collaborators
Showing cs.CLShow all

8 papers · 1 filter

cs.CL2026

Compliance versus Sensibility: On the Reasoning Controllability in Large Language Models

Xingwei Tan, Marco Valentino, Mahmud Elahi Akhter +3

Large Language Models (LLMs) are known to acquire reasoning capabilities through shared inference patterns in pre-training data, which are further elicited via Chain-of-Thought (Co…

cs.CL2026

Where does output diversity collapse in post-training?

Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras

Post-trained language models produce less varied outputs than their base counterparts. This output diversity collapse undermines inference-time scaling methods that rely on varied…

cs.CL2026

Fundamental Reasoning Paradigms Induce Out-of-Domain Generalization in Language Models

Mingzi Cao, Xingwei Tan, Mahmud Elahi Akhter +4

Deduction, induction, and abduction are fundamental reasoning paradigms, core for human logical thinking. Although improving Large Language Model (LLM) reasoning has attracted sign…

cs.CL2026

No Shortcuts to Culture: Indonesian Multi-hop Question Answering for Complex Cultural Understanding

Vynska Amalia Permadi, Xingwei Tan, Nafise Sadat Moosavi +1

Understanding culture requires reasoning across context, tradition, and implicit social knowledge, far beyond recalling isolated facts. Yet most culturally focused question answeri…

cs.CL2026

An Empirical Study on Preference Tuning Generalization and Diversity Under Domain Shift

Constantinos Karouzos, Xingwei Tan, Nikolaos Aletras

Preference tuning aligns base language models to human judgments of quality, helpfulness, or safety by optimizing over explicit preference signals rather than likelihood alone. Pri…

cs.CL2026

Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?

Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao +1

Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and s…