3 papers
cs.LG2026
Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency
Victoria Lin, Xinnuo Xu, Rachel Lawrence +4
Despite their strong performance on reasoning benchmarks, large language models (LLMs) have proven brittle when presented with counterfactual questions, suggesting weaknesses in th…
cs.CL2025
RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation
Xinnuo Xu, Rachel Lawrence, Kshitij Dubey +7
Recent Large Language Models (LLMs) have reported high accuracy on reasoning benchmarks. However, it is still unclear whether the observed results arise from true reasoning or from…
cs.CL2025
DeduCE: Deductive Consistency as a Framework to Evaluate LLM Reasoning
Atharva Pandey, Kshitij Dubey, Rahul Sharma +1
Despite great performance on Olympiad-level reasoning problems, frontier large language models can still struggle on high school math when presented with novel problems outside sta…