DLawBench: Evaluating LLMs Through Multi-Turn Legal Consultation
Quick Answer
DLawBench introduces a benchmark for evaluating LLMs in legal consultations, revealing that even the best model, GPT-5.5, scores only 0.562 in realistic scenarios.
Quick Take
DLawBench introduces a benchmark for evaluating LLMs in legal consultations, revealing that even the best model, GPT-5.5, scores only 0.562 in realistic scenarios. The study highlights the challenges LLMs face in eliciting accurate information from clients, particularly under pressure.
Key Points
- DLawBench evaluates 26 LLMs using 461 legal cases from Chinese and U.S. law.
- The benchmark categorizes lawyer-client interactions into four types: Cooperative, Dependent, Withdrawn, and Adversarial.
- GPT-5.5, the top-performing model, achieves a score of only 0.562 in legal reasoning.
- The study uncovers sycophancy in legal consultations and models' performance paradox.
- Realistic dialogues reveal LLMs struggle most when clients require guidance.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 13931v1 Announce Type: new Abstract: Lawyer-client consultation is a critical starting point for legal services. Effective legal assistance hinges on eliciting sufficient and truthful information from clients in order to devise strategies that best protect their interests. This task requires Large Language Models (LLMs) not only to perform robust legal reasoning, but also to strategically elicit material facts through multi-turn interactions and effectively guide clients with diverse personalities.
Yet existing legal benchmarks overlook this interactive capability. To fill this gap, we introduce DLawBench, a diagnostic benchmark for real-world legal consultation. Drawing on realistic client behavior, we characterize lawyer-client interactions into four types: Cooperative, Dependent, Withdrawn, and Adversarial. Using dialogues grounded in real cases, DLawBench evaluates whether LLMs can effectively conduct legal consultation under realistic conditions. DLawBench comprises 461 cases from Chinese and U. S.
law, 5,532 paired fact entries, 3,411 inquiry rubrics, and 3,348 issue-resolution rubrics, and evaluates 26 representative LLMs. Systematic experiments show substantial headroom: the best-performing model, GPT-5. 5, achieves only 0. 562 on consultation-grounded legal reasoning. More importantly, DLawBench exposes both sycophancy in legal consultation and a paradox: models perform worse when clients need guidance most.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?
The REFLECT benchmark reveals that current LLM judges are unreliable, achieving below 55% accuracy in evaluating reasoning and evidence use, highlighting the need for improved evaluation methods for deep research agents.