2 citations · 4 across the 9 of their papers we have counts for
12 papers
Calibrating LLM Explanations to Human Decisions with Reinforcement Learning
Dong Shu, Ziyang Guo, Negar Kamali +2
Explanations of LLM outputs are considered an important way to make model behavior legible, helping human users make good decisions on downstream tasks. However, default training a…
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…
Learning from the Right Rollouts: Data Attribution for PPO-based LLM Post-Training
Dong Shu, Denghui Zhang, Jessica Hullman
Traditional RL algorithms like Proximal Policy Optimization (PPO) typically train on the entire rollout buffer, operating under the assumption that all generated episodes provide a…
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…
Enhancing LLM Steering through Sparse Autoencoder-Based Vector Refinement
Anyi Wang, Xuansheng Wu, Dong Shu +2
Steering has emerged as a promising approach in controlling large language models (LLMs) without modifying model parameters. However, most existing steering methods rely on large-s…
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…
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders
Dong Shu, Xuansheng Wu, Haiyan Zhao +2
Sparse Autoencoders (SAEs) have recently emerged as powerful tools for interpreting and steering the internal representations of large language models (LLMs). However, conventional…
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
Dong Shu, Xuansheng Wu, Haiyan Zhao +4
Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted…
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability
Dong Shu, Haiyan Zhao, Jingyu Hu +4
Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in processing both visual and textual information. However, the critical challenge of alignment betwe…
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…
Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI
Bo Shu, Yiting Zhang, Saisai Hu +1
This report investigates the history and impact of Generative Models and Connected and Automated Vehicles (CAVs), two groundbreaking forces pushing progress in technology and trans…