RT @ACM_CHIIR: Consider submitting your work to CHIIR 2026 — where HCI meets IR 🤝.📍 Seattle | 🗓️ March 22–26, 2026.📝 Full Papers due: Oct 1….

RT @readswithravi:

Link to the accepted version: Early/arxiv version:

🧐 Need IR user-interaction data but stuck on sketchy docs & privacy hurdles? Our just-accepted JASIST paper shows how #IIR scholars actually find, judge & reuse datasets, pinpoints key reuse drivers and challenges, and offers metadata + privacy frameworks to unlock those silos.

RT @AiBreakfast: The next generation of LLMs will give you the answer before you ask the question.

The first rose of spring in my front yard :-)

RT @DeepPsycho_HQ: 10 Brutal Truths That Will Slap You Into Action:. 1.

4/4 This study provides new insights into how personality-driven biases emerge in automated systems and offers a foundation for designing more transparent and accountable LLM applications. Check out our work here: #LLM #Bias #InformationRetrieval #AI.

3/4 and debiasing efficacy. The findings reveal that while certain personality traits enhance mitigation strategies, others exacerbate biases, which emphasizes the need for personality-aware bias interventions to ensure fairness and reliability in AI-assisted decision-making.

2/4 Through a structured experimental framework and the introduction of a new BiasEval dataset, we identify six prevalent biases in LLM decision-making, showing that personality traits such as Agreeableness and Conscientiousness significantly impact both bias manifestation.

1/4 🚀 New Research on LLM Personality and Cognitive Bias 🤖 Our latest study with @jiangenhe systematically investigates how personality traits influence cognitive biases in LLMs and assesses the effectiveness of bias mitigation strategies across different architectures.

RT @acmtois: "Decoy Effect in Search Interaction: Understanding User Behavior and Measuring System Vulnerability" by Nuo Chen, Jiqun Liu, H….

RT @year_progress: 2024 is 100% complete.

RT @tetsuyasakai: Accepted by ACM TOIS:. Decoy Effect In Search Interaction: Understanding User Behavior and Measuring System Vulnerability….

How do Interactive IR researchers make the most of shared data? Our interview study uncovers their strategies and challenges in data reuse and reusability evaluation, revealing how it can fuel innovation and collaboration in IR. #DataReuse #IR #OpenScience

Ever wondered if AI can be tricked like humans? 🤔 Our study dives into cognitive biases in LLMs, and shows that while advanced models outperform humans in assessing medical information, they’re MORE vulnerable to decoy effects. #AI #Bias #Misinformation

The tutorial will cover theoretical foundations, user study design, and actionable strategies for developing bias-aware Conversational and GenIR systems. Please join our slack channel @ACMSIGIR for more material and discussions: sigir24-searchunderuncertainty-tutorial @claclarke.

We invite you to our @ACMSIGIR_AP tutorial "Evaluating Cognitive Biases in Conversational and Generative IIR" w/@leifos on Dec 9! Join us to explore the role of cognitive biases in generative #InformationRetrieval. Essential for researchers committed to advancing bias-aware IR.

How do older adults understand and manage biases in recommender system? Our latest study @JASIST uncovers their unique strategies for interacting with personalized content and emphasizes the importance of designing systems that are inclusive to all users:

RT @JASIST: Understanding users' dynamic perceptions of search gain and cost in sessions: An expectation confirmation model.Ben Wang, Jiqun….