1 citations · 2 across the 12 of their papers we have counts for
19 papers
Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation
Hangxi Guo, Fengyuan Liu, Yue Wang +4
Reinforcement learning is commonly used to train language agents in interactive environments, but cannot be directly applied when rewards are unavailable. Recent methods use enviro…
From a Prompt to Repertoires: Evolving Functional REpertoires Enable LLM Continual Learning
Fengyuan Liu, Yue Wang, Hangxi Guo +3
Continual learning remains challenging for large language models, which must enable models to acquire new skills and knowledge without degrading existing capabilities. Existing app…
MM-FinEval: A Multi-Task Multimodal Benchmark for Real-World Financial Forecasting
Dong Shu, Yanguang Liu, Huopu Zhang +4
Financial forecasting from earnings conference calls requires models to reason over complex corporate disclosures, market expectations, and subtle communication signals. However, e…
Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation
Yongliang Miao, Shuang Liu, Yanguang Liu +2
On-policy distillation (OPD) uses teacher correction on student-generated responses. Full-vocabulary correction can provide important corrections even for tokens that the student a…
BiasReducer: Adaptive Bias Mitigation for Reward Models
Shuang Liu, Yongliang Miao, Yanguang Liu +2
Reward models score responses from large language models (LLMs) and guide LLM training toward human preferences. However, reward models can favor superficial attributes such as len…
DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity
Fengyuan Liu, Yongliang Miao, Zirui He +3
Reward models trained from pairwise preferences often exploit superficial shortcut cues rather than learning true response quality. We propose DynaCF, a dynamic reweighting framewo…
SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization
Jingyi He, Haiyan Zhao, Ruxue Shi +4
Although Sparse Autoencoders (SAEs) have mitigated the opacity of large language models (LLMs) by decomposing dense representations into sparse features, explaining these features…
RASFT: Rollout-Adaptive Supervised Fine-Tuning for Reasoning
Yongliang Miao, Fengyuan Liu, Wei Shi +4
Supervised fine-tuning (SFT) is a prevailing method for adapting large language models to reasoning tasks by imitating offline expert demonstrations, often treating a single expert…
HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models
Shuang Liu, Yuxuan Bo, Qiuyang Zhao +4
Reward models are central to large language model (LLM) alignment, but they remain vulnerable to reward hacking. To evaluate reward-model robustness, we introduce RewardHackBench c…
The Model Shape Behind Scaling Laws: A Gradient Superposition Perspective
Wenjie Sun, Jinning Yang, Shuai Zhang +1
Neural scaling laws guide resource allocation, but how should a fixed parameter budget be divided between depth and width? Motivated by inverse-width representation-error scaling u…
Universal Activation Verbalizer: A Unified Framework for Cross-Model Activation Explanation
Haiyan Zhao, Zirui He, Guanchu Wang +3
Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each model explains only its own ac…
FinAnchor: Aligned Multi-Model Representations for Financial Prediction
Zirui He, Huopu Zhang, Yanguang Liu +2
Financial prediction from long documents involves significant challenges, as actionable signals are often sparse and obscured by noise, and the optimal LLM for generating embedding…
FinCall-Surprise: A Large Scale Multi-modal Benchmark for Earning Surprise Prediction
Dong Shu, Yanguang Liu, Huopu Zhang +1
Predicting corporate earnings surprises is a profitable yet challenging task, as accurate forecasts can inform significant investment decisions. However, progress in this domain ha…
Improving LLM Reasoning through Interpretable Role-Playing Steering
Anyi Wang, Dong Shu, Yifan Wang +2
Role-playing has emerged as an effective technique for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods primarily rely on prompt engi…
SAE-FiRE: Enhancing Earnings Surprise Predictions Through Sparse Autoencoder Feature Selection
Huopu Zhang, Yanguang Liu, Miao Zhang +2
Predicting earnings surprises from financial documents, such as earnings conference calls, regulatory filings, and financial news, has become increasingly important in financial ec…
DBR: Divergence-Based Regularization for Debiasing Natural Language Understanding Models
Zihao Li, Ruixiang Tang, Lu Cheng +3
Pre-trained language models (PLMs) have achieved impressive results on various natural language processing tasks. However, recent research has revealed that these models often rely…
Aligning Large Language Models and Geometric Deep Models for Protein Representation
Dong Shu, Bingbing Duan, Kai Guo +3
Latent representation alignment has become a foundational technique for constructing multimodal large language models (MLLM) by mapping embeddings from different modalities into a…
Comparative Analysis of Demonstration Selection Algorithms for LLM In-Context Learning
Dong Shu, Mengnan Du
In-context learning can help Large Language Models (LLMs) to adapt new tasks without additional training. However, this performance heavily depends on the quality of the demonstrat…
DemoShapley: Valuation of Demonstrations for In-Context Learning
Shan Xie, Man Luo, Chadly Daniel Stern +2
Large language models (LLMs) using in-context learning (ICL) excel in many tasks without task-specific fine-tuning. However, demonstration selection and ordering greatly impact ICL…