Search Results for author: Chi Han

Found 26 papers, 13 papers with code

Can Language Models Follow Multiple Turns of Entangled Instructions?

1 code implementation17 Mar 2025 Chi Han

This work presents a systematic investigation of LLMs' capabilities in handling multiple turns of instructions, covering three levels of difficulty: (1) retrieving information from instructions, (2) tracking and reasoning across turns, and (3) resolving conflicts among instructions.

Instruction Following Memorization

The Law of Knowledge Overshadowing: Towards Understanding, Predicting, and Preventing LLM Hallucination

no code implementations22 Feb 2025 Yuji Zhang, Sha Li, Cheng Qian, Jiateng Liu, Pengfei Yu, Chi Han, Yi R. Fung, Kathleen McKeown, ChengXiang Zhai, Manling Li, Heng Ji

To address it, we propose a novel concept: knowledge overshadowing, where model's dominant knowledge can obscure less prominent knowledge during text generation, causing the model to fabricate inaccurate details.

Hallucination Text Generation

SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering

no code implementations10 Feb 2025 Xuehang Guo, Xingyao Wang, Yangyi Chen, Sha Li, Chi Han, Manling Li, Heng Ji

Besides substantial performance gaps among agents (from Llama-3. 1 agent <= 3. 33% to Claude-3. 5-Sonnet >= 28. 18%), their consistently low collaboration willingness (<= 4. 86%) suggests fundamental limitations of existing LLM in CSE.

Large Language Model

Learning to Generate Research Idea with Dynamic Control

no code implementations19 Dec 2024 Ruochen Li, Liqiang Jing, Chi Han, Jiawei Zhou, Xinya Du

Our framework provides a balanced approach to research ideation, achieving high-quality outcomes by dynamically navigating the trade-offs among novelty, feasibility, and effectiveness.

Reinforcement Learning (RL) scientific discovery

Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play

no code implementations24 Oct 2024 Sha Li, Revanth Gangi Reddy, Khanh Duy Nguyen, Qingyun Wang, May Fung, Chi Han, Jiawei Han, Kartik Natarajan, Clare R. Voss, Heng Ji

Complex news events, such as natural disasters and socio-political conflicts, require swift responses from the government and society.

Humanitarian

MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorders

1 code implementation9 Oct 2024 Cheng Li, May Fung, Qingyun Wang, Chi Han, Manling Li, Jindong Wang, Heng Ji

In this paper, we introduce MentalArena, a self-play framework to train language models by generating domain-specific personalized data, where we obtain a better model capable of making a personalized diagnosis and treatment (as a therapist) and providing information (as a patient).

Towards LifeSpan Cognitive Systems

no code implementations20 Sep 2024 Yu Wang, Chi Han, Tongtong Wu, Xiaoxin He, Wangchunshu Zhou, Nafis Sadeq, Xiusi Chen, Zexue He, Wei Wang, Gholamreza Haffari, Heng Ji, Julian McAuley

In this paper we focus on the domain of Large Language Models (LLMs), where we identify two major challenges: (1) Abstraction and Experience Merging, and (2) Long-term Retention with Accurate Recall.

Continual Learning

Why Does New Knowledge Create Messy Ripple Effects in LLMs?

no code implementations2 Jul 2024 Jiaxin Qin, Zixuan Zhang, Chi Han, Manling Li, Pengfei Yu, Heng Ji

Extensive previous research has focused on post-training knowledge editing (KE) for language models (LMs) to ensure that knowledge remains accurate and up-to-date.

knowledge editing Negation

Eliminating Position Bias of Language Models: A Mechanistic Approach

1 code implementation1 Jul 2024 Ziqi Wang, HANLIN ZHANG, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji

Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context.

Math object-detection +4

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

1 code implementation26 Mar 2024 Rui Pan, Xiang Liu, Shizhe Diao, Renjie Pi, Jipeng Zhang, Chi Han, Tong Zhang

Attempting to complement this deficiency, we investigate the layerwise properties of LoRA on fine-tuning tasks and observe an unexpected but consistent skewness of weight norms across different layers.

GSM8K Language Modeling +5

Large Language Models on Graphs: A Comprehensive Survey

1 code implementation5 Dec 2023 Bowen Jin, Gang Liu, Chi Han, Meng Jiang, Heng Ji, Jiawei Han

Besides, although LLMs have shown their pure text-based reasoning ability, it is underexplored whether such ability can be generalized to graphs (i. e., graph-based reasoning).

Language Modelling Survey

InfoPattern: Unveiling Information Propagation Patterns in Social Media

no code implementations27 Nov 2023 Chi Han, Jialiang Xu, Manling Li, Hanning Zhang, Tarek Abdelzaher, Heng Ji

Social media play a significant role in shaping public opinion and influencing ideological communities through information propagation.

Red Teaming Stance Detection

Defining a New NLP Playground

no code implementations31 Oct 2023 Sha Li, Chi Han, Pengfei Yu, Carl Edwards, Manling Li, Xingyao Wang, Yi R. Fung, Charles Yu, Joel R. Tetreault, Eduard H. Hovy, Heng Ji

The recent explosion of performance of large language models (LLMs) has changed the field of Natural Language Processing (NLP) more abruptly and seismically than any other shift in the field's 80-year history.

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

1 code implementation30 Aug 2023 Chi Han, Qifan Wang, Hao Peng, Wenhan Xiong, Yu Chen, Heng Ji, Sinong Wang

As a result, their performance suffers drastically on inputs longer than those encountered during training, substantially limiting their applications in real-world tasks involving long contexts such as encoding scientific articles, code repositories, or long dialogues.

2k 4k +1

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

2 code implementations23 May 2023 Cheng Qian, Chi Han, Yi R. Fung, Yujia Qin, Zhiyuan Liu, Heng Ji

Additionally, we introduce the Creation Challenge dataset, featuring 2K diverse questions, to emphasize the necessity and benefits of LLMs' tool creation ability.

2k Math +1

Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning

1 code implementation22 May 2023 Chi Han, Qizheng He, Charles Yu, Xinya Du, Hanghang Tong, Heng Ji

A LERP is designed as a vector of probabilistic logical functions on the entity's neighboring sub-graph.

Link Prediction

Word Embeddings Are Steers for Language Models

1 code implementation22 May 2023 Chi Han, Jialiang Xu, Manling Li, Yi Fung, Chenkai Sun, Nan Jiang, Tarek Abdelzaher, Heng Ji

In this work, we theoretically and empirically revisit output word embeddings and find that their linear transformations are equivalent to steering language model generation styles.

Language Modeling Language Modelling +1

Understanding the Effect of Data Augmentation on Knowledge Distillation

no code implementations21 May 2023 Ziqi Wang, Chi Han, Wenxuan Bao, Heng Ji

However, such data augmentation methods are sub-optimal for knowledge distillation since the teacher model could provide label distributions and is more tolerant to semantic shifts.

Data Augmentation Knowledge Distillation

Zero-Shot Classification by Logical Reasoning on Natural Language Explanations

1 code implementation7 Nov 2022 Chi Han, Hengzhi Pei, Xinya Du, Heng Ji

To this end, we propose the framework CLORE (Classification by LOgical Reasoning on Explanations).

Classification Logical Reasoning +1

Learning Homophilic Incentives in Sequential Social Dilemmas

no code implementations29 Sep 2021 Heng Dong, Tonghan Wang, Jiayuan Liu, Chi Han, Chongjie Zhang

Promoting cooperation among self-interested agents is a long-standing and interdisciplinary problem, but receives less attention in multi-agent reinforcement learning (MARL).

Multi-agent Reinforcement Learning

Learning Shared Semantic Space for Speech-to-Text Translation

2 code implementations Findings (ACL) 2021 Chi Han, Mingxuan Wang, Heng Ji, Lei LI

By projecting audio and text features to a common semantic representation, Chimera unifies MT and ST tasks and boosts the performance on ST benchmarks, MuST-C and Augmented Librispeech, to a new state-of-the-art.

Machine Translation Speech-to-Text +2

Birds of a Feather Flock Together: A Close Look at Cooperation Emergence via Multi-Agent RL

no code implementations23 Apr 2021 Heng Dong, Tonghan Wang, Jiayuan Liu, Chi Han, Chongjie Zhang

We propose a novel learning framework to encourage homophilic incentives and show that it achieves stable cooperation in both SSDs of public goods and tragedy of the commons.

Multi-agent Reinforcement Learning

Visual Concept-Metaconcept Learning

1 code implementation NeurIPS 2019 Chi Han, Jiayuan Mao, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu

Humans reason with concepts and metaconcepts: we recognize red and green from visual input; we also understand that they describe the same property of objects (i. e., the color).

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