Author name cluster

Haonan Li

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2026 Conference Paper

Control Illusion: The Failure of Instruction Hierarchies in Large Language Models

Yilin Geng
Haonan Li
Honglin Mu
Xudong Han
Timothy Baldwin
Omri Abend
Eduard Hovy
Lea Frermann

Large language models (LLMs) are increasingly deployed with hierarchical instruction schemes, where certain instructions (e.g., system-level directives) are expected to take precedence over others (e.g., user messages). Yet, we lack a systematic understanding of how effectively these hierarchical control mechanisms work. We introduce a systematic evaluation framework based on constraint prioritization to assess how well LLMs enforce instruction hierarchies. Our experiments across six state-of-the-art LLMs reveal that models struggle with consistent instruction prioritization, even for simple formatting conflicts. We find that the widely-adopted system/user prompt separation fails to establish a reliable instruction hierarchy, and models exhibit strong inherent biases toward certain constraint types regardless of their priority designation. Interestingly, we also find that societal hierarchy framings (e.g., authority, expertise, consensus) show stronger influence on model behavior than system/user roles, suggesting that pretraining-derived social structures function as latent behavioral priors with potentially greater impact than post-training guardrails.

PDF Details DOI

JAIR Journal 2025 Journal Article

Against The Achilles' Heel: A Survey on Red Teaming for Generative Models

Lizhi Lin
Honglin Mu
Zenan Zhai
Minghan Wang
Yuxia Wang
Renxi Wang
Junjie Gao
Yixuan Zhang

Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safe use as various vulnerabilities are exposed. In light of this, the field of red teaming is undergoing fast-paced growth, highlighting the need for a comprehensive survey covering the entire pipeline and addressing emerging topics. Our extensive survey, which examines over 120 papers, introduces a taxonomy of fine-grained attack strategies grounded in the inherent capabilities of language models. Additionally, we have developed the “searcher” framework to unify various automatic red teaming approaches. Moreover, our survey covers novel areas including multimodal attacks and defenses, risks around LLM-based agents, overkill of harmless queries, and the balance between harmlessness and helpfulness. Warning: This paper contains examples that may be offensive, harmful, or biased.

PDF Details DOI

TMLR Journal 2025 Journal Article

Bi-Mamba: Towards Accurate 1-Bit State Space Model

Shengkun Tang
Liqun Ma
Haonan Li
Mingjie Sun
Zhiqiang Shen

The typical selective state-space model (SSM) of Mamba addresses several limitations of Transformers, such as quadratic computational complexity with sequence length and significant inference-time memory requirements due to the key-value cache. However, the growing size of Mamba models continues to pose training and deployment challenges and raises concerns due to considerable training and inference compute consumption. In this work, we introduce Bi-Mamba, a scalable and powerful 1-bit Mamba architecture designed for more efficient large language models with multiple sizes across 780M, 1.3B, and 2.7B. Bi-Mamba models are trained from scratch on data volume as regular LLM pertaining using an autoregressive distillation loss. Extensive experimental results on language modeling demonstrate that Bi-Mamba achieves performance comparable to its full-precision counterparts (e.g., FP16 or BF16) and much better accuracy than post-training-binarization (PTB) Mamba and binarization-aware training (BAT) Transformer baselines, while significantly reducing memory footprint and computational consumption compared to the original Mamba model. Our study pioneers a new linear computational complexity LLM framework under low-bit representation and facilitates future design of specialized hardware tailored for efficient 1-bit Mamba-based LLMs. Our code is provided in Supplementary Material and the pre-trained weights are available anonymously at https://drive.google.com/drive/folders/1jfk_TlDzFbER84ITvU2hOX2VyPC9H4MA?usp=sharing

PDF Details

ICML Conference 2025 Conference Paper

Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

Chengqian Gao
Haonan Li
Liu Liu 0014
Zeke Xie
Peilin Zhao
Zhiqiang Xu 0003

The alignment of large language models (LLMs) often assumes that using more clean data yields better outcomes, overlooking the match between model capacity and example difficulty. Challenging this, we propose a new principle: Preference data vary in difficulty, and overly difficult examples hinder alignment, by exceeding the model’s capacity. Through systematic experimentation, we validate this principle with three key findings: (1) preference examples vary in difficulty, as evidenced by consistent learning orders across alignment runs; (2) overly difficult examples significantly degrade performance across four LLMs and two datasets; and (3) the capacity of a model dictates its threshold for handling difficult examples, underscoring a critical relationship between data selection and model capacity. Building on this principle, we introduce Selective DPO, which filters out overly difficult examples. This simple adjustment improves alignment performance by 9-16% in win rates on the AlpacaEval 2 benchmark compared to the DPO baseline, surpassing a series of DPO variants with different algorithmic adjustments. These results together illuminate the importance of aligning data difficulty with model capacity, offering a transformative perspective for improving alignment strategies in LLMs. Code is available at https: //github. com/glorgao/SelectiveDPO

Details

NeurIPS Conference 2025 Conference Paper

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Jorge (Zhoujun) Cheng
Shibo Hao
Tianyang Liu
Fan Zhou
Yutao Xie
Feng Yao
Yuexin Bian
Nilabjo Dey

Reinforcement learning (RL) has shown promise in enhancing large language model (LLM) reasoning, yet progress towards broader capabilities is limited by the availability of high-quality, multi-domain datasets. This work introduces \ours, a 92K RL-for-reasoning dataset designed to address this gap, covering six reasoning domains: Math, Code, Science, Logic, Simulation, and Tabular, each with corresponding verifiers. We build \ours via a careful data-curation pipeline, including sourcing, deduplication, reward design, and domain-specific and difficulty-based filtering, to facilitate the systematic investigation of cross-domain RL generalization. Our study using \ours suggests the efficacy of a simple mixed-domain RL training approach and reveals several key aspects affecting cross-domain transferability. We further train two models {\ours}-7B and {\ours}-32B purely with RL on our curated data and observe largely improved performance over leading open RL reasoning model baselines, with gains of 7. 3\% and 7. 8\% respectively on an extensive 17-task, six-domain evaluation suite. We are releasing our dataset, code, and evaluation suite to the community, aiming to support further research and development of more general RL-enhanced reasoning models.

PDF Details

NeurIPS Conference 2024 Conference Paper

Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs

Sukmin Yun
haokun lin
Rusiru Thushara
Mohammad Q. Bhat
Yongxin Wang
Zutao Jiang
Mingkai Deng
Jinhong Wang

Multimodal large language models (MLLMs) have shown impressive success across modalities such as image, video, and audio in a variety of understanding and generation tasks. However, current MLLMs are surprisingly poor at understanding webpage screenshots and generating their corresponding HTML code. To address this problem, we propose Web2Code, a benchmark consisting of a new large-scale webpage-to-code dataset for instruction tuning and an evaluation framework for the webpage understanding and HTML code translation abilities of MLLMs. For dataset construction, we leverage pretrained LLMs to enhance existing webpage-to-code datasets as well as generate a diverse pool of new webpages rendered into images. Specifically, the inputs are webpage images and instructions, while the responses are the webpage's HTML code. We further include diverse natural language QA pairs about the webpage content in the responses to enable a more comprehensive understanding of the web content. To evaluate model performance in these tasks, we develop an evaluation framework for testing MLLMs' abilities in webpage understanding and web-to-code generation. Extensive experiments show that our proposed dataset is beneficial not only to our proposed tasks but also in the general visual domain. We hope our work will contribute to the development of general MLLMs suitable for web-based content generation and task automation. Our data and code are available at https: //github. com/MBZUAI-LLM/web2code.

PDF Details DOI

JAIR Journal 2022 Journal Article

Neural Character-Level Syntactic Parsing for Chinese

Zuchao Li
Junru Zhou
Hai Zhao
Zhisong Zhang
Haonan Li
Yuqi Ju

In this work, we explore character-level neural syntactic parsing for Chinese with two typical syntactic formalisms: the constituent formalism and a dependency formalism based on a newly released character-level dependency treebank. Prior works in Chinese parsing have struggled with whether to de ne words when modeling character interactions. We choose to integrate full character-level syntactic dependency relationships using neural representations from character embeddings and richer linguistic syntactic information from human-annotated character-level Parts-Of-Speech and dependency labels. This has the potential to better understand the deeper structure of Chinese sentences and provides a better structural formalism for avoiding unnecessary structural ambiguities. Specifically, we first compare two different character-level syntax annotation styles: constituency and dependency. Then, we discuss two key problems for character-level parsing: (1) how to combine constituent and dependency syntactic structure in full character-level trees and (2) how to convert from character-level to word-level for both constituent and dependency trees. In addition, we also explore several other key parsing aspects, including di erent character-level dependency annotations and joint learning of Parts-Of-Speech and syntactic parsing. Finally, we evaluate our models on the Chinese Penn Treebank (CTB) and our published Shanghai Jiao Tong University Chinese Character Dependency Treebank (SCDT). The results show the e effectiveness of our model on both constituent and dependency parsing. We further provide empirical analysis and suggest several directions for future study.

PDF Details DOI

AAAI Conference 2018 Conference Paper

Neural Character-level Dependency Parsing for Chinese

Haonan Li
Zhisong Zhang
Yuqi Ju
Hai Zhao

This paper presents a truly full character-level neural dependency parser together with a newly released character-level dependency treebank for Chinese, which has suffered a lot from the dilemma of deﬁning word or not to model character interactions. Integrating full character-level dependencies with character embedding and human annotated characterlevel part-of-speech and dependency labels for the ﬁrst time, we show an extra performance enhancement from the evaluation on Chinese Penn Treebank and SJTU (Shanghai Jiao Tong University) Chinese Character Dependency Treebank and the potential of better understanding deeper structure of Chinese sentences.

PDF Details