2 citations · 3 across the 10 of their papers we have counts for
11 papers
Mitigating Video Hallucinations via Attention-Guided Representation Perturbation
Zhixin Cai, Ruoqi Yuan, Xinchen Yang +4
Video large language models (Video LLMs) often generate responses unsupported by the input video. Contrastive decoding (CD) can mitigate these hallucinations, but its effectiveness…
Your Dense Retriever is Secretly an Expeditious Reasoner
Yichi Zhang, Jun Bai, Zhixin Cai +4
Dense retrievers enhance retrieval by encoding queries and documents into continuous vectors, but they often struggle with reasoning-intensive queries. Although Large Language Mode…
CogAtom: From Cognitive Atoms to Olympiad-level Mathematical Reasoning in Large Language Models
Zhuofan Chen, Jiyuan He, Yichi Zhang +4
Mathematical reasoning poses significant challenges for Large Language Models (LLMs) due to its demand for multi-step reasoning and abstract conceptual integration. While recent te…
DiscRec: Disentangled Semantic-Collaborative Modeling for Generative Recommendation
Chang Liu, Yimeng Bai, Xiaoyan Zhao +3
Generative recommendation is emerging as a powerful paradigm that directly generates item predictions, moving beyond traditional matching-based approaches. However, current methods…
Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matching
Jianfei Zhang, Bei Li, Jun Bai +4
In-Context Learning (ICL) empowers Large Language Models (LLMs) for rapid task adaptation without Fine-Tuning (FT), but its reliance on demonstration selection remains a critical c…
Beyond One-Size-Fits-All: Inversion Learning for Highly Effective NLG Evaluation Prompts
Hanhua Hong, Chenghao Xiao, Yang Wang +3
Evaluating natural language generation systems is challenging due to the diversity of valid outputs. While human evaluation is the gold standard, it suffers from inconsistencies, l…
Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment
Jianfei Zhang, Jun Bai, Bei Li +4
Aligning Large Language Models (LLMs) with general human preferences has been proved crucial in improving the interaction quality between LLMs and human. However, human values are…
Leveraging Estimated Transferability Over Human Intuition for Model Selection in Text Ranking
Jun Bai, Zhuofan Chen, Zhenzi Li +5
Text ranking has witnessed significant advancements, attributed to the utilization of dual-encoder enhanced by Pre-trained Language Models (PLMs). Given the proliferation of availa…
PFME: A Modular Approach for Fine-grained Hallucination Detection and Editing of Large Language Models
Kunquan Deng, Zeyu Huang, Chen Li +3
Large Language Models (LLMs) excel in fluency but risk producing inaccurate content, called "hallucinations." This paper outlines a standardized process for categorizing fine-grain…
Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors
Han Li, Zehao Huang, Zitian Wang +3
3D lane detection and topology reasoning are essential tasks in autonomous driving scenarios, requiring not only detecting the accurate 3D coordinates on lane lines, but also reaso…
How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey
Jun Bai, Xiaofeng Zhang, Chen Li +4
Transferability estimation has been attached to great attention in the computer vision fields. Researchers try to estimate with low computational cost the performance of a model wh…