Related papers: ECLIPTICA -- A Framework for Switchable LLM Alignm…

Large Language Models (LLMs) are increasingly deployed in business-critical domains such as finance, education, healthcare, and customer support, where users expect consistent and reliable recommendations. Yet LLMs often exhibit variability…

Offline preference alignment for language models such as Direct Preference Optimization (DPO) is favored for its effectiveness and simplicity, eliminating the need for costly reinforcement learning. Various offline algorithms have been…

Finding preferences expressed in natural language is an important but challenging task. State-of-the-art(SotA) methods leverage transformer-based models such as BERT, RoBERTa, etc. and graph neural architectures such as graph attention…

Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static…

In-Context Learning (ICL) allows Large Language Models (LLMs) to adapt to new tasks with just a few examples, but their predictions often suffer from systematic biases, leading to unstable performance in classification. While calibration…

Instruction tuning is a pivotal technique for aligning large language models (LLMs) with human intentions, safety constraints, and domain-specific requirements. This survey provides a comprehensive overview of the full pipeline,…

The risk of harmful content generated by large language models (LLMs) becomes a critical concern. This paper presents a systematic study on assessing and improving LLMs' capability to perform the task of \textbf{course-correction}, \ie, the…

In real-world continual learning (CL) scenarios, tasks often exhibit intricate and unpredictable semantic shifts, posing challenges for fixed prompt management strategies which are tailored to only handle semantic shifts of uniform degree…

In recent years, continual learning with pre-training (CLPT) has received widespread interest, instead of its traditional focus of training from scratch. The use of strong pre-trained models (PTMs) can greatly facilitate knowledge transfer…

In this paper, we aim to align large language models with the ever-changing, complex, and diverse human values (e.g., social norms) across time and locations. This presents a challenge to existing alignment techniques, such as supervised…

To acquire instruction-following capabilities, large language models (LLMs) undergo instruction tuning, where they are trained on instruction-response pairs using next-token prediction (NTP). Efforts to improve instruction tuning often…

Fine-grained control over large language models (LLMs) remains a significant challenge, hindering their adaptability to diverse user needs. While Reinforcement Learning from Human Feedback (RLHF) shows promise in aligning LLMs, its reliance…

Prior research shows that large language models (LLMs) exhibit systematic extrapolation bias when forming predictions from both experimental and real-world data, and that prompt-based approaches appear limited in alleviating this bias. We…

Large Language Models (LLMs) demand significant computational resources, making it essential to enhance their capabilities without retraining from scratch. A key challenge in this domain is \textit{catastrophic forgetting} (CF), which…

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while…

Despite their impressive capabilities, multilingual large language models (MLLMs) frequently exhibit inconsistent behaviour when the prompt's language changes. While such adaptation is generally desirable, it becomes a critical failure when…

Instruction-based Large Language Models (LLMs) have proven effective in numerous few-shot or zero-shot Natural Language Processing (NLP) tasks. However, creating human-annotated instruction data is time-consuming, expensive, and often…

Large language models (LLMs) are increasingly used as reasoning modules in many applications. While they are efficient in certain tasks, LLMs often struggle to produce human-aligned solutions. Human-aligned decision making requires…

While continual visual instruction tuning (CVIT) has shown promise in adapting multimodal large language models (MLLMs), existing studies predominantly focus on models without safety alignment. This critical oversight ignores the fact that…

Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent studies demonstrate that open-sourced smaller foundational…