Papers by Pinlong Zhao
B-APO: Bias-Targeted Adversarial Preference Optimization for Debiasing Multimodal Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing debiasing methods create biased responses by completely removing an entire modality, forming an extreme and static training environment. |
| Approach: | They propose a method to debiase multimodal large language models by masking one modality and then enlarge the margin between clean and adversarial responses. |
| Outcome: | The proposed method achieves superior debiasing performance while maintaining general capabilities. |
Learning Temporally-Aware Sample Weights for Preference Optimization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for preference optimization rely on static functions of instantaneous model states and ignore temporal learning dynamics. |
| Approach: | They propose a framework that meta-learns adaptive weights using three temporal features: reward margin evolution, learning volatility, and reference deviation. |
| Outcome: | The proposed framework achieves statistically significant improvements over baselines on models ranging from 7B to 70B parameters. |
What Do LLMs Learn First? Asymmetric Learning Dynamics of Input Complexity and Output Ambiguity in Preference Alignment (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods treat all preference pairs uniformly during training. |
| Approach: | They propose a training framework that maintains separate, adaptive pacing schedules for each dimension. |
| Outcome: | The proposed training framework outperforms curriculum baselines by 2.1% and 0.21 points . it achieves 42.3% length-controlled win rate on AlpacaEval 2.0 and 7.66 on MT-Bench . |
What Tokens Truly Matter? The Logit Conflation Problem in LLM Sampling (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for large language models filter tokens based on logit magnitudes or derived statistics, under the implicit assumption that high-logit tokens are desirable. |
| Approach: | They propose to isolate the Logit Conflation Problem by using attention-weighted attribution to extract prompt-relevance from token logits. |
| Outcome: | The proposed method improves on LLaMA-3 and is training-free and low latency. |