Related papers: ZEBRA: Leveraging Model-Behavioral Knowledge for Z…
Reward models (RMs) are a core component in the post-training of large language models (LLMs), serving as proxies for human preference evaluation and guiding model alignment. However, training reliable RMs under limited resources remains…
Bargaining is often regarded as a logical arena rather than an art or a matter of intuition, yet Large Language Models (LLMs) still struggle to navigate it due to limited strategic depth and difficulty adapting to complex human factors.…
Response selection plays a vital role in building retrieval-based conversation systems. Despite that response selection is naturally a learning-to-rank problem, most prior works take a point-wise view and train binary classifiers for this…
Recent advances in artificial intelligence, including the development of highly sophisticated large language models (LLM), have proven beneficial in many real-world applications. However, evidence of inherent bias encoded in these LLMs has…
Preference-based reinforcement learning (PbRL) is a suitable approach for style adaptation of pre-trained robotic behavior: adapting the robot's policy to follow human user preferences while still being able to perform the original task.…
Data annotation refers to the labeling or tagging of textual data with relevant information. A large body of works have reported positive results on leveraging LLMs as an alternative to human annotators. However, existing studies focus on…
Reinforcement learning is a general method for learning in sequential settings, but it can often be difficult to specify a good reward function when the task is complex. In these cases, preference feedback or expert demonstrations can be…
In the field of Natural Language Processing (NLP), Named Entity Recognition (NER) is recognized as a critical technology, employed across a wide array of applications. Traditional methodologies for annotating datasets for NER models are…
Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed…
Large-scale supervised data is essential for training modern ranking models, but obtaining high-quality human annotations is costly. Click data has been widely used as a low-cost alternative, and with recent advances in large language…
Instruction fine-tuning stands as a crucial advancement in leveraging large language models (LLMs) for enhanced task performance. However, the annotation of instruction datasets has traditionally been expensive and laborious, often relying…
Active learning strategically selects informative unlabeled data points and queries their ground truth labels for model training. The prevailing assumption underlying this machine learning paradigm is that acquiring these ground truth…
Preference optimization is a standard approach to fine-tuning large language models to align with human preferences. The quantity, diversity, and representativeness of the preference dataset are critical to the effectiveness of preference…
This paper explores the use of large language models (LLMs) for annotating document utility in training retrieval and retrieval-augmented generation (RAG) systems, aiming to reduce dependence on costly human annotations. We address the gap…
Although LLMs have achieved significant success, their reliance on large volumes of human-annotated data has limited their potential for further scaling. In this situation, utilizing self-generated synthetic data has become crucial for…
One of the key technologies for the success of Large Language Models (LLMs) is preference alignment. However, a notable side effect of preference alignment is poor calibration: while the pre-trained models are typically well-calibrated,…
Social behavior is crucial for survival in many animal species, and a heavily investigated research subject. Current analysis methods generally rely on measuring animal interaction time or annotating predefined behaviors. However, these…
We propose probe-based data attribution, a method that traces behavioral changes in post-trained language models to responsible training datapoints. By computing activation-difference vectors for both test prompts and preference pairs and…
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…
Rerankers play a pivotal role in refining retrieval results for Retrieval-Augmented Generation. However, current reranking models are typically optimized on static human annotated relevance labels in isolation, decoupled from the downstream…