---
title: "Hao Li — author profile and papers · Bias, fairness & safety"
description: "Hao Li, Beijing Institute of Technology: 11 papers on Elamur Research (2020–2026), h-index 1 — affiliations, topics, co-authors and who cites…"
canonical: "https://research.elamur.ai/free/en/authors/hao-li/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/hao-li/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Hao Li

# Hao Li

Hao Li has 11 papers in our library, in 2020–2026, most of them on [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Jing Shao](https://md.research.elamur.ai/free/en/authors/jing-shao/), [Lei Sha](https://md.research.elamur.ai/free/en/authors/lei-sha/), [Dongrui Liu](https://md.research.elamur.ai/free/en/authors/dongrui-liu/).

11 papers in our library · 2020–2026

[OpenAlex](https://openalex.org/A5139836816) · [ORCID](https://orcid.org/0009-0002-0090-4870) · [**h-index 1**](https://openalex.org/authors/A5139836816) · [9 works](https://openalex.org/works?filter=author.id:A5139836816) · [4 citations](https://openalex.org/works?filter=author.id:A5139836816&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 11 works in our library](https://md.research.elamur.ai/free/en/authors/hao-li/#papers) · [🔗 Cited 207 times in our library](https://md.research.elamur.ai/free/en/authors/hao-li/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #3761](https://md.research.elamur.ai/free/en/paper-stars/page/38/#star-3761)

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Hao+Li) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Hao+Li) · [dblp](https://dblp.org/search?q=Hao+Li) · [ACL Anthology](https://aclanthology.org/search/?q=Hao+Li)

## Affiliations

[🔬**Shanghai Artificial Intelligence Laboratory** Shanghai · China 2025–2026 · 3 papers*current*](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) · [🏢**Alibaba Group** Hangzhou · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/alibaba-group/) · [🎓**Beihang University** Beijing · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/beihang-university/) · [🎓**Beijing Institute of Technology** Beijing · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/beijing-institute-of-technology/) · [🎓**Northwestern Polytechnical University** Xi'an · China 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/northwestern-polytechnical-university/)

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

## Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 11 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 11 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 9 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 9 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Safety Research · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/)

🧭 Topics 6 Research subjects and languages the work is about.[Sentiment & emotion · 1 work](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · [Bias, fairness & safety · 5 works](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Dialogue systems · 1 work](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · [Vision & language · 2 works](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Language models & pretraining · 3 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Information retrieval & search · 1 work](https://md.research.elamur.ai/free/en/topics/information-retrieval/)

## Works by year

### 2020s

[**2026** 5 papers](https://md.research.elamur.ai/free/en/authors/hao-li/year/2026/) · [**2025** 5 papers](https://md.research.elamur.ai/free/en/authors/hao-li/year/2025/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/authors/hao-li/year/2020/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://md.research.elamur.ai/free/en/papers/xu-2020-position-aware-tagging-aspect-sentiment/)** *(2020 · 370 citations)* This paper addresses Aspect Sentiment Triplet Extraction (ASTE). The task is to find each target in a sentence, its sentiment polarity, and the opinion span that explains that sentiment. The only earlier method (Peng et al., 2019) used two stages: it first labelled targets with sentiment and opinion spans, then…
2. **[Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://md.research.elamur.ai/free/en/papers/li-2025-hello-again-llm-powered-personalized/)** *(2025 · 55 citations)* Most open-domain chatbots are built for short, single-session exchanges. Real companionship, however, requires remembering past conversations and keeping track of who the user and the bot are. The authors present LD-Agent, a model-agnostic framework that splits long-term dialogue into three separately trainable…
3. **[VLSBench: Unveiling Visual Leakage in Multimodal Safety](https://md.research.elamur.ai/free/en/papers/hu-2025-vlsbench-unveiling-visual-leakage-multimodal/)** *(2025 · 32 citations)* Earlier work reported a puzzling result: aligning multimodal LLMs with text-only data seemed to make them about as safe as aligning them with image-text pairs.
4. **[LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts](https://md.research.elamur.ai/free/en/papers/ren-2025-llms-know-their-vulnerabilities-uncover/)** *(2025 · 18 citations)* The paper investigates a safety weakness of aligned LLMs. Seemingly harmless prompts that are semantically connected to a harmful request can steer a model into producing unsafe output. The authors call this exploitation of "natural distribution shift" and contrast it with attacks that deliberately distort the toxic…
5. **[PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free](https://md.research.elamur.ai/free/en/papers/li-2025-piguard-prompt-injection-guardrail-mitigating/)** *(2025 · 16 citations)* Lightweight prompt guard classifiers screen LLM inputs for prompt injection, but they often learn a shortcut.
6. **[Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment](https://md.research.elamur.ai/free/en/papers/li-2025-layer-aware-representation-filtering-purifying/)** *(2025 · 11 citations)* Fine-tuning a safety-aligned LLM can weaken its refusal behaviour even when the training data look harmless.
7. **[Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://md.research.elamur.ai/free/en/papers/hua-2026-rethinking-jailbreak-detection-large-vision/)** *(2026 · 10 citations)* Multimodal jailbreak attacks on Large Vision-Language Models (LVLMs) call for detectors that work on attack types never seen in training and that add little runtime cost.
8. **[LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation](https://md.research.elamur.ai/free/en/papers/liu-2026-logitspec-accelerating-retrieval-based-speculative/)** *(2026 · 6 citations)* Speculative decoding speeds up LLM inference by drafting several tokens and having the target model verify them in one pass.
9. **[Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay](https://md.research.elamur.ai/free/en/papers/wang-2026-be-your-own-red-teamer/)** *(2026 · 1 citation)* LLM safety training usually depends on fixed red-teaming resources, such as static defense prompts or pre-collected jailbreak datasets.
10. **[Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training](https://md.research.elamur.ai/free/en/papers/yang-2026-data-mixing-agent-learning-re/)** *(2026 · 1 citation)* Continual pre-training of an LLM on a narrow target field, such as math, often causes catastrophic forgetting of general skills.
11. **[AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs](https://md.research.elamur.ai/free/en/papers/lyu-2026-autotaskeval-domain-specific-fine-grained/)** *(2026)* Static, manually built benchmarks are expensive, cover few tasks, and lose discriminative power as LLMs improve.

## All works

12 works of theirs in our library, the most cited first; 11 with a page here, the others link their original until we summarise them.

1. **[Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://md.research.elamur.ai/free/en/papers/xu-2020-position-aware-tagging-aspect-sentiment/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Lu Xu, Hao Li, Wei Lu, et al.*2020 · 370 citations*
2. **[Hello Again! LLM-powered Personalized Agent for Long-term Dialogue](https://md.research.elamur.ai/free/en/papers/li-2025-hello-again-llm-powered-personalized/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Hao Li, Chenghao Yang, An Zhang, et al.*2025 · 55 citations*
3. **[VLSBench: Unveiling Visual Leakage in Multimodal Safety](https://md.research.elamur.ai/free/en/papers/hu-2025-vlsbench-unveiling-visual-leakage-multimodal/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xuhao Hu, Dongrui Liu, Hao Li, et al.*2025 · 32 citations*
4. **[LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts](https://md.research.elamur.ai/free/en/papers/ren-2025-llms-know-their-vulnerabilities-uncover/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Qibing Ren, Hao Li, Dongrui Liu, et al.*2025 · 18 citations*
5. **[PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free](https://md.research.elamur.ai/free/en/papers/li-2025-piguard-prompt-injection-guardrail-mitigating/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Hao Li, Xiaogeng Liu, Ning Zhang, et al.*2025 · 16 citations*
6. **[Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignment](https://md.research.elamur.ai/free/en/papers/li-2025-layer-aware-representation-filtering-purifying/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Hao Li, Lijun Li, Zhenghao Lu, et al.*2025 · 11 citations*
7. **[Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://md.research.elamur.ai/free/en/papers/hua-2026-rethinking-jailbreak-detection-large-vision/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Peichun Hua, Hao Li, Shanghao Shi, et al.*2026 · 10 citations*
8. **[LogitSpec: Accelerating Retrieval-based Speculative Decoding via Next Next Token Speculation](https://md.research.elamur.ai/free/en/papers/liu-2026-logitspec-accelerating-retrieval-based-speculative/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Tianyu Liu, Qitan Lv, Hao Li, et al.*2026 · 6 citations*
9. **[Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay](https://md.research.elamur.ai/free/en/papers/wang-2026-be-your-own-red-teamer/) [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/)**Hao Wang, Yanting Wang, Hao Li, et al.*2026 · 1 citation*
10. **[Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training](https://md.research.elamur.ai/free/en/papers/yang-2026-data-mixing-agent-learning-re/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Kailai Yang, Xiao Liu, Lei Ji, et al.*2026 · 1 citation*
11. **[AutoTaskEval: Towards Domain-Specific and Fine-Grained Evaluation for LLMs](https://md.research.elamur.ai/free/en/papers/lyu-2026-autotaskeval-domain-specific-fine-grained/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Qingqing Lyu, Linjuan Wu, Yongliang Shen, et al.*2026*
12. **[MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings ↗](https://aclanthology.org/2026.acl-long.2045/) Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Yiqun Zhang et al.*2026*

## Co-authors here

12 of 40 co-authors with a page, the most papers together first.

- [Jing Shao](https://md.research.elamur.ai/free/en/authors/jing-shao/) ×3
- [Lei Sha](https://md.research.elamur.ai/free/en/authors/lei-sha/) ×3
- [Dongrui Liu](https://md.research.elamur.ai/free/en/authors/dongrui-liu/) ×2
- [Ning Zhang](https://md.research.elamur.ai/free/en/authors/ning-zhang/) ×2
- [Rui Li](https://md.research.elamur.ai/free/en/authors/rui-li/) ×2
- [An Zhang](https://md.research.elamur.ai/free/en/authors/an-zhang/)
- [Chaowei Xiao](https://md.research.elamur.ai/free/en/authors/chaowei-xiao/)
- [Chenghao Yang](https://md.research.elamur.ai/free/en/authors/chenghao-yang/)
- [Hao Wang](https://md.research.elamur.ai/free/en/authors/hao-wang/)
- [Hengwei Liu](https://md.research.elamur.ai/free/en/authors/hengwei-liu/)
- [Junchi Yan](https://md.research.elamur.ai/free/en/authors/junchi-yan/)
- [Kailai Yang](https://md.research.elamur.ai/free/en/authors/kailai-yang/)

## Venues

Where their works here were published, the most works first, with the editions of those that have a page.

- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×7: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×3, [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) ×3
- [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/) ×2: [EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/), [EMNLP 2020](https://md.research.elamur.ai/free/en/venues/emnlp/2020/)
- [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/) ×2: [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) ×2
- [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/): [NAACL 2025](https://md.research.elamur.ai/free/en/venues/naacl/2025/)

## Cited by

Papers of our library cite their works 207 times (of the 149,439 papers whose bibliographies we read); [50 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/hao-li/cited-by/).

Updated 1 November 2026