Seyed Mohssen Ghafari

Seyed Mohssen Ghafari, Ronny Kol, Juan C. Quiroz et al.

Large language models (LLMs) frequently generate responses that are lengthy and verbose, filled with redundant or unnecessary details. This diminishes clarity and user satisfaction, and it increases costs for model developers, especially with well-known proprietary models that charge based on the number of output tokens. In this paper, we introduce a novel reference-free metric for evaluating the conciseness of responses generated by LLMs. Our method quantifies non-essential content without relying on gold standard references and calculates the average of three calculations: i) a compression ratio between the original response and an LLM abstractive summary; ii) a compression ratio between the original response and an LLM extractive summary; and iii) wordremoval compression, where an LLM removes as many non-essential words as possible from the response while preserving its meaning, with the number of tokens removed indicating the conciseness score. Experimental results demonstrate that our proposed metric identifies redundancy in LLM outputs, offering a practical tool for automated evaluation of response brevity in conversational AI systems without the need for ground truth human annotations.

Seyed Mohssen Ghafari

Trust can be defined as a measure to determine which source of information is reliable and with whom we should share or from whom we should accept information. There are several applications for trust in Online Social Networks (OSNs), including social spammer detection, fake news detection, retweet behaviour detection and recommender systems. Trust prediction is the process of predicting a new trust relation between two users who are not currently connected. In applications of trust, trust relations among users need to be predicted. This process faces many challenges, such as the sparsity of user-specified trust relations, the context-awareness of trust and changes in trust values over time. In this dissertation, we analyse the state-of-the-art in pair-wise trust prediction models in OSNs. We discuss three main challenges in this domain and present novel trust prediction approaches to address them. We first focus on proposing a low-rank representation of users that incorporates users' personality traits as additional information. Then, we propose a set of context-aware trust prediction models. Finally, by considering the time-dependency of trust relations, we propose a dynamic deep trust prediction approach. We design and implement five pair-wise trust prediction approaches and evaluate them with real-world datasets collected from OSNs. The experimental results demonstrate the effectiveness of our approaches compared to other state-of-the-art pair-wise trust prediction models.

Shahpar Yakhchi, Amin Beheshti, Seyed Mohssen Ghafari et al.

Existing Recommender Systems mainly focus on exploiting users' feedback, e.g., ratings, and reviews on common items to detect similar users. Thus, they might fail when there are no common items of interest among users. We call this problem the Data Sparsity With no Feedback on Common Items (DSW-n-FCI). Personality-based recommender systems have shown a great success to identify similar users based on their personality types. However, there are only a few personality-based recommender systems in the literature which either discover personality explicitly through filling a questionnaire that is a tedious task, or neglect the impact of users' personal interests and level of knowledge, as a key factor to increase recommendations' acceptance. Differently, we identifying users' personality type implicitly with no burden on users and incorporate it along with users' personal interests and their level of knowledge. Experimental results on a real-world dataset demonstrate the effectiveness of our model, especially in DSW-n-FCI situations.