Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options
Obed Junias, Maria Leonor Pacheco
Large language models often fail when answer options require combining atomic judgments under explicit logical operators, even when they judge the individual atoms correctly. We st…
cs.CL2026
LOGICAL-COMMONSENSEQA: A Benchmark for Logical Commonsense Reasoning
Obed Junias, Maria Leonor Pacheco
Commonsense reasoning often involves evaluating multiple plausible interpretations rather than selecting a single atomic answer, yet most benchmarks rely on single-label evaluation…
cs.CL2025
Assessing Algorithmic Bias in Language-Based Depression Detection: A Comparison of DNN and LLM Approaches
Obed Junias, Prajakta Kini, Theodora Chaspari
This paper investigates algorithmic bias in language-based models for automated depression detection, focusing on socio-demographic disparities related to gender and race/ethnicity…