11 papers · 1 filter
Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering Calibrator
Alhasan Mahmood, Samir Abdaljalil, Hasan Kurban
Multilingual LLM judges produce different evaluator-backbone rankings depending on the prompt language: on an eight-language Agent-as-a-Judge benchmark, the top-ranked backbone alt…
Multilingual Prompt Localization for Agent-as-a-Judge: Language and Backbone Sensitivity in Requirement-Level Evaluation
Alhasan Mahmood, Samir Abdaljalil, Hasan Kurban
Evaluation language is typically treated as a fixed English default in agentic code benchmarks, yet we show that changing the judge's language can invert backbone rankings. We loca…
IsoSci: A Benchmark of Isomorphic Cross-Domain Science Problems for Evaluating Reasoning versus Knowledge Retrieval in LLMs
Samir Abdaljalil, Erchin Serpedin, Hasan Kurban
We introduce ISOSCI, a benchmark of isomorphic cross-domain science problem pairs that separates reasoning ability from domain knowledge retrieval in LLM evaluation. Each pair shar…
Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
Samir Abdaljalil, Erchin Serpedin, Hasan Kurban
Large language models are increasingly used to answer and verify scientific claims, yet existing evaluations typically assume that a model must always produce a definitive answer.…
Halluverse-M^3: A multitask multilingual benchmark for hallucination in LLMs
Samir Abdaljalil, Parichit Sharma, Erchin Serpedin +1
Hallucinations in large language models remain a persistent challenge, particularly in multilingual and generative settings where factual consistency is difficult to maintain. Whil…
Audit-of-Understanding: Posterior-Constrained Inference for Mathematical Reasoning in Language Models
Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe +1
Large language models (LLMs) often generate reasoning traces that appear coherent but rest on unsupported assumptions, leading to hallucinated conclusions. Prior work mainly addres…