Papers by Lang Li
Exploring Large Language Models for Multi-Modal Out-of-Distribution Detection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. |
| Approach: | They propose to apply world knowledge to enhance OOD detection performance through selective generation from large language models (LLMs) they propose to extract visual objects from each image to fully capitalize on the aforementioned world knowledge. |
| Outcome: | The proposed method outperforms the state-of-the-art on visual OOD detection on in-distribution (ID) samples. |
RAG or Learning? Understanding the Limits of LLM Adaptation under Continuous Knowledge Drift in the Real World (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to update or supplement large language models struggle under continuous knowledge drift. |
| Approach: | They propose a dynamic event benchmark and time-aware retrieval baseline that captures how knowledge evolves over time. |
| Outcome: | The proposed method enables systematic evaluation of model adaptation under continuous knowledge drift. |
Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to improve mathematical reasoning require extensive datasets for training or depend on few-shot methods that compromise computational accuracy. |
| Approach: | They propose a training-free adaptation framework that efficiently equips general-purpose pre-trained language models with enhanced mathematical reasoning capabilities. |
| Outcome: | The proposed framework outperforms Qwen2.5-72B-Math-Instruct on MMLU-STEM with a score of 90.9%, compared to 87.3%. |
LEAF: Towards Lightweight Explainable Hateful Video Detection via Self-Grounding CoT Guided Stage-Wise Distillation (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for detecting hateful videos rely on opaque models with no insight into their decisions. |
| Approach: | They propose a lightweight, explainable video detection framework that distills "explainability" from LMMs into efficient Smaller Multimodal Models (SMMs) they use a self-grounded chain-of-thought mechanism to generate unbiased supervision signals for videos . |
| Outcome: | The proposed framework outperforms existing methods in detection accuracy and explainability on three video benchmarks. |
TEaR: Improving LLM-based Machine Translation with Systematic Self-Refinement (2025.findings-naacl)
Copied to clipboard
Zhaopeng Feng, Yan Zhang, Hao Li, Bei Wu, Jiayu Liao, Wenqiang Liu, Jun Lang, Yang Feng, Jian Wu, Zuozhu Liu
| Challenge: | Large Language Models (LLMs) have achieved impressive results in Machine Translation (MT). human evaluations reveal that LLM-generated translations still contain various errors. |
| Approach: | They propose a LLM-based self-refinement framework that feeds error information back into LLMs to facilitate self-finement, leading to enhanced translation quality. |
| Outcome: | The proposed framework outperforms internal refinement and feedback methods while ensuring a robust translation quality baseline. |
Fine-Tuning Language Models with Reward Learning on Policy (2024.naacl-long)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is an effective approach to align large language models (LLMs) to human preferences. |
| Approach: | They propose a framework that refines a reward model using policy samples to keep it on-distribution. |
| Outcome: | The proposed framework outperforms the state-of-the-art on three benchmark datasets showing that it can learn robust representations of policy samples. |
Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models (2026.acl-long)
Copied to clipboard
Zirui Song, Qian Jiang, Mingxuan Cui, Mingzhe Li, Lang Gao, Zeyu Zhang, Zixiang Xu, Yanbo Wang, Guangxian Ouyang, Zhenhao Chen, Xiuying Chen
| Challenge: | a recent study evaluated large audio-language models against jailbreak attacks . a new benchmark is being developed to evaluate LAM safety against jailbreaking attacks based on temporal and semantic nature of speech . |
| Approach: | They propose a benchmark to evaluate LAM jailbreak vulnerabilities in adversarial audio prompts . they use a dataset of 1,495 adversarials to evaluate their performance . |
| Outcome: | The proposed benchmark evaluates state-of-the-art LAMs against jailbreak attacks . it demonstrates that even small, semantically preserved perturbations can reduce safety . |
Out-of-Domain Intent Detection Considering Multi-Turn Dialogue Contexts (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for OOD intent detection are limited to single dialogue turns. |
| Approach: | They propose a context-aware OOD intent detection framework to model multi-turn contexts in OOD context detection tasks using unlabeled data. |
| Outcome: | The proposed framework improves the F1-OOD score by 29% on multi-turn OOD detection tasks compared to the previous best method. |
Test-Time Code-Switching for Cross-lingual Aspect Sentiment Triplet Extraction (2025.naacl-long)
Copied to clipboard
| Challenge: | Aspect Sentiment Triplet Extraction (ASTE) is a thriving research area . current code-switching methods suffer from term boundary detection issues and out-of-dictionary problems. |
| Approach: | They propose a test-time code-switching framework which bridges the gap between bilingual training and monolingual test- time prediction. |
| Outcome: | The proposed framework achieves an average improvement of 3.7% on four cross-lingual datasets. |
PRAM: An End-to-end Prototype-based Representation Alignment Model for Zero-resource Cross-lingual Named Entity Recognition (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to address the named entity recognition problem are limited and lack explicit optimization specific to the task. |
| Approach: | They propose a prototype-based representation alignment model for a cross-lingual named entity recognition task using labeled source language data. |
| Outcome: | The proposed model outperforms existing state-of-the-art methods in some challenging scenarios. |
Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions (2026.acl-long)
Copied to clipboard
| Challenge: | Recent reinforcement learning (RL) has been widely explored for adapting MCAs to various human-AI interaction scenarios. |
| Approach: | They propose to use a latent action space for reinforcement learning instead of RL to fine-tune MCAs. |
| Outcome: | The proposed method outperforms baselines on two conversation tasks with a novel cycle consistency loss. |
ClinicalTrialsHub: Bridging Registries and Literature for Comprehensive Clinical Trial Access (2026.eacl-demo)
Copied to clipboard
Jiwoo Park, Ruoqi Liu, Avani Jagdale, Andrew Srisuwananukorn, Jing Zhao, Lang Li, Ping Zhang, Sachin Kumar
| Challenge: | ClinicalTrialsHub consolidates clinical trial data from ClinicalTrial.gov and augments it by extracting and structuring trial-relevant information from PubMed. |
| Approach: | They propose a search-focused platform that consolidates PubMed data and extracts structured trial information. |
| Outcome: | ClinicalTrialsHub increases access to structured clinical trial data by 83.8% compared to ClinicalTrial.gov alone. |
Domain Incremental Lifelong Learning in an Open World (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to lifelong learning (LL) models require access to task identities in the testing phase or cannot handle samples from unseen tasks. |
| Approach: | They propose a dynamic architecture-based lifelong learning model that tries to learn a sequence of tasks with a prompt-enhanced language model. |
| Outcome: | The proposed model outperforms state-of-the-art models in handling unseen tasks and focuses on task-level prompts to capture knowledge from different granularities. |
Long-Tailed Question Answering in an Open World (2023.acl-long)
Copied to clipboard
| Challenge: | Existing QA approaches require access to seen tasks or do not explicitly model samples from unseen tasks. |
| Approach: | They propose an open-tailed QA model that encourages knowledge sharing between head, tail and unseen tasks and explicitly mines knowledge from a large pre-trained language model. |
| Outcome: | The proposed model outperforms the state-of-the-art on a large-scale dataset. |
MultiChartQA: Benchmarking Vision-Language Models on Multi-Chart Problems (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing chart understanding benchmarks focus on single-chart tasks, neglecting multi-hop reasoning required to extract and integrate information from multiple charts. |
| Approach: | They propose a benchmark that evaluates MLLMs’ capabilities in four key areas: direct question answering, parallel question answering and comparative reasoning. |
| Outcome: | The proposed benchmark evaluates MLLMs’ capabilities in four key areas: direct question answering, parallel question answering and comparative reasoning. |
Scaling Data Diversity for Fine-Tuning Language Models in Human Alignment (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) can reveal toxic or offensive content inadvertently or intentionally. |
| Approach: | They propose to control the diversity of both sides according to the number of samples for fine-tuning, which can directly reflect their impact. |
| Outcome: | The proposed approach improves the performance of large language models after fine-tuning. |
Thinking about GPT-3 In-Context Learning for Biomedical IE? Think Again (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Large pre-trained language models (PLMs) such as GPT-3 have shown strong in-context learning capabilities, which are appealing for domains such as biomedicine that feature high and diverse demands of language technologies but also high data annotation costs. |
| Approach: | They propose to compare the few-shot performance of GPT-3 in-context learning with fine-tuning smaller (i.e., BERT-sized) PLMs on two representative biomedical information extraction tasks: named entity recognition and relation extraction. |
| Outcome: | The proposed model underperforms on two representative biomedical information extraction tasks. |
Understanding Generalization in Role-Playing Models via Information Theory (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to characterize RPM generalization are inadequate . existing methods do not provide a fine-grained diagnosis of distribution shifts . |
| Approach: | They propose a reasoning-based effective mutual information difference (R-EMID) to measure RPM performance degradation in an interpretable way. |
| Outcome: | The proposed model predicts the worst-case generalization performance of RPMs and reveals how shifts contribute to degradation. |
When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)
Copied to clipboard
Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen
| Challenge: | Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation. |
| Approach: | They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts . |
| Outcome: | The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results. |
Estimating Soft Labels for Out-of-Domain Intent Detection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to detect out-of-dominance (OOD) intents are limited by the lack of OOD samples. |
| Approach: | They propose an adaptive soft pseudo labeling method that can estimate soft labels for pseudo OOD samples when training OOD detectors. |
| Outcome: | The proposed method outperforms competing methods on three benchmark datasets and consistently outperformed previous methods. |
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)
Copied to clipboard
Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui
| Challenge: | Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge. |
| Approach: | They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. |
| Outcome: | The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks. |
Counterfactual reasoning: Testing language models’ understanding of hypothetical scenarios (2023.acl-short)
Copied to clipboard
| Challenge: | Existing language models have demonstrated remarkable improvements in downstream tasks, but it remains unclear to what extent they are consequences of correlation with linguistic heuristics versus robust reasoning about causal relations grounded on understanding of world knowledge. |
| Approach: | They propose to test language models with counterfactual conditionals to test their ability to distinguish hypothetical scenarios from reality. |
| Outcome: | The proposed model overrides real-world knowledge in counterfactual scenarios, but most models are driven by lexical cues. |