MT-Bench

Multi-turn open-ended questions scored by an LLM judge, used to evaluate chat and instruction-following quality.

Papers using MT-Bench (32)

Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization2025Token-weighted Direct Preference Optimization with Attention2026Bridging Draft Policy Misalignment: Group Tree Optimization for Speculative Decoding2025 · 2 citesTACOS: Open Tagging and Comparative Scoring for Instruction Fine-Tuning Data Selection2025 · 1 citesDropping Just a Handful of Preferences Can Change Top Large Language Model Rankings2025TOWER: Tree Organized Weighting For Evaluating Complex Instructions2024 · 1 citesTransitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment2026MMoA: An AI-Agent framework with recurrence for Memoried Mixure-of-Agent2026Strategic Over-Parameterization for Generalizable Low-Rank Adaptation2026TAPS: Task Aware Proposal Distributions for Speculative Sampling2026SCOPE: Selective Conformal Optimized Pairwise LLM Judging2026DYCP: Dynamic Context Pruning for Long-Form Dialogue with LLMs2026Weights-Rotated Preference Optimization for Large Language Models2025Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization2025Alignment through Meta-Weighted Online Sampling: Bridging the Gap between Data Generation and Preference Optimization2025MaPPO: Maximum a Posteriori Preference Optimization with Prior Knowledge2025ComPO: Preference Alignment via Comparison Oracles2025ReviewInstruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models2025MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation2025Alignment Data Map for Efficient Preference Data Selection and Diagnosis2025RSPO: Regularized Self-Play Alignment of Large Language Models2025CrowdSelect: Synthetic Instruction Data Selection with Multi-LLM Wisdom2025DiffPO: Diffusion-styled Preference Optimization for Efficient Inference-Time Alignment of Large Language Models2025Leveraging Uncertainty Estimation for Efficient LLM Routing2025RIDE: Enhancing Large Language Model Alignment through Restyled In-Context Learning Demonstration Exemplars2025Capturing Nuanced Preferences: Preference-Aligned Distillation for Small Language Models2025Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning2024 · 2 citesLength Desensitization in Direct Preference Optimization2024AIPO: Improving Training Objective for Iterative Preference Optimization2024RRM: Robust Reward Model Training Mitigates Reward Hacking2024Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback2024TODO: Enhancing LLM Alignment with Ternary Preferences2024