3 papers
cs.CL2026
Knowing the Form, Not the Function: Automatically Auditing Answer--Authority Decoupling in Legal Benchmarks
Hsien-Jyh Liao
Legal benchmarks typically score final answers even when models also state legal authority. We test whether answer correctness can serve as a proxy for authority grounding. Under o…
cs.AI2026
Intrinsic Stability Limits of Autoregressive Reasoning: Structural Consequences for Long-Horizon Execution
Hsien-Jyh Liao
Large language models (LLMs) demonstrate remarkable reasoning capabilities, yet their performance often deteriorates sharply in long-horizon tasks, exhibiting systematic breakdown…
cs.CL2026
Enforcing Monotonic Progress in Legal Cross-Examination: Preventing Long-Horizon Stagnation in LLM-Based Inquiry
Hsien-Jyh Liao
Large language models (LLMs) exhibit impressive linguistic fluency but struggle to reliably complete long-horizon tasks under explicit procedural constraints. In legal cross-examin…