Related papers: Self-Constructed Context Decompilation with Fined-…

Federated learning (FL) is a promising paradigm to enable collaborative model training with decentralized data. However, the training process of Large Language Models (LLMs) generally incurs the update of significant parameters, which…

Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing methods attempt to restore safety by incorporating…

When performing tasks like automatic speech recognition or spoken language understanding for a given utterance, access to preceding text or audio provides contextual information can improve performance. Considering the recent advances in…

Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised adaptation (UA) for fine-grained classification with VLMs…

Code completion aims at speeding up code writing by recommending to developers the next tokens they are likely to type. Deep Learning (DL) models pushed the boundaries of code completion by redefining what these coding assistants can do: We…

Large Language Model (LLM)-based agents (e.g., OpenClaw) increasingly rely on reusable skill libraries to solve artifact-rich tasks such as document-centric workflows and data-intensive analysis. As these libraries grow, a few works have…

In-context learning (ICL) is an important yet not fully understood ability of pre-trained large language models (LLMs). It can greatly enhance task performance using a few examples, termed demonstrations, without fine-tuning. Although…

In this paper, we present a semi-supervised fine-tuning approach designed to improve the performance of pre-trained foundation models on downstream tasks with limited labeled data. By leveraging content-style decomposition within an…

Large language models (LLMs) have achieved substantial progress in processing long contexts but still struggle with long-context reasoning. Existing approaches typically involve fine-tuning LLMs with synthetic data, which depends on…

The effective alignment of Large Language Models (LLMs) with precise instructions is essential for their application in diverse real-world scenarios. Current methods focus on enhancing the diversity and complexity of training and evaluation…

Refinement transforms an abstract system model into a concrete, executable program, such that properties established for the abstract model carry over to the concrete implementation. Refinement has been used successfully in the development…

We present a method for rewriting an input sentence to match specific values of nontrivial linguistic features, such as dependency depth. In contrast to earlier work, our method uses in-context learning rather than finetuning, making it…

Large language models (LLMs) have achieved notable success in code generation. However, they still frequently produce uncompilable output because their next-token inference procedure does not model formal aspects of code. Although…

Large language model (LLM)-based debugging systems can generate failure explanations, but these explanations may be incomplete or incorrect. Misleading explanations are harmful for downstream tasks (e.g., bug triage, bug fixing). We…

Recent advancements in Large Language Models (LLMs) have significantly improved reasoning capabilities, with in-context learning (ICL) emerging as a key technique for adaptation without retraining. While previous works have focused on…

Large Language Models (LLMs) have the unique capability to understand and generate human-like text from input queries. When fine-tuned, these models show enhanced performance on domain-specific queries. OpenAI highlights the process of…

With the rapid development of large language models (LLMs), an increasing number of applications leverage cloud-based LLM APIs to reduce usage costs. However, since cloud-based models' parameters and gradients are agnostic, users have to…

Assembly code analysis and comprehension play critical roles in applications like reverse engineering, yet they face substantial challenges due to low information density and a lack of explicit syntactic structures. While traditional masked…

Emotion-Cause Pair Extraction (ECPE) involves extracting clause pairs representing emotions and their causes in a document. Existing methods tend to overfit spurious correlations, such as positional bias in existing benchmark datasets,…

Large language models (LLMs) often seamlessly adapt to new tasks through in-context learning (ICL) or supervised fine-tuning (SFT). However, ICL is inefficient when handling many demonstrations, and SFT incurs training overhead while…