Related papers: The Realignment Problem: When Right becomes Wrong …
Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself…
In the realm of large language models (LLMs), the ability of models to accurately follow instructions is paramount as more agents and applications leverage LLMs for construction, where the complexity of instructions are rapidly increasing.…
As large language models (LMs) advance, there is an increasing need to control their outputs to align with human values (e.g., detoxification) or desired attributes (e.g., personalization, topic). However, autoregressive models focus on…
Test-time scaling improves the reasoning performance of large language models but often results in token-inefficient overthinking, where models continue reasoning beyond what is necessary for a correct answer. Existing dynamic early-exit…
The growing awareness of safety concerns in large language models (LLMs) has sparked considerable interest in the evaluation of safety. This study investigates an under-explored issue about the evaluation of LLMs, namely the substantial…
New Large Language Models (LLMs) become available every few weeks, and modern application developers confronted with the unenviable task of having to decide if they should switch to a new model. While human evaluation remains the gold…
Health systems are rapidly deploying large language models (LLMs) that use clinical notes for clinical decision support applications. However, modern documentation practices rely heavily on templates, copy--paste shortcuts, and…
Current human-AI alignment and evaluation methods for large language models (LLMs) often rely on preference signals collected immediately after an interaction. This practice implicitly treats preference as static, even though many…
We present TRACE-CS, a novel hybrid system that combines symbolic reasoning with large language models (LLMs)to address contrastive queries in course scheduling problems. TRACE-CS leverages logic-based techniques to encode scheduling…
Large language models offer a scalable alternative to human coding for data annotation tasks, enabling the scale-up of research across data-intensive domains. While LLMs are already achieving near-human accuracy on objective annotation…
LLM implementations are failing in highly regulated industries owing to instability issues, inconsistent reasoning, hallucinations and performance variability, especially in workflows. These reliability issues restrict safe use of LLM in…
Large Language Models (LLMs) are increasingly used in empirical software engineering (ESE) to automate or assist annotation tasks such as labeling commits, issues, and qualitative artifacts. Yet the reliability and reproducibility of such…
Standard human preference-based alignment methods, such as Reinforcement Learning from Human Feedback (RLHF), are a cornerstone for aligning large language models (LLMs) with human values. However, these methods typically assume that…
Direct preference optimization methods have emerged as a computationally efficient alternative to Reinforcement Learning from Human Feedback (RLHF) for aligning Large Language Models (LLMs). Latest approaches have streamlined the alignment…
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…
Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, including the re-emergence of explicit reasoning traces under strict…
Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…
As LLMs occupy an increasingly important role in society, they are more and more confronted with questions that require them not only to draw on their general knowledge but also to align with certain human value systems. Therefore, studying…
Large language models (LLMs) are increasingly used in social science simulations. While their performance on reasoning and optimization tasks has been extensively evaluated, less attention has been paid to their ability to simulate human…
Instruction tuning has underscored the significant potential of large language models (LLMs) in producing more human controllable and effective outputs in various domains. In this work, we focus on the data selection problem for…