic understanding of tabular data. Existing encoder-only language models achieve high accuracy when fine-tuned on labeled columns, but their…

Medical question-answering (QA) systems can benefit from advances in large language models (LLMs), but directly applying LLMs to the clinical domain poses challenges such as maintaining factual accuracy and avoiding hallucinations. In this…