Papers by Ping Luo
DSP: Discriminative Soft Prompts for Zero-Shot Entity and Relation Extraction (2023.findings-acl)
Copied to clipboard
| Challenge: | Prompt-based methods have shown their efficacy in transferring general knowledge within pre-trained language models (PLMs) however, when applied to zero-shot entity and relation extraction, they struggle with the limited coverage of verbalizers to labels and the slow inference speed. |
| Approach: | They propose a method which reformulates zero-shot tasks into token discrimination tasks without having to construct verbalizers. |
| Outcome: | The proposed method outperforms baselines on two zero-shot entity recognition datasets with higher inference speed and achieves 7.5% improvement over previous state-of-the-art models on Wiki-ZSL and FewRel. |
AttnComp: Attention-Guided Adaptive Context Compression for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for augmented large language models suffer from irrelevant retrieved content . existing methods struggle to adapt compression rates for different context, maintain low latency . |
| Approach: | We propose an adaptive, efficient and context-aware compression framework to reduce retrieved content . AttnComp uses a top-p compression algorithm to retain the minimal set of documents whose attention weights exceed a threshold. |
| Outcome: | Experiments show that AttnComp outperforms existing compression methods and uncompressed baselines in achieving higher accuracy with substantial compression rates and lower latency. |
Uncovering Limitations of Large Language Models in Information Seeking from Tables (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks for Table Information Seeking (TabIS) are lacking in reliable evaluation. |
| Approach: | They propose a benchmark to evaluate the table information seeking abilities of large language models . they use a single-choice question format instead of a text-based evaluation . |
| Outcome: | The proposed benchmark is more reliable than existing models and is available online. |
Structured Pruning for Efficient Generative Pre-trained Language Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Large-scale generative Pre-trained Language Models (PLMs) are limited in their deployment in real-world applications. |
| Approach: | They propose to prune the feed-forward networks of generative pre-trained language models to smaller widths without designing extra operators. |
| Outcome: | The proposed method achieves 1.51x/6.96x inference speedup on GPU/CPU with 67% size reduction. |
Guideline Learning for In-Context Information Extraction (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models can perform a task by conditioning on task instructions and a few input-output examples without optimizing any parameters. |
| Approach: | They propose a guideline learning framework for In-context IE which reflectively learns and follows guidelines. |
| Outcome: | The proposed framework improves the performance of in-context IE by synthesizing and following guidelines. |
Compression of Generative Pre-trained Language Models via Quantization (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods to compress generative pre-trained language models fail on generative tasks due to homogeneous word embeddings and limited memory. |
| Approach: | They propose a token-level contrastive distillation method to learn distinguishable word embeddings and a module-wise dynamic scaling method to make quantizers adaptive to different modules. |
| Outcome: | The proposed method outperforms the state-of-the-art compression methods on generative PLMs by a clear margin. |
Zero-shot Generative Linguistic Steganography (2024.naacl-long)
Copied to clipboard
| Challenge: | Generative linguistic steganography attempts to hide secret messages into covertext . previous studies focused on the statistical differences between the covertext and stegotext - however, ill-formed stegotas can readily be identified by humans . |
| Approach: | They propose a zero-shot approach based on in-context learning for linguistic steganography to achieve better perceptual and statistical imperceptibility. |
| Outcome: | The proposed method produces 1.926 more innocent and intelligible stegotext than any other method. |
Beyond Query Memorization: Large Language Model Routing with Query Decomposition and Historical Matching (2026.acl-long)
Copied to clipboard
Bo Lv, Jingbo Sun, Jianwei Lv, Chen Tang, Shaojie Zhang, Nayu Liu, Guoxin Yu, Zihao Li, Qichao Zhang, Dongbin Zhao, Ping Luo, Yue Yu
| Challenge: | Existing routing methods rely on direct mapping from queries to models based on surface-level features, leading to poor generalizability on out-of-distribution data. |
| Approach: | They propose a new routing framework that recasts the routing task as a matching process of sifting similar queries from historical logs. |
| Outcome: | The proposed framework improves matching accuracy while lowering inference costs . it decouples linguistic surface forms from task-intrinsic requirements . |
Lost in Overlap: Exploring Logit-based Watermark Collision in LLMs (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing watermarking methods embed imperceptible identifiers into text to address copyright concerns. |
| Approach: | They propose a new philosophy for watermark attacks that addresses watermark collision . they demonstrate that collision poses a threat to all logit-based watermark algorithms . |
| Outcome: | The proposed method improves watermark collision performance on top of other methods. |
Adaptive Graph Convolutional Network for Knowledge Graph Entity Alignment (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Entity alignment (EA) aims to identify equivalent entities from different Knowledge Graphs (KGs) noisy neighbors of entities transfer invalid information, drown out equivalent information, and ultimately reduce the performance of EA. |
| Approach: | They propose a method to deal with neighbor noises to reduce the performance of EA by capturing the differences and complementarities of multiple KGs. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods in supervised and unsupervised settings. |
URG: A Unified Ranking and Generation Method for Ensembling Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to rank and generate large language models have limited performance due to time-intensive nature of ranking process and lack of error propagation. |
| Approach: | They propose a framework that jointly ranks the outputs of Large Language Models and generates fine-grained fusion results. |
| Outcome: | The proposed framework achieves state-of-the-art (SOTA) performance on ranking and generation tasks. |
Plot2Code: A Comprehensive Benchmark for Evaluating Multi-modal Large Language Models in Code Generation from Scientific Plots (2025.findings-naacl)
Copied to clipboard
| Challenge: | Multi-modal Large Language Models have shown remarkable progress in visual contexts, yet their ability to convert visual figures into executable code remains underexplored. |
| Approach: | They propose to use a set of visual coding metrics to assess MLLMs' visual . pass rate, text-match ratio, and GPT-4V rating judgement to assess the quality of generated code and rendered images. |
| Outcome: | The proposed benchmark includes 132 high-quality matplotlib plots across six plot types, as well as 150 and 86 plots from Python’s and R’s plotly libraries respectively, totaling 368 plots. |
LLaMA Pro: Progressive LLaMA with Block Expansion (2024.acl-long)
Copied to clipboard
| Challenge: | Existing studies have demonstrated that pre-trained LLMs are limited in certain domains, such as programming, mathematics, biomedical, or finance. |
| Approach: | They propose a new post-pretraining method with an expansion of Transformer blocks to tune the expanded blocks using only new corpus, efficiently and effectively improving the model’s knowledge while mitigating forgetting. |
| Outcome: | The proposed model outperforms existing models in programming and math and its instruction-following counterpart LLaMA Pro-8.3B in general tasks, programming, and mathematics. |
TVWorld: Foundations for Remote-Control TV Agents (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing work on large vision–language models focuses on point-and-click interaction, while remote-control interaction is underexplored. |
| Approach: | They propose a topology-aware training framework that injects topology awareness into LVLMs. |
| Outcome: | The proposed model achieves 68.3% success rate on TVWorld-N, surpassing closed-source benchmarks and state-of-the-art (SOTA) benchmarks show that existing agents lack topology awareness for focus-based, long-horizon TV navigation. |
TAeKD: Teacher Assistant Enhanced Knowledge Distillation for Closed-Source Multilingual Neural Machine Translation (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have produced impressive results in the field of Multilingual Neural Machine Translation (MNMT). |
| Approach: | They propose a Teacher Assistant enhanced Knowledge Distillation method to augment knowledge transfer capacity from closed-source MNMT models. |
| Outcome: | The proposed method outperforms the state-of-the-art KD methods on both WMT22 and FLORES-101 test sets. |
Text2World: Benchmarking Large Language Models for Symbolic World Model Generation (2025.findings-acl)
Copied to clipboard
Mengkang Hu, Tianxing Chen, Yude Zou, Yuheng Lei, Qiguang Chen, Ming Li, Yao Mu, Hongyuan Zhang, Wenqi Shao, Ping Luo
| Challenge: | Recent studies have encountered limitations in leveraging large language models to generate symbolic world models. |
| Approach: | They propose a benchmarking framework based on planning domain definition language (PDDL) that employs multi-criteria, execution-based metrics for a more robust evaluation. |
| Outcome: | The proposed model outperforms models trained with large-scale reinforcement learning, but lacks the robustness needed to perform in world modeling. |
Attention with Dependency Parsing Augmentation for Fine-Grained Attribution (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing fine-grained attribution methods rely on model-internal similarity metrics but lack a fine-grain representation of the data. |
| Approach: | They propose to use model-internal similarity metrics to validate RAG-generated content . they aggregate token-wise evidence through set union operations and integrate dependency parsing to enrich the semantic completeness of target spans. |
| Outcome: | The proposed method outperforms all prior works in the validation of RAG-generated content. |
KET-QA: A Dataset for Knowledge Enhanced Table Question Answering (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing datasets that ignore the challenge of missing knowledge in TableQA are limited in their use. |
| Approach: | They propose to use a knowledge base as the external knowledge source for TableQA and construct a dataset with fine-grained gold evidence annotation. |
| Outcome: | The proposed model achieves remarkable performance improvements on three different settings, but still lags behind the human-level performance. |
HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize agent performance by incorporating entire historical action-observation pairs into LLMs are redundant in long-horizon tasks. |
| Approach: | They propose a framework that leverages subgoals as memory chunks to manage working memory of LLM-based agents hierarchically. |
| Outcome: | The proposed framework achieves a twofold increase in success rate and reduces the average number of steps required by 3.8. |
ChartAssistant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning (2024.findings-acl)
Copied to clipboard
| Challenge: | Charts are an effective tool for understanding data patterns, but their combination of graphical elements and textual components poses challenges for general-purpose multimodal models. |
| Approach: | They propose a chart-based vision-language model for universal chart comprehension and reasoning that leverages a dataset of chart-related tasks. |
| Outcome: | The proposed model outperforms the state-of-the-art charts with zero-shot setting on various chart tasks. |
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysis (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) enriches the input to LLMs by retrieving information from the relevant knowledge database. |
| Approach: | They propose to use a knowledge database to enrich the input of LLMs by retrieving information from the relevant knowledge database. |
| Outcome: | The proposed approach can achieve 98% true positive rate while maintaining a false positive rate close to 1%. |
Whether LLMs Know If They Know: Identifying Knowledge Boundaries via Debiased Historical In-Context Learning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for active retrieval (AR) rely on training classification models or using the confidence of the model’s answer to determine knowledge boundaries. |
| Approach: | They propose a method to identify knowledge boundaries in active retrieval by retrieving historical queries as high-confidence in-context examples. |
| Outcome: | Experiments on four QA benchmarks show that DH-ICL achieves performance comparable to full retrieval on LLaMA with only half the number of retrievals, without any additional training. |
EfficientQAT: Efficient Quantization-Aware Training for Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Quantization-aware training (QAT) is a low-bit training solution that requires substantial training resources. |
| Approach: | They propose an algorithm that reduces memory consumption by low-bit representations with minimal accuracy loss. |
| Outcome: | EfficientQAT achieves 2-bit Llama-2-70B model on single GPU in 41 hours . compared to previous methods, it obtains model with less than 3 points accuracy degradation . |
Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing multi-document QA benchmarks require information from only a few documents with limited cross-document reasoning. |
| Approach: | They propose a benchmark for multi-document analytical QA that extracts and synthesizes information across multiple documents to perform quantitative analysis. |
| Outcome: | The proposed approach improves both process and outcome metrics but still has bottlenecks compared to human experts. |