4 papers
The Alignment Bottleneck in Decomposition-Based Claim Verification
Mahmud Elahi Akhter, Federico Ruggeri, Iman Munire Bilal +2
Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these incons…
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…
Enhancing Logical Reasoning in Language Models via Symbolically-Guided Monte Carlo Process Supervision
Xingwei Tan, Marco Valentino, Mahmud Akhter +2
Large language models (LLMs) have shown strong performance in many reasoning benchmarks. However, recent studies have pointed to memorization, rather than generalization, as one of…
Temporal reasoning for timeline summarisation in social media
Jiayu Song, Mahmud Elahi Akhter, Dana Atzil Slonim +1
This paper explores whether enhancing temporal reasoning capabilities in Large Language Models (LLMs) can improve the quality of timeline summarisation, the task of summarising lon…