Zahra Abbasiantaeb

Zahra Abbasiantaeb

Auto-generated profile, based on publicly available information

Zahra Abbasiantaeb

University of Amsterdam, Amsterdam, Netherlands

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 March 2024
Verified
Conference Paper
Open access
ZAZahra Abbasiantaeb
Zahra Abbasiantaeb
YYYifei Yuan
Yifei Yuan
EKEvangelos Kanoulas
Evangelos Kanoulas
MAMohammad Aliannejadi
Mohammad Aliannejadi
CQA systems aim to create interactive search systems that effectively retrieve information by interacting with users. To replicate human-to-human conversations, existing work uses human annotators to play the roles of the questioner (student) and the answerer (teacher). Despite its effectiveness, challenges exist as human annotation is time-consuming, inconsistent, and not scalable. To address this issue and investigate the applicability of LLM in CQA simulation, we propose a simulation framework that employs zero-shot learner LLM for simulating teacher--student interactions. Our framework involves two LLMs interacting on a specific topic, with the first LLM acting as a student, generating questions to explore a given search topic. The second LLM plays the role of a teacher by answering questions and is equipped with additional information, including a text on the given topic. We implement both the student and teacher by zero-shot prompting the GPT-4 model. To assess the effectiveness of LLMs in simulating CQA interactions and understand the disparities between LLM- and human-generated conversations, we evaluate the simulated data from various perspectives. We begin by evaluating the teacher's performance through both automatic and human assessment. Next, we evaluate the performance of the student, analyzing and comparing the disparities between questions generated by the LLM and those generated by humans. Furthermore, we conduct extensive analyses to thoroughly examine the LLM performance by benchmarking state-of-the-art reading comprehension models on both datasets. Our results reveal that the teacher LLM generates lengthier answers that tend to be more accurate and complete. The student LLM generates more diverse questions, covering more aspects of a given topic.

16 June 2023
Verified
Conference Paper
Open access
Emiliana MurgiaEmiliana Murgia
Emiliana Murgia
ZAZahra Abbasiantaeb
Zahra Abbasiantaeb
MAMohammad Aliannejadi
Mohammad Aliannejadi
THTheo Huibers
Theo Huibers
MLMonica Landoni
Monica Landoni
MPMaria Soledad Pera
Maria Soledad Pera
The influence of ChatGPT and similar models on education is being increasingly discussed. With the current level of enthusiasm among users, ChatGPT is envisioned as having great potential. As generative models are unpredictable in terms of producing biased, harmful, and unsafe content, we argue that they should be comprehensively tested for more vulnerable groups, such as children, to understand what role they can play and what training and supervision are necessary. Here, we present the results of a preliminary exploration aiming to understand whether ChatGPT can adapt to support children in completing information discovery tasks in the education context. We analyze ChatGPT responses to search prompts related to the 4th grade classroom curriculum using a variety of lenses (e.g., readability and language) to identify open challenges and limitations that must be addressed by interdisciplinary communities.

10 July 2024
Verified
Conference Paper
Open access
MAMohammad Aliannejadi
Mohammad Aliannejadi
ZAZahra Abbasiantaeb
Zahra Abbasiantaeb
SCShubham Chatterjee
Shubham Chatterjee
JDJeffrey Dalton
Jeffrey Dalton
LALeif Azzopardi
Leif Azzopardi
Conversational information seeking has evolved rapidly in the last few years with the development of Large Language Models (LLMs), providing the basis for interpreting and responding in a naturalistic manner to user requests. The extended TREC Interactive Knowledge Assistance Track (iKAT) collection aims to enable researchers to test and evaluate their Conversational Search Agent (CSA). The collection contains a set of 36 personalized dialogues over 20 different topics each coupled with a Personal Text Knowledge Base (PTKB) that defines the bespoke user personas. A total of 344 turns with approximately 26,000 passages are provided as assessments on relevance, as well as additional assessments on generated responses over four key dimensions: relevance, completeness, groundedness, and naturalness. The collection challenges CSAs to efficiently navigate diverse personal contexts, elicit pertinent persona information, and employ context for relevant conversations. The integration of a PTKB and the emphasis on decisional search tasks contribute to the uniqueness of this test collection, making it an essential benchmark for advancing research in conversational and interactive knowledge assistants.

13 July 2025
Verified
Conference Paper
Open access
ZAZahra Abbasiantaeb
Zahra Abbasiantaeb
SLSimon Lupart
Simon Lupart
LALeif Azzopardi
Leif Azzopardi
JDJeffrey Dalton
Jeffrey Dalton
MAMohammad Aliannejadi
Mohammad Aliannejadi

3 April 2025
Verified
Book Chapter
Closed access
PDF file
ZAZahra Abbasiantaeb
Zahra Abbasiantaeb
CMChuan Meng
Chuan Meng
LALeif Azzopardi
Leif Azzopardi
MAMohammad Aliannejadi
Mohammad Aliannejadi