Related papers: Targeting Misalignment: A Conflict-Aware Framework…
Chain-of-thought explanations are widely used to inspect the decision process of large language models (LLMs) and to evaluate the trustworthiness of model outputs, making them important for effective collaboration between LLMs and humans.…
The demand for regulating potentially risky behaviors of large language models (LLMs) has ignited research on alignment methods. Since LLM alignment heavily relies on reward models for optimization or evaluation, neglecting the quality of…
Direct alignment methods are increasingly used to align large language models (LLMs) with human preferences. However, many real-world alignment problems involve multiple conflicting objectives, where naive aggregation of preferences can…
Fine-tuning large language models (LLMs) based on human preferences, commonly achieved through reinforcement learning from human feedback (RLHF), has been effective in improving their performance. However, maintaining LLM safety throughout…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…
Language models often misinterpret human intentions due to their handling of ambiguity, a limitation well-recognized in NLP research. While morally clear scenarios are more discernible to LLMs, greater difficulty is encountered in morally…
The rise of large language models (LLMs) has significantly influenced the quality of information in decision-making systems, leading to the prevalence of AI-generated content and challenges in detecting misinformation and managing…
Large Language Model (LLM) alignment conventionally relies on supervised fine-tuning or reinforcement learning based alignment frameworks. These methods typically require labeled or preference datasets and involve updating model weights to…
In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve into agentic systems capable of autonomous tool invocation and…
Recent advancements in Artificial Intelligence, particularly in Large Language Models (LLMs), have transformed natural language processing by improving generative capabilities. However, detecting biases embedded within these models remains…
While large language models demonstrate remarkable capabilities at task-specific applications through fine-tuning, extending these benefits across diverse languages is essential for broad accessibility. However, effective cross-lingual…
Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human values. However, noisy preferences in human feedback can lead to reward misgeneralization - a phenomenon where reward models learn spurious…
Misalignment in Large Language Models (LLMs) refers to the failure to simultaneously satisfy safety, value, and cultural dimensions, leading to behaviors that diverge from human expectations in real-world settings where these dimensions…
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment between visual and textual representations is not fully…
Large Language Models (LLMs) are being increasingly integrated into software systems, offering powerful capabilities but also raising concerns about fairness. Existing fairness benchmarks, however, focus on stereotype-specific associations,…
We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from…
Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…
Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on…
Misalignment in Large Language Models (LLMs) arises when model behavior diverges from human expectations and fails to simultaneously satisfy safety, value, and cultural dimensions, which must co-occur in real-world settings to solve a…
Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…