5 papers
Analyzing the Narration Gap in LLM-Solver Loops
Zunchen Huang, Songgaojun Deng
Formal tools such as SAT and SMT solvers are increasingly embedded in language model reasoning pipelines when a safety or security critical question can be formulated in logic. Unl…
AdversaRiskQA: An Adversarial Factuality Benchmark for High-Risk Domains
Adam Szelestey, Sofie van Engelen, Tianhao Huang +3
Hallucination in large language models (LLMs) remains an acute concern, contributing to the spread of misinformation and diminished public trust, particularly in high-risk domains.…
Mitigating Social Desirability Bias in Random Silicon Sampling
Sashank Chapala, Maksym Mironov, Songgaojun Deng
Large Language Models (LLMs) are increasingly used to simulate population responses, a method known as ``Silicon Sampling''. However, responses to socially sensitive questions freq…
Beyond Natural Language Plans: Structure-Aware Planning for Query-Focused Table Summarization
Weijia Zhang, Songgaojun Deng, Evangelos Kanoulas
Query-focused table summarization requires complex reasoning, often approached through step-by-step natural language (NL) plans. However, NL plans are inherently ambiguous and lack…
Learning Latent Spaces for Domain Generalization in Time Series Forecasting
Songgaojun Deng, Maarten de Rijke
Time series forecasting is vital in many real-world applications, yet developing models that generalize well on unseen relevant domains -- such as forecasting web traffic data on n…