papers

Publications (18)

cs.CL2026

Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling

Changze Lv, Zhenghua Wang, Yiran Ding +9

Large Language Models (LLMs) still struggle with the ``lost-in-the-middle'' problem, where critical information located in the middle of long-context inputs is often underrepresent…

cs.LG2026

Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges

Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20

Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models…

cs.AI2025

RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data

Zhengkang Guo, Wenhao Liu, Mingchen Xie +13

Large language models (LLMs) are increasingly expected to tackle complex tasks, driven by their expanding applications and users' growing proficiency in crafting sophisticated prom…

cs.SE2024

Multi-Programming Language Sandbox for LLMs

Shihan Dou, Jiazheng Zhang, Jianxiang Zang +25

We introduce MPLSandbox, an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Lang…

cs.LG2025

Enhancing Model Privacy in Federated Learning with Random Masking and Quantization

Zhibo Xu, Jianhao Zhu, Jingwen Xu +7

The primary goal of traditional federated learning is to protect data privacy by enabling distributed edge devices to collaboratively train a shared global model while keeping raw…

cs.CL2024

Aligning Large Language Models with Human Preferences through Representation Engineering

Wenhao Liu, Xiaohua Wang, Muling Wu +7

Aligning large language models (LLMs) with human preferences is crucial for enhancing their utility in terms of helpfulness, truthfulness, safety, harmlessness, and interestingness…

cs.CL2025

Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning

Muling Wu, Qi Qian, Wenhao Liu +12

Large Language Models (LLMs) have achieved remarkable performance across various reasoning tasks, yet post-training is constrained by inefficient sample utilization and inflexible…

cs.LG2024

Advancing Parameter Efficiency in Fine-tuning via Representation Editing

Muling Wu, Wenhao Liu, Xiaohua Wang +7

Parameter Efficient Fine-Tuning (PEFT) techniques have drawn significant attention due to their ability to yield competitive results while updating only a small portion of the adju…

cs.CL2026

Benchmark^2: Systematic Evaluation of LLM Benchmarks

Qi Qian, Chengsong Huang, Jingwen Xu +13

The rapid proliferation of benchmarks for evaluating large language models (LLMs) has created an urgent need for systematic methods to assess benchmark quality itself. We propose B…

cs.CL2025

UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation

Tianlong Li, Wenhao Liu, Muling Wu +6

Personality is a crucial factor that shapes human communication patterns, thereby regulating the personalities of large language models (LLMs) holds significant potential in enhanc…

cs.LG2024

Promoting Data and Model Privacy in Federated Learning through Quantized LoRA

JianHao Zhu, Changze Lv, Xiaohua Wang +7

Conventional federated learning primarily aims to secure the privacy of data distributed across multiple edge devices, with the global model dispatched to edge devices for paramete…

cs.AI2025

Tell Me What You Don't Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editing

Wenhao Liu, Siyu An, Junru Lu +8

Role-Playing Agents (RPAs) have shown remarkable performance in various applications, yet they often struggle to recognize and appropriately respond to hard queries that conflict w…

cs.AI2025

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling

Xiaoyu Liu, Di Liang, Chang Dai +9

Reward Models (RMs) are key components for evaluating and guiding language model outputs. However, traditional scalar RMs often struggle with incorporating contextual and backgroun…

cs.NE2025

SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network

Changze Lv, Tianlong Li, Wenhao Liu +6

Spiking Neural Networks (SNNs) have emerged as a promising alternative to conventional Artificial Neural Networks (ANNs), demonstrating comparable performance in both visual and li…

cs.CL2025

Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective

Tianlong Li, Zhenghua Wang, Wenhao Liu +6

The recent surge in jailbreaking attacks has revealed significant vulnerabilities in Large Language Models (LLMs) when exposed to malicious inputs. While various defense strategies…

cs.SE2025

What's Wrong with Your Code Generated by Large Language Models? An Extensive Study

Shihan Dou, Haoxiang Jia, Shenxi Wu +14

The increasing development of LLMs in code generation has drawn significant attention among researchers. To enhance LLM-based code generation ability, current efforts are predomina…

cs.LG2025

Improving RL Exploration for LLM Reasoning through Retrospective Replay

Shihan Dou, Muling Wu, Jingwen Xu +4

Reinforcement learning (RL) has increasingly become a pivotal technique in the post-training of large language models (LLMs). The effective exploration of the output space is essen…

cs.NE2024

Towards Biologically Plausible Computing: A Comprehensive Comparison

Changze Lv, Yufei Gu, Zhengkang Guo +16

Backpropagation is a cornerstone algorithm in training neural networks for supervised learning, which uses a gradient descent method to update network weights by minimizing the dis…