Papers by Ke Qin
CAT: Confidence-Adaptive Thinking for Efficient Reasoning of Large Reasoning Models (2026.acl-industry)
Copied to clipboard
| Challenge: | Existing compression methods for large reasoning models rely on uniform length reduction or coarse-grained difficulty estimation, often leading to performance degradation on difficult problems. |
| Approach: | They propose a framework that incorporates modelโs intrinsic self-certainty signals as confidence into the preference optimization process, which autonomously modulates reasoning lengths based on problem difficulty. |
| Outcome: | The proposed framework outperforms state-of-the-art models on reasoning accuracy across multiple benchmarks on different base models. |
From Implicit Graph Encoding to Explicit Evidence: A Training-Free LLM Framework for Temporal Knowledge Graph Reasoning (2026.findings-acl)
Copied to clipboard
Guo Tang, Ke Cheng, Huiming Fan, Heng Chang, Wenxiang Zheng, Xianhao Ou, Junjia Xiang, Ming Liu, Yujun Zhou, Li Lanyu, Bing Qin
| Challenge: | Existing Large Language Models (LLMs) struggle with implicit modality alignment and suboptimal graph linearization. |
| Approach: | They propose a training-free, test-time adaptive framework that reframes TKG prediction as explicit evidence-driven reasoning. |
| Outcome: | ExE-LLM outperforms fully trained graph neural networks on four benchmarks . it achieves SOTA performance in inductive settings, significantly outperforming fully trained neural networks . |
DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding (2026.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive (AR) large audio language models are expensive in data and computation . prior work shows diffusion-based LALMs can improve audio understanding under matched settings . |
| Approach: | They propose a diffusion-based LALM that upgrades the speech encoder and employs dual semantic and acoustic adapters. |
| Outcome: | a new model improves over existing autoregressive large language models and is competitive to strong AR models . the proposed model can make use of limited training data and improve inference efficiency . a recent study shows that diffusion-based models can improve audio understanding . |
MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning (2026.acl-long)
Copied to clipboard
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Binbin Zheng, Chaowen Hu, Zekai Shao, Cong Qin, Lu Pan, Ke Zeng, Xunliang Cai
| Challenge: | Existing RLVR algorithms rely on rigid, uniform, and symmetric trust region mechanisms . current algorithms lack robustness, asymmetric signal reliability and inefficient gradient utilization . |
| Approach: | They propose a framework to harmonize three dimensions of RLVR algorithms, a paper argues . a binary cutoff is used to discard valuable reinforcement signals, they argue . |
| Outcome: | The proposed framework outperforms baselines in evaluating a robust RLVR solution. |
Sinkhorn Distance Minimization for Knowledge Distillation (2024.lrec-main)
Copied to clipboard
Xiao Cui, Yulei Qin, Yuting Gao, Enwei Zhang, Zihan Xu, Tong Wu, Ke Li, Xing Sun, Wengang Zhou, Houqiang Li
| Challenge: | Existing knowledge distillation methods investigate divergence measures but fail to deliver effective supervision when few distribution overlap exists between teacher and student. |
| Approach: | They propose a knowledge distillation method that exploits the Sinkhorn distance to ensure a nuanced assessment of the disparity between teacher and student distributions. |
| Outcome: | The proposed method outperforms state-of-the-art methods on all kinds of LLMs with encoder-only, encoder decoder, and decoded architectures. |
From log ๐ to ๐: Taming Divergence in Soft Clipping via Bilateral Decoupled Decay of Probability Gradient Weight (2026.acl-long)
Copied to clipboard
Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Chaowen Hu, Cong Qin, Zekai Shao, Binbin Zheng, Lu Pan, Ke Zeng
| Challenge: | Standard algorithms for Large Language Models (LLMs) enforce stability via "hard clipping" but relying on log-probability gradient yields divergent weights as probabilities vanish, destabilizing LLM training. |
| Approach: | They propose a decoupled gradient policy optimization that uses a decay mechanism to decouple the probability of a boundary token. |
| Outcome: | The proposed algorithm outperforms baselines on various mathematical benchmarks. |
SDPO: Segment-Level Direct Preference Optimization for Social Agents (2025.acl-long)
Copied to clipboard
Aobo Kong, Wentao Ma, Shiwan Zhao, Yongbin Li, Yuchuan Wu, Ke Wang, Xiaoqian Liu, Qicheng Li, Yong Qin, Fei Huang
| Challenge: | Direct Preference Optimization (DPO) has proven effective in aligning LLM behavior with human preferences across various tasks, but is limited in multi-turn social interactions. |
| Approach: | They propose a method which dynamically selects key segments within interactions to optimize multi-turn agent behavior. |
| Outcome: | The proposed methods outperform existing methods and proprietary LLMs on the SOTOPIA benchmark and show that they can improve social intelligence. |
Beta-LR: Interpretable Logical Reasoning based on Beta Distribution (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to capture logical information from text are limited by the uncertainty of the text. |
| Approach: | They propose a probabilistic embedding method to capture logical information from text . they embed texts into beta distributions on each dimension to eliminate logical uncertainty . |
| Outcome: | The proposed method achieves competitive performances on two datasets. |
How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization (2026.findings-acl)
Copied to clipboard
Yangyi Fang, Jiaye Lin, Xiaoliang Fu, Cong Qin, Haolin Shi, Chaowen Hu, Lu Pan, Ke Zeng, Xunliang Cai
| Challenge: | Existing methods for reinforcement learning with verifiable rewards are limited by the complexity of the problem and the complexity. |
| Approach: | They propose a theoretically-grounded dual-pronged optimization framework for reinforcement learning with verifiable rewards that compensates for gradient attenuation of high-confidence correct actions while utilizing entropy changes as computable indicators to stabilize excessive update magnitudes. |
| Outcome: | The proposed framework compensates for gradient attenuation of high-confidence correct actions while utilizing entropy changes as computable indicators to stabilize excessive update magnitudes. |
Understanding Large Language Model Vulnerabilities to Social Bias Attacks (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable linguistic capabilities across tasks . however, there is a growing concern about their potential to perpetuate social biases . |
| Approach: | They evaluate LLMs across gender, racial, and religious bias types . they also explore cross-bias and multiple-biases attacks . |
| Outcome: | The proposed models are more susceptible to gender bias attacks than racial or religious biases. |
EntroBench: Evaluating LLM Watermarking Under Multi-Entropy Scenarios and Practical User Operations (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluations of large language models (LLMs) watermarking are limited to fixed entropy settings. |
| Approach: | They propose a benchmark for LLM watermarking that systematically covers three entropy levels and seven representative tasks. |
| Outcome: | The proposed framework covers three entropy levels and seven representative tasks. |
LMOD: A Large Multimodal Ophthalmology Dataset and Benchmark for Large Vision-Language Models (2025.findings-naacl)
Copied to clipboard
Zhenyue Qin, Yu Yin, Dylan Campbell, Xuansheng Wu, Ke Zou, Ninghao Liu, Yih Chung Tham, Xiuzhen Zhang, Qingyu Chen
| Challenge: | Existing benchmarks for large vision-language models (LVLMs) are limited to ophthalmology-specific applications. |
| Approach: | They introduce a large-scale multimodal ophthalmology benchmark consisting of 21,993 instances across five ocular imaging modalities and 13 state-of-the-art LVLM representatives from closed-source, open-source and medical domains. |
| Outcome: | The proposed model shows significant performance drop in ophthalmology compared to other domains. |