Search Results for author: Lichang Chen

Found 29 papers, 14 papers with code

Learning to Reason via Mixture-of-Thought for Logical Reasoning

1 code implementation21 May 2025 Tong Zheng, Lichang Chen, Simeng Han, R. Thomas McCoy, Heng Huang

To fill in this gap, we propose Mixture-of-Thought (MoT), a framework that enables LLMs to reason across three complementary modalities: natural language, code, and a newly introduced symbolic modality, truth-table, which systematically enumerates logical cases and partially mitigates key failure modes in natural language reasoning.

Logical Reasoning Natural Language Inference

Self-rewarding correction for mathematical reasoning

1 code implementation26 Feb 2025 Wei Xiong, Hanning Zhang, Chenlu Ye, Lichang Chen, Nan Jiang, Tong Zhang

We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback.

Mathematical Reasoning

OmnixR: Evaluating Omni-modality Language Models on Reasoning across Modalities

no code implementations16 Oct 2024 Lichang Chen, Hexiang Hu, Mingda Zhang, YiWen Chen, Zifeng Wang, Yandong Li, Pranav Shyam, Tianyi Zhou, Heng Huang, Ming-Hsuan Yang, Boqing Gong

To address this, OmnixR offers two evaluation variants: (1)synthetic subset: a synthetic dataset generated automatically by translating text into multiple modalities--audio, images, video, and hybrids (Omnify).

From Lists to Emojis: How Format Bias Affects Model Alignment

no code implementations18 Sep 2024 Xuanchang Zhang, Wei Xiong, Lichang Chen, Tianyi Zhou, Heng Huang, Tong Zhang

In this work, we extend the study of biases in preference learning beyond the commonly recognized length bias, offering a comprehensive analysis of a wider range of format biases.

Chatbot

OPTune: Efficient Online Preference Tuning

no code implementations11 Jun 2024 Lichang Chen, Jiuhai Chen, Chenxi Liu, John Kirchenbauer, Davit Soselia, Chen Zhu, Tom Goldstein, Tianyi Zhou, Heng Huang

In this paper, we propose a more efficient data exploration strategy for online preference tuning (OPTune), which does not rely on human-curated or pre-collected teacher responses but dynamically samples informative responses for on-policy preference alignment.

Instruction Following

Unveiling the Impact of Coding Data Instruction Fine-Tuning on Large Language Models Reasoning

no code implementations30 May 2024 Xinlu Zhang, Zhiyu Zoey Chen, Xi Ye, Xianjun Yang, Lichang Chen, William Yang Wang, Linda Ruth Petzold

First, coding data tuning enhances the overall reasoning capabilities of LLMs across different model families and scales.

Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation

no code implementations CVPR 2024 Tianyu Luan, Zhong Li, Lele Chen, Xuan Gong, Lichang Chen, Yi Xu, Junsong Yuan

Then, we calculate the Area Under the Curve (AUC) difference between the two spectrums, so that each frequency band that captures either the overall or detailed shape is equitably considered.

Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements

1 code implementation16 Feb 2024 Ming Li, Jiuhai Chen, Lichang Chen, Tianyi Zhou

To examine DEBATUNE, we curate the largest dataset of debate topics so far, which covers 710 controversial topics and corresponding arguments for each topic.

Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

2 code implementations15 Feb 2024 Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Jiuxiang Gu, Tianyi Zhou

This paper introduces Selective Reflection-Tuning, a novel paradigm that synergizes a teacher LLM's reflection and introspection for improving existing data quality with the data selection capability of the student LLM, to automatically refine existing instruction-tuning data.

Data Augmentation Instruction Following

ODIN: Disentangled Reward Mitigates Hacking in RLHF

1 code implementation11 Feb 2024 Lichang Chen, Chen Zhu, Davit Soselia, Jiuhai Chen, Tianyi Zhou, Tom Goldstein, Heng Huang, Mohammad Shoeybi, Bryan Catanzaro

In this work, we study the issue of reward hacking on the response length, a challenge emerging in Reinforcement Learning from Human Feedback (RLHF) on LLMs.

GPT-4 Vision on Medical Image Classification -- A Case Study on COVID-19 Dataset

no code implementations27 Oct 2023 Ruibo Chen, Tianyi Xiong, Yihan Wu, Guodong Liu, Zhengmian Hu, Lichang Chen, Yanshuo Chen, Chenxi Liu, Heng Huang

This technical report delves into the application of GPT-4 Vision (GPT-4V) in the nuanced realm of COVID-19 image classification, leveraging the transformative potential of in-context learning to enhance diagnostic processes.

Diagnostic image-classification +3

AlpaCare:Instruction-tuned Large Language Models for Medical Application

1 code implementation23 Oct 2023 Xinlu Zhang, Chenxin Tian, Xianjun Yang, Lichang Chen, Zekun Li, Linda Ruth Petzold

Instruction-finetuning (IFT) has become crucial in aligning Large Language Models (LLMs) with diverse human needs and has shown great potential in medical applications.

Diversity Instruction Following

Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning

2 code implementations18 Oct 2023 Ming Li, Lichang Chen, Jiuhai Chen, Shwai He, Heng Huang, Jiuxiang Gu, Tianyi Zhou

Recent advancements in Large Language Models (LLMs) have expanded the horizons of natural language understanding and generation.

Natural Language Understanding

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection

1 code implementation31 Jul 2023 Jun Yan, Vikas Yadav, Shiyang Li, Lichang Chen, Zheng Tang, Hai Wang, Vijay Srinivasan, Xiang Ren, Hongxia Jin

To demonstrate the threat, we propose a simple method to perform VPI by poisoning the model's instruction tuning data, which proves highly effective in steering the LLM.

Backdoor Attack

AlpaGasus: Training A Better Alpaca with Fewer Data

3 code implementations17 Jul 2023 Lichang Chen, Shiyang Li, Jun Yan, Hai Wang, Kalpa Gunaratna, Vikas Yadav, Zheng Tang, Vijay Srinivasan, Tianyi Zhou, Heng Huang, Hongxia Jin

Large language models (LLMs) strengthen instruction-following capability through instruction-finetuning (IFT) on supervised instruction/response data.

Instruction Following

InstructZero: Efficient Instruction Optimization for Black-Box Large Language Models

2 code implementations5 Jun 2023 Lichang Chen, Jiuhai Chen, Tom Goldstein, Heng Huang, Tianyi Zhou

Large language models~(LLMs) are instruction followers, but it can be challenging to find the best instruction for different situations, especially for black-box LLMs on which backpropagation is forbidden.

Bayesian Optimization

Prompting Language-Informed Distribution for Compositional Zero-Shot Learning

1 code implementation23 May 2023 Wentao Bao, Lichang Chen, Heng Huang, Yu Kong

Compositional zero-shot learning (CZSL) task aims to recognize unseen compositional visual concepts, e. g., sliced tomatoes, where the model is learned only from the seen compositions, e. g., sliced potatoes and red tomatoes.

Compositional Zero-Shot Learning Informativeness +1

Backdoor Learning on Sequence to Sequence Models

no code implementations3 May 2023 Lichang Chen, Minhao Cheng, Heng Huang

Backdoor learning has become an emerging research area towards building a trustworthy machine learning system.

Machine Translation Sentence +3

PTP: Boosting Stability and Performance of Prompt Tuning with Perturbation-Based Regularizer

no code implementations3 May 2023 Lichang Chen, Heng Huang, Minhao Cheng

To address this critical problem, we first investigate and find that the loss landscape of vanilla prompt tuning is precipitous when it is visualized, where a slight change of input data can cause a big fluctuation in the loss landscape.

Natural Language Understanding

When do you need Chain-of-Thought Prompting for ChatGPT?

no code implementations6 Apr 2023 Jiuhai Chen, Lichang Chen, Heng Huang, Tianyi Zhou

However, it is not clear whether CoT is still effective on more recent instruction finetuned (IFT) LLMs such as ChatGPT.

Arithmetic Reasoning Memorization

How Many Demonstrations Do You Need for In-context Learning?

no code implementations14 Mar 2023 Jiuhai Chen, Lichang Chen, Chen Zhu, Tianyi Zhou

Moreover, ICL (with and w/o CoT) using only one correct demo significantly outperforms all-demo ICL adopted by most previous works, indicating the weakness of LLMs in finding correct demo(s) for input queries, which is difficult to evaluate on the biased datasets.

In-Context Learning

Task-Aware Sampling Layer for Point-Wise Analysis

no code implementations9 Jul 2021 Yiqun Lin, Lichang Chen, Haibin Huang, Chongyang Ma, Xiaoguang Han, Shuguang Cui

Sampling, grouping, and aggregation are three important components in the multi-scale analysis of point clouds.

Keypoint Detection Point Cloud Completion +1

Graph Edit Distance Reward: Learning to Edit Scene Graph

no code implementations ECCV 2020 Lichang Chen, Guosheng Lin, Shijie Wang, Qingyao Wu

Scene Graph, as a vital tool to bridge the gap between language domain and image domain, has been widely adopted in the cross-modality task like VQA.

Graph Matching Image Retrieval +2

Cannot find the paper you are looking for? You can Submit a new open access paper.