Related papers: Self-Guided Function Calling in Large Language Mod…
Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by prompting intermediate steps, improving accuracy and robustness in arithmetic, logic, and commonsense tasks. However, this benefit comes with high computational…
This paper systematically addresses the challenges of rule retrieval, a crucial yet underexplored area. Vanilla retrieval methods using sparse or dense retrievers to directly search for relevant rules to support downstream reasoning, often…
Large Language Models (LLMs) face persistent and evolving trustworthiness issues, motivating developers to seek automated and flexible repair methods that enable convenient deployment across diverse scenarios. Existing repair methods like…
Autoregressive Large Language Models (AR-LLMs) are widely used in software engineering (SE) but face limitations in processing code structure information and suffer from high inference latency. Diffusion LLMs (DLLMs) offer a promising…
Augmenting large language models (LLMs) with external tools has emerged as a promising approach to extend their utility, enabling them to solve practical tasks. Previous methods manually parse tool documentation and create in-context…
Function calling is a complex task with widespread applications in domains such as information retrieval, software engineering and automation. For example, a query to book the shortest flight from New York to London on January 15 requires…
Large language models (LLMs) remain prone to factual inaccuracies and computational errors, including hallucinations and mistakes in mathematical reasoning. Recent work augmented LLMs with tools to mitigate these shortcomings, but often…
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts. However, prompting often leads models to make predictions with lower accuracy compared to finetuning a model…
Recent years have seen a rapid surge in research leveraging Large Language Models (LLMs) for recommendation. These methods typically employ supervised fine-tuning (SFT) to adapt LLMs to recommendation scenarios, and utilize beam search…
Recent advancements in tool learning have enabled large language models (LLMs) to integrate external tools, enhancing their task performance by expanding their knowledge boundaries. However, relying on tools often introduces tradeoffs…
Test-time scaling has been widely adopted to enhance the capabilities of Large Language Model (LLM) agents in software engineering (SWE) tasks. However, the standard approach of repeatedly sampling trajectories from scratch is…
Large language models (LLMs) hold promise for generating plans for complex tasks, but their effectiveness is limited by sequential execution, lack of control flow models, and difficulties in skill retrieval. Addressing these issues is…
Due to the textual and repetitive nature of many Requirements Engineering (RE) artefacts, Large Language Models (LLMs) have proven useful to automate their generation and processing. In this paper, we discuss a possible approach for…
The paper investigates using a Large Language Model (LLM) to automatically perform web software tasks using click, scroll, and text input operations. Previous approaches, such as reinforcement learning (RL) or imitation learning, are…
Conventional mechanical design follows an iterative process in which initial concepts are refined through cycles of expert assessment and resource-intensive Finite Element Method (FEM) analysis to meet performance goals. While machine…
Although LLM-based conversational agents demonstrate strong fluency and coherence, they still produce undesirable behaviors (errors) that are challenging to prevent from reaching users during deployment. Recent research leverages large…
Continual Learning (CL) aims at incrementally learning new tasks without forgetting the knowledge acquired from old ones. Experience Replay (ER) is a simple and effective rehearsal-based strategy, which optimizes the model with current…
Incorporating collaborative information (CI) effectively is crucial for leveraging LLMs in recommendation tasks. Existing approaches often encode CI using soft tokens or abstract identifiers, which introduces a semantic misalignment with…
This paper investigates how Large Language Models (LLMs) represent non-English tokens -- a question that remains underexplored despite recent progress. We propose a lightweight intervention method using representation steering, where a…
In this work, we propose a simple method that applies a large language model (LLM) to large-scale retrieval in zero-shot scenarios. Our method, the Language language model as Retriever (LameR), is built upon no other neural models but an…