When the Strongest Teacher Is Not the Best Teacher: Student-Centric Answer Selection
cs.LG, cs.AI, cs.CL
Submitted: 2026-05-26
Updated: 2026-09-01
Code: https://github.com/ppsmk388/Student-Centric-Answer-Selection
Terminology
Sources
- Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking
- Training Verifiers to Solve Math Word Problems
- Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance
- Phi-4 Technical Report
- Deep Bayesian Active Learning with Image Data
- Measuring Mathematical Problem Solving With the MATH Dataset
- Influence Functions for Efficient Data Selection in Reasoning
- Towards Active Synthetic Data Generation for Finetuning Language Models
- DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
- How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients
- In Good GRACEs: Principled Teacher Selection for Knowledge Distillation
- NaturalThoughts: Selecting and Distilling Reasoning Traces for General Reasoning Tasks
- From Word to World: Can Large Language Models be Implicit Text-based World Models?
- ToolACE: Winning the Points of LLM Function Calling
- CYCLE-INSTRUCT: Fully Seed-Free Instruction Tuning via Dual Self-Training and Cycle Consistency
- TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
- ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis
- SynthAgent: Adapting Web Agents with Synthetic Supervision
- Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment
- Data Valuation using Reinforcement Learning
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks