Given the increasingly prominent role NLP models (will) play in our lives, it is important for human expectations of model behavior to align with actual model behavior. Using Natural Language Inference (NLI) as a case study, we investigate the extent to which human-generated explanations of models' inference decisions align with how models actually make these decisions. More specifically, we define three alignment metrics that quantify how well natural language explanations align with model sensitivity to input words, as measured by integrated gradients. Then, we evaluate eight different models (the base and large versions of BERT, RoBERTa and ELECTRA, as well as anRNN and bag-of-words model), and find that the BERT-base model has the highest alignment with human-generated explanations, for all alignment metrics. Focusing in on transformers, we find that the base versions tend to have higher alignment with human-generated explanations than their larger counterparts, suggesting that increasing the number of model parameters leads, in some cases, to worse alignment with human explanations. Finally, we find that a model's alignment with human explanations is not predicted by the model's accuracy, suggesting that accuracy and alignment are complementary ways to evaluate models.
Annotating large collections of textual data can be time consuming and expensive. That is why the ability to train models with limited annotation budgets is of great importance. In this context, it has been shown that under tight annotation budgets the choice of data representation is key. The goal of this paper is to better understand why this is so. With this goal in mind, we propose a metric that measures the extent to which a given representation is structurally aligned with a task. We conduct experiments on several text classification datasets testing a variety of models and representatio…
Human fixation patterns have been shown to correlate strongly with Transformer-based attention. Those correlation analyses are usually carried out without taking into account individual differences between participants and are mostly done on monolingual datasets making it difficult to generalise findings. In this paper, we analyse eye-tracking data from speakers of 13 different languages reading both in their native language (L1) and in English as language learners (L2). We find considerable differences between languages but also that individual reading behaviour such as skipping rate, total r…
Forgetting Our Way to Shared Meaning: Effects of Forgetting on Conceptual Alignment in a Non-Partnership Coordination Game
Institute for Complex Social Dynamics, Carnegie Mellon University（复杂社会动态研究所，卡内基梅隆大学）；Department of Computer Science, Carleton University（计算机科学系，卡尔顿大学）；Department of Cognitive Science, Carleton University（认知科学系，卡尔顿大学）
Impact of Decoding Methods on Human Alignment of Conversational LLMs
Birla Institute of Technology and Science, Pilani（比拉理工与科学学院（皮拉尼））；National University of Singapore（新加坡国立大学）；NUS Center for Trusted Internet and Community（新加坡国立大学可信互联网与社区中心）；Department of Communications and New Media, National University of Singapore（新加坡国立大学传播与新媒体系）
本文研究了Beam Search、Top K Sampling和Nucleus Sampling等解码方法对LLM与人类对话对齐的影响，提出了内容、风格和心理测量导向的新衡量标准，发现较少beam数和较低P值对齐效果更好，且任务导向与开放式数据集表现不同。
Cal-DPO: Calibrated Direct Preference Optimization for Language Model Alignment
Artificial Intelligence Research Laboratory, Pennsylvania State University（宾夕法尼亚州立大学人工智能研究实验室）；University of Chinese Academy of Sciences（中国科学院大学）；Tencent AI Lab（腾讯人工智能实验室）
IIMedGPT: Promoting Large Language Model Capabilities of Medical Tasks by Efficient Human Preference Alignment
University of Science and Technology of China（中国科学技术大学）；School of Artificial Intelligence and Big Data, Hefei University（合肥大学人工智能与大数据学院）；Anhui University of Science and Technology（安徽理工大学）
University of Charleston（查尔斯顿大学）；Apple Inc.（苹果公司）；Cerence B. V.（赛轮思公司）
Efficient textual data distributions (TDD) alignment and generation are open research problems in textual analytics and NLP. It is presently difficult to parsimoniously and methodologically confirm that two or more natural language datasets belong to similar distributions, and to identify the extent to which textual data possess alignment. This study focuses on addressing a segment of the broader problem described above by applying multiple supervised and unsupervised machine learning (ML) methods to explore the behavior of TDD by (i) topical alignment, and (ii) by sentiment alignment. Further…
BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
Graduate School of AI, KAIST（韩国科学技术院人工智能研究生院）；Samsung Advanced Institute of Technology（三星先进技术研究院）；Department of Electrical and Computer Engineering, UBC（不列颠哥伦比亚大学电气与计算机工程系）
