Papers by Zhiyuan Wang
Recyclable Tuning for Continual Pre-training (2023.findings-acl)
Copied to clipboard
Yujia Qin, Cheng Qian, Xu Han, Yankai Lin, Huadong Wang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie Zhou
| Challenge: | Continual pre-training is the paradigm where pre-trained language models acquire fresh knowledge and gradually get upgraded. |
| Approach: | They propose to use adapted weights to recycle old PLMs for continual pre-training . they propose to combine initialization and distillation methods to achieve better performance . |
| Outcome: | The proposed method improves the convergence and performance of the upgraded PLM. |
FLIQA-AD: a Fusion Model with Large Language Model for Better Diagnose and MMSE Prediction of Alzheimer’s Disease (2025.naacl-short)
Copied to clipboard
| Challenge: | Existing classification and regression models that only extract finer-grained information from magnetic resonance imaging (MRI) may not be effective for Alzheimer's disease (AD). |
| Approach: | They propose to use a 3D Adapter in a Vision Transformer to extract the patient's EHR information and questions related to the disease as text prompts. |
| Outcome: | The proposed model can discriminate and predict the corresponding MMSE score based on the extracted brain structural information and textual content . |
MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Text-guided image editing has seen significant progress in natural image domains, but its application in medical imaging remains limited. |
| Approach: | a new benchmark is designed to diagnose reliability in text-guided medical image editing. a clinically grounded evaluation framework measures Editing Accuracy, Context Preservation, and Visual Quality. |
| Outcome: | a new benchmark is designed to diagnose reliability in medical image editing. |
Disentangled Multi-span Evolutionary Network against Temporal Knowledge Graph Reasoning (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for temporal knowledge Graphs neglect internal structural interactions between subgraphs and ignore potential smooth features that do not lead to semantic changes. |
| Approach: | They propose to use a disentangled multi-span evolutionary network to capture local neighbor features while perceiving historical neighbor semantic information. |
| Outcome: | Extensive experiments show that the proposed model outperforms the state-of-the-art in TKG reasoning by 22.7%. |
MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter (2023.emnlp-main)
Copied to clipboard
| Challenge: | Language Models (LMs) have demonstrated impressive molecule understanding ability on 1D text-related tasks, but lack 2D graph perception, a critical ability of human professionals in comprehending molecules’ topological structures. |
| Approach: | They propose to combine a cross-modal projector and a uni-modal adapter to enable an LM to understand both text- and graph-based molecular contents via a Q-Former. |
| Outcome: | The proposed model outperforms the baselines on tasks such as molecule captioning, IUPAC name prediction, and molecule-text retrieval. |
Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification (2022.acl-long)
Copied to clipboard
| Challenge: | Recent studies suggest that pre-trained language models have gained rich knowledge during pre-training. |
| Approach: | They propose to tune pre-trained language models with task-specific prompts to improve and stabilize prompttuning. |
| Outcome: | Extensive experiments on zero and few-shot text classification tasks show that prompt-tuning improves and stabilizes prompttun-ing. |
Sparse Low-rank Adaptation of Pre-trained Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning pre-trained large language models in a parameter-efficient manner are gaining traction within the research community. |
| Approach: | They propose a method of low-rank adaptation that enables dynamic adjustments to the intrinsic rank during the adaptation process. |
| Outcome: | The proposed approach outperforms the current method with a fixed and unalterable intrinsic rank and a low-rank adaptation process. |
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for defending NLP models against backdoors have ignored the clean weights of PLMs. |
| Approach: | They exploit pre-trained weights to mitigate backdoors in fine-tuned NLP models . they use a fine-mixing technique and an Embedding Purification technique to do the same . |
| Outcome: | The proposed method outperforms baseline mitigation methods on three single-sentence sentiment classification tasks and two sentence-pair classification tasks. |
Repairing Catastrophic-Neglect in Text-to-Image Diffusion Models via Attention-Guided Feature Enhancement (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Text-to-Image Diffusion models generate high-quality images from textual descriptions, but they often produce images that do not fully align with the input prompts, resulting in semantic inconsistencies. |
| Approach: | They propose an automated repair approach to address catastrophic-neglect in T2I DMs. |
| Outcome: | The proposed model achieves 10.1%-16.3% higher Correct Rate in image generation compared to baselines. |
RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework (2025.acl-long)
Copied to clipboard
Kunlun Zhu, Yifan Luo, Dingling Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Ruobing Wang, Shuo Wang, Yishan Li, Nan Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing evaluation metrics for RAG systems are lacking due to high costs of data construction and lack of factual accuracy. |
| Approach: | They propose a framework to evaluate RAG systems in specialized scenarios . they propose three new metrics to evaluate LLM-generated responses . |
| Outcome: | The proposed framework outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples. |
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators (2025.findings-acl)
Copied to clipboard
Jianling Li, ShangZhan Li, Zhenye Gao, Qi Shi, Yuxuan Li, Zefan Wang, Jiacheng Huang, WangHaojie WangHaojie, Jianrong Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Triton is a high-level Python-like programming language for building efficient GPU kernels. |
| Approach: | They propose a TritonBench benchmark that provides a comprehensive evaluation of Tritonic operators on widely deployed GPUs. |
| Outcome: | The proposed benchmarks show that current LLMs struggle to generate efficient Triton operators on widely deployed GPUs aligned with industry applications. |
On LLM-Based Scientific Inductive Reasoning Beyond Equations (2025.emnlp-main)
Copied to clipboard
Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing research on inductive reasoning models emphasizes rule design without grounding them in specific scenarios. |
| Approach: | They propose to use LLMs to learn underlying patterns from limited examples in entirely new environments. |
| Outcome: | The proposed benchmark evaluates the inductive reasoning abilities of large language models in scientific settings. |
MAVEN: A Massive General Domain Event Detection Dataset (2020.emnlp-main)
Copied to clipboard
Xiaozhi Wang, Ziqi Wang, Xu Han, Wangyi Jiang, Rong Han, Zhiyuan Liu, Juanzi Li, Peng Li, Yankai Lin, Jie Zhou
| Challenge: | Existing datasets exhibit data scarcity and limited coverage of general-domain events. |
| Approach: | They present a MAssive eVENt detection dataset which contains 4,480 Wikipedia documents and 168 event types. |
| Outcome: | The proposed dataset shows that existing methods cannot achieve promising results on the small datasets. |
MAVEN-ARG: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation (2024.acl-long)
Copied to clipboard
Xiaozhi Wang, Hao Peng, Yong Guan, Kaisheng Zeng, Jianhui Chen, Lei Hou, Xu Han, Yankai Lin, Zhiyuan Liu, Ruobing Xie, Jie Zhou, Juanzi Li
| Challenge: | Existing datasets for event understanding have limited coverage due to complexity of tasks. |
| Approach: | They propose a dataset that augments MAVEN datasets with event argument annotations . they propose 98,591 events and 290,613 arguments obtained with laborious human annotation . |
| Outcome: | The proposed dataset is the first all-in-one dataset supporting event detection, event argument extraction, and event relation extraction. |
I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing (2026.acl-long)
Copied to clipboard
Jinghan Yu, Junhao Xiao, Chenyu Zhu, Jiaming Li, Jia Li, HanMing Deng, Xirui Wang, Guoli Jia, Jianjun Li, Xiang Bai, Bowen Zhou, Zhiyuan Ma
| Challenge: | Existing text-guided image editing methods rely on end-to-end pixel-level inpainting paradigm . existing models lack such intermediate representations and Reasoning-then-action process . |
| Approach: | They propose a "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment. |
| Outcome: | The proposed paradigm outperforms existing methods in compositional editing tasks. |
Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry (2026.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) achieve high accuracy on established Classical Chinese Poetry benchmarks, but it remains challenging to distinguish transferable Linguistic-Aesthetic Reasoning from reliance on familiar pre-training patterns. |
| Approach: | They propose a benchmark that combines a constructionist Out-of-Sample dataset with reverse understanding probes to evaluate large-scale large-format models. |
| Outcome: | The proposed model performs well on classical Chinese poetry benchmarks, but a performance gap persists . the model can complete famous couplets and can be used to understand a variety of texts. |
COPEN: Probing Conceptual Knowledge in Pre-trained Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge probing studies focus on evaluating factual knowledge of pre-trained language models (PLMs) but ignore conceptual knowledge. |
| Approach: | They evaluate conceptual knowledge of pre-trained language models by annotating 24k data instances covering 393 concepts. |
| Outcome: | The proposed tasks evaluate pre-trained language models' conceptual knowledge of entities, learn conceptual properties, and conceptualize entities in contexts. |
ProQA: Structural Prompt-based Pre-training for Unified Question Answering (2022.naacl-main)
Copied to clipboard
Wanjun Zhong, Yifan Gao, Ning Ding, Yujia Qin, Zhiyuan Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan
| Challenge: | Existing QA research on question answering is focused on specific question types, knowledge domains, or reasoning skills. |
| Approach: | They propose a unified QA paradigm that solves various tasks through a single model. |
| Outcome: | The proposed model improves QA-centric ability on 11 QA benchmarks. |
Mirror-Consistency: Harnessing Inconsistency in Majority Voting (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are a widely-used decoding strategy that relies on the plurality voting rule, which focuses on the most frequent answer while overlooking all other minority responses. |
| Approach: | They propose to incorporate a ‘reflective mirror’ into the self-ensemble decoding process and enables LLMs to critically examine inconsistencies among multiple generations. |
| Outcome: | The proposed method incorporates a ‘reflective mirror’ into the self-ensemble decoding process and enables LLMs to critically examine inconsistencies among multiple generations. |
LoRA-Flow: Dynamic LoRA Fusion for Large Language Models in Generative Tasks (2024.acl-long)
Copied to clipboard
| Challenge: | LoRA-Flow uses lightweight modules to customize large language models for downstream tasks . previous work on LoRA combination relied on task-level weights for each involved LoRA . |
| Approach: | They propose a LoRA-Flow approach that uses dynamic weights to adjust the impact of different LoRAs. |
| Outcome: | The proposed method outperforms baselines with task-level weights on six generative tasks. |
ProtT3: Protein-to-Text Generation for Text-based Protein Understanding (2024.acl-long)
Copied to clipboard
| Challenge: | Language Models excel in understanding textual descriptions of proteins, but struggle to process texts. |
| Approach: | They propose a framework for Protein-to-Text Generation for Text-based Protein Understanding that integrates a PLM as its protein understanding module. |
| Outcome: | The proposed framework surpasses existing baselines and is highly efficient in protein-to-text generation. |
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing (2026.acl-industry)
Copied to clipboard
Junbo Niu, Zheng Liu, Zhuangcheng Gu, Bin Wang, Linke Ouyang, Zhiyuan Zhao, Tao Chu, Tianyao He, Fan Wu, Qintong Zhang, Zhenjiang Jin, Guang Liang, Rui Zhang, Wenzheng Zhang, Yuan Qu, Zhifei Ren, Yuefeng Sun, Zirui Tang, Boyu Niu, Yuanhong Zheng, Dongsheng Ma, Ziyang Miao, Hejun Dong, Siyi Qian, Junyuan Zhang, Fangdong Wang, Jingzhou Chen, Xiaomeng Zhao, Liqun Wei, Wei Li, Shasha Wang, RuiLiang Xu, Yuanyuan Cao, Lu Chen, Qianqian Wu, Huaiyu Gu, Lindong Lu, Dechen Lin, null Shenguanlin, Xuanhe Zhou, Linfeng Zhang, Yuhang Zang, Xiaoyi Dong, Jiaqi Wang, Bo Zhang, Lei Bai, Pei Chu, Weijia Li, Jiang Wu, Lijun Wu, Zhenxiang Li, Guangyu Wang, Zhongying Tu, Chao Xu, Kai Chen, Bowen Zhou, Dahua Lin, Wentao Zhang, Conghui He
| Challenge: | Document images are characterized by higher resolutions, denser content, and more complex structural layouts. |
| Approach: | They propose a 1.2B-parameter document parsing vision-language model that decouples layout analysis from local content recognition. |
| Outcome: | The proposed model surpasses general-purpose and domain-specific models on multiple benchmarks while maintaining significantly lower computational overhead. |
LLM×MapReduce-V3: Enabling Interactive In-Depth Survey Generation through a MCP-Driven Hierarchically Modular Agent System (2025.emnlp-demos)
Copied to clipboard
Yu Chao, Siyu Lin, Xiaorong Wang, Zhu Zhang, Zihan Zhou, Haoyu Wang, Shuo Wang, Jie Zhou, Zhiyuan Liu, Maosong Sun
| Challenge: | Generating high-quality long-form survey articles poses significant challenges to AI Agent systems. |
| Approach: | They propose a hierarchically modular agent system for long-form survey generation . they use atomic models to implement skeleton initialization, digest construction, and skelet refinement . human evaluations demonstrate system surpasses representative baselines . |
| Outcome: | The proposed system surpasses representative baselines in both content depth and length, highlighting the strength of MCP-based modular planning. |
Adversarial Training for Weakly Supervised Event Detection (N19-1)
Copied to clipboard
| Challenge: | Detecting and identifying events is an important subtask of event extraction. |
| Approach: | They build a large event-related candidate set with good coverage and apply an adversarial training mechanism to iteratively identify informative instances from the candidate set and filter out those noisy ones. |
| Outcome: | The proposed method significantly outperforms the state-of-the-art methods on two real-world datasets. |
Few-shot Classification with Hypersphere Modeling of Prototypes (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fewshot learning use embeddings in space, but they lack expressivity and are difficult to perform statistically. |
| Approach: | They propose a method where class information is represented by hyperspheres with dynamic sizes with two sets of learnable parameters: the hypersphere’s center and the radius. |
| Outcome: | The proposed method is much more expressive than embeddings and performs better than statistical modeling. |
Multimodal Causal Reasoning Benchmark: Challenging Multimodal Large Language Models to Discern Causal Links Across Modalities (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing MLLMs lack robustness in multimodal causal reasoning compared to their performance in textual settings. |
| Approach: | They propose a novel multimodal chain-of-thought (CoT) reasoning benchmark that leverages siamese images and text pairs to challenge MLLMs. |
| Outcome: | The proposed benchmark leverages siamese images and text pairs to challenge MLLMs. |
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation (2021.tacl-1)
Copied to clipboard
| Challenge: | Existing language representation models (PLMs) cannot capture factual knowledge from text. |
| Approach: | They propose a unified model for Knowledge Embedding and Pre-trained LanguagERepresentation which integrates factual knowledge into PLMs and produces effective text-enhanced KE with the strong PLM. |
| Outcome: | The proposed model improves on existing pre-trained language representation models and improves their performance on various NLP tasks. |
Exploring Lottery Prompts for Pre-trained Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to optimize pre-trained language models are expensive and slow to scale. |
| Approach: | They propose to search for instance-level lottery prompts and generalize them to unseen data . they validate the assumption that for every instance, there is almost always a lottery prompt that induces the correct prediction from the PLM . |
| Outcome: | The proposed method can achieve comparable results with other gradient-free and optimization-free baselines. |
UltraEval-Audio: A Unified Framework for Comprehensive Evaluation of Audio Foundation Models (2026.acl-demo)
Copied to clipboard
Qundong Shi, Jie Zhou, Biyuan Lin, Junbo Cui, Guoyang Zeng, Yixuan Zhou, Ziyang Wang, Xin Liu, Zhen Luo, Yudong Wang, Zhiyuan Liu
| Challenge: | Existing evaluation frameworks for audio foundation models are heavily reliant on English, making it difficult to objectively assess models’ performance on Chinese. |
| Approach: | They propose a unified framework that supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards. |
| Outcome: | The proposed framework supports 10 languages, 14 task categories, 24 models, and 36 benchmarks with one-command evaluation and real-time leaderboards. |
ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Existing open-source MLLMs fail to fully capture dense information embedded in charts . current models still face significant challenges in understanding and analyzing visual tasks such as captioning and question answering. |
| Approach: | They propose a chart-to-code MLLM which leverages Code LLMs as the language backbone to enhance the executability of the generated code. |
| Outcome: | The proposed model surpasses existing open-source models on chart-to-code benchmarks with only 7B parameters and provides lossless representations that contain all critical details. |
HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference (2026.acl-long)
Copied to clipboard
| Challenge: | Existing static compression methods suffer from coarse-grained caching and high I/O overhead. |
| Approach: | They propose a training-free dynamic compression framework that uses a sparse attention mechanism to categorize attention heads based on stability and similarity. |
| Outcome: | The proposed framework achieves state-of-the-art performance on long-context benchmarks and accelerates decoding by up to 3 compared to the original model with a 224K context. |
HyKGE: A Hypothesis Knowledge Graph Enhanced RAG Framework for Accurate and Reliable Medical LLMs Responses (2025.acl-long)
Copied to clipboard
Xinke Jiang, Ruizhe Zhang, Yongxin Xu, Rihong Qiu, Yue Fang, Zhiyuan Wang, Jinyi Tang, Hongxin Ding, Xu Chu, Junfeng Zhao, Yasha Wang
| Challenge: | Recent approaches suffer from insufficient and repetitive knowledge retrieval, tedious and time-consuming query parsing, and monotonous knowledge utilization. |
| Approach: | They propose a retrieval-augmented generation framework which leverages LLMs’ powerful reasoning capacity to compensate for the incompleteness of user queries. |
| Outcome: | The proposed framework improves the accuracy and reliability of Large Language Models (LLMs) by combining the rich knowledge of LLMs with Hypothesis Outputs. |
AgentCPM-GUI: Building Mobile-Use Agents with Reinforcement Fine-Tuning (2025.emnlp-demos)
Copied to clipboard
Zhong Zhang, Yaxi Lu, Yikun Fu, Yupeng Huo, Shenzhi Yang, Yesai Wu, Han Si, Xin Cong, Haotian Chen, Yankai Lin, Xie Xie, Wei Zhou, Wang Xu, Zhou Su, Zhongwu Zhai, Xiaoming Liu, null Meiyudong, Jianming Xu, Hongyan Tian, Chongyi Wang, Chi Chen, Yuan Yao, Zhiyuan Liu, Maosong Sun
| Challenge: | Large language model agents have enabled GUI-based automation, but their deployment is limited by noisy data, poor generalization, and lack of support for non-English GUIs. |
| Approach: | They propose an 8B-parameter GUI agent built for robust and efficient on-device GUI interaction. |
| Outcome: | The proposed GUI agent achieves promising performance on five public benchmarks and proposed Chinese benchmark CAGUI. |
Few-NERD: A Few-shot Named Entity Recognition Dataset (2021.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to few-shot named entity recognition (NER) focus on coarse-grained entities with few examples, while most unseen entities are fine-grounded. |
| Approach: | They present a human-annotated few-shot named entity recognition dataset . they construct benchmark tasks to assess the generalization capability of models . |
| Outcome: | The proposed model is the first few-shot NER dataset and the largest human-crafted NER data set. |
KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases (2025.findings-emnlp)
Copied to clipboard
Zheni Zeng, Yuxuan Chen, Shi Yu, Ruobing Wang, Yukun Yan, Zhenghao Liu, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing methods for retrieval-augmented generation (RAG) are limited and fine-tuning incurs prohibitive costs of external signals. |
| Approach: | They propose a self-supervised framework that enhances RAG systems through efficient model adaptation. |
| Outcome: | The proposed framework achieves 90% of the performance gain obtained through GPT-4-supervised adaptation while relying entirely on self-annotation of much smaller models. |
ReactXT: Understanding Molecular “Reaction-ship” via Reaction-Contextualized Molecule-Text Pretraining (2024.findings-acl)
Copied to clipboard
Zhiyuan Liu, Yaorui Shi, An Zhang, Sihang Li, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, Tat-Seng Chua
| Challenge: | Molecular-text modeling is an emerging research field that aims to facilitate molecule-relevant tasks with a textual interface and textual knowledge. |
| Approach: | They propose a new method for reaction-text modeling that uses three types of input contexts to incrementally pretrain LMs. |
| Outcome: | The proposed method improves experimental procedure prediction and molecule captioning and offers competitive results in retrosynthesis. |
GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification (P19-1)
Copied to clipboard
| Challenge: | Existing methods to extract information from evidence are unable to grasp relational and logical information among the evidence. |
| Approach: | They propose a graph-based evidence aggregating and reasoning framework to integrate evidence from multiple pieces of evidence. |
| Outcome: | The proposed framework achieves significant performance improvements on a large-scale benchmark dataset. |
MolTC: Towards Molecular Relational Modeling In Language Models (2024.findings-acl)
Copied to clipboard
Junfeng Fang, Shuai Zhang, Chang Wu, Zhengyi Yang, Zhiyuan Liu, Sihang Li, Kun Wang, Wenjie Du, Xiang Wang
| Challenge: | Molecular Relational Learning (MRL) is a promising way to understand interactions between molecular pairs. |
| Approach: | They propose a novel LLM-based multi-modal framework for molecular interaction modeling following Chain-of-Thought (CoT) theory which integrates graphical information of two molecules in pair. |
| Outcome: | The proposed framework integrates graphical information of two molecules in pair. |
RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository (2026.acl-long)
Copied to clipboard
Zhiyuan Peng, Xin Yin, Pu Zhao, Fangkai Yang, Lu Wang, Ran Jia, Xu Chen, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang
| Challenge: | Existing benchmarks focus on isolated function/class-level generation, neglecting complete microservice repository generation. |
| Approach: | They propose a multilingual benchmark for repository-level end-to-end web microservice generation that reflects real-world development workflows. |
| Outcome: | The benchmark compared 106 repositories across 18 domains and 11 frameworks and 1,258 API endpoints and 2,335 test cases. |
Prompt Tuning for Discriminative Pre-trained Language Models (2022.findings-acl)
Copied to clipboard
Yuan Yao, Bowen Dong, Ao Zhang, Zhengyan Zhang, Ruobing Xie, Zhiyuan Liu, Leyu Lin, Maosong Sun, Jianyong Wang
| Challenge: | Recent studies have shown promising results of prompt tuning in stimulating pre-trained language models (PLMs) for natural language processing tasks. |
| Approach: | They propose a prompt tuning framework that reformulates NLP tasks into a discriminative language modeling problem. |
| Outcome: | The proposed framework improves on text classification and question answering tasks and prevents unstable tuning problems in low-resource settings. |
Decode with Template: Content Preserving Sentiment Transfer (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods to transfer sentiments for text use only explicit sentiments and templates to remove them from input sentences. |
| Approach: | They propose a method to transfer sentiments from input sentences to output sentences using templates. |
| Outcome: | The proposed model significantly outperforms state-of-the-art models in content preservation. |
Neural Gibbs Sampling for Joint Event Argument Extraction (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for event argument extraction cannot adequately model the correlation between event arguments and their roles. |
| Approach: | They propose a Bayesian model to jointly extract event arguments using Gibbs sampling . they train two neural networks to model prior distribution and conditional distribution over event arguments . |
| Outcome: | The proposed model can achieve comparable results to existing methods on two widely-used datasets. |
Sub-Character Tokenization for Chinese Pretrained Language Models (2023.tacl-1)
Copied to clipboard
Chenglei Si, Zhengyan Zhang, Yingfa Chen, Fanchao Qi, Xiaozhi Wang, Zhiyuan Liu, Yasheng Wang, Qun Liu, Maosong Sun
| Challenge: | Existing tokenization methods for Chinese PLMs treat each character as an indivisible token, but ignore the unique feature of the writing system where additional linguistic information exists below the character level. |
| Approach: | They propose to encode Chinese characters into short sequences and construct Chinese vocabulary based on the encoded text. |
| Outcome: | The proposed tokenizers can tokenize inputs into much shorter sequences, improving computational efficiency. |
Gumbel Reranking: Differentiable End-to-End Reranker Optimization (2025.acl-long)
Copied to clipboard
Siyuan Huang, Zhiyuan Ma, Jintao Du, Changhua Meng, Weiqiang Wang, Jingwen Leng, Minyi Guo, Zhouhan Lin
| Challenge: | Existing distillation-based approaches suffer from training-inference misalignment and fail to capture interdependencies among candidate documents. |
| Approach: | They propose a method to optimize rerankers by learning a stochastic, document-wise Top-k attention mask using the Gumbel Trick and Relaxed Top-K Sampling. |
| Outcome: | The proposed framework minimizes the overall language loss and improves recall on hotpotQA. |
ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for predicting chemical reactions are limited by insufficient training data and inability to utilize textual information. |
| Approach: | They propose a framework that leverages chemical knowledge encoded in language models to assist GNNs, thereby enhancing the accuracy of real-world chemical reaction predictions. |
| Outcome: | The proposed framework improves state-of-the-art GNN-based methods across chemical reaction datasets especially in out-of distribution settings. |
RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents (2026.acl-long)
Copied to clipboard
Jize Wang, Han Wu, Zhiyuan You, Yiming Song, Yijun Wang, Zifei Shan, Yining Li, Songyang Zhang, Xinyi Le, Cailian Chen, Xinping Guan, Dacheng Tao
| Challenge: | Existing methods for mixing-of-agents (MoA) lack model selection criteria and struggle with large model pools. |
| Approach: | They propose a mixture-of-agents framework with dynamic routing that uses a lightweight scorer to perform initial screening and refines the model scores through self- and cross-assessment. |
| Outcome: | The proposed framework outperforms existing methods for large model pools and tasks . it reduces cost by 89.8% and latency by 63.6% in the large-scale model pool. |
ITAKE: Interactive Unstructured Text Annotation and Knowledge Extraction System with LLMs and ModelOps (2024.acl-demos)
Copied to clipboard
| Challenge: | Unstructured text data contains a large amount of valuable knowledge, but there are many tools that do not meet the needs of actual business. |
| Approach: | They propose an unstructured text annotation and knowledge extraction system that integrates Large Language Models and ModelOps to improve model supervision and performance. |
| Outcome: | The proposed system integrates large language models and ModelOps to improve performance in low-resource contexts. |
RA2FD: Distilling Faithfulness into Efficient Dialogue Systems (2024.emnlp-main)
Copied to clipboard
| Challenge: | Retrieval Augmented Generation (RAG) is effective but inference inefficient, while Retrieral Free Generations (RFG) are more efficient but sacrifice faithfulness. |
| Approach: | They propose a retrieval-free model training scheme that uses a teacher-student framework to distill the faithfulness capacity of a student's knowledge-infused responses. |
| Outcome: | The proposed model surpasses the previous SOTA RFG model on knowledge-grounded dialogue datasets by an average of 33% while improving inference efficiency. |
READIN: A Chinese Multi-Task Benchmark with Realistic and Diverse Input Noises (2023.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for Chinese inputs often lack a realistic representation of real-world noises. |
| Approach: | They construct a Chinese multi-task benchmark with REalistic and Diverse input noises . they use pinyin input and speech input to recruit speakers from diverse dialects based on their inputs - a feature that is important for Chinese NLP benchmarks if it is implemented in real-world applications. |
| Outcome: | The proposed benchmarks are based on four different tasks and are designed to maximize diversity. |
ExpanRL: Hierarchical Reinforcement Learning for Course Concept Expansion in MOOCs (2020.aacl-main)
Copied to clipboard
| Challenge: | Existing methods for concept expansion in MOOCs are inefficient because of the diversity of MOOC courses and rapid updates. |
| Approach: | They propose an end-to-end hierarchical reinforcement learning (HRL) model for concept expansion in MOOCs that employs a two-level mechanism of seed selection and concept expansion. |
| Outcome: | The proposed model improves on nine real MOOC datasets and maintains competitive performance under different settings. |
LSTPrompt: Large Language Models as Zero-Shot Time Series Forecasters by Long-Short-Term Prompting (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing prompting methods oversimplify time-series forecasting (TSF) time-Series data are ubiquitous across various domains, including public health, finance and energy. |
| Approach: | They propose a method for prompting off-the-shelf Large Language Models (LLMs) they decompose TSF into short-term and long-term forecasting sub-tasks, tailoring prompts to each . |
| Outcome: | The proposed approach decomposes TSF into short-term and long-term forecasting sub-tasks, tailoring prompts to each. |
Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forward (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Vision Language Models (LVLMs) have shown impressive performance on various vision-language tasks. |
| Approach: | They propose a benchmark framework for evaluating Visual Variation Robustness of Large Vision Language Models that incorporates automated evaluation dataset generation and principled metrics for thorough robustness assessment. |
| Outcome: | The proposed framework identifies a vulnerability to visual variations affecting even advanced models that excel at complex vision-language tasks but significantly underperform on simple tasks like object recognition. |
Enhancing Advanced Visual Reasoning Ability of Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models’ advanced reasoning ability. |
| Approach: | They propose a novel multi-modal in-context learning methodology to enhance LLMs’ contextual understanding and reasoning. |
| Outcome: | The proposed model achieves SOTA performance among all visual reasoning tasks and achieves a 'higher level of accuracy' than previous models. |
CE-VDG: Counterfactual Entropy-based Bias Reduction for Video-grounded Dialogue Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to reduce question-related bias in video-grounded dialogue generation (VDG) however, the dataset often contains inherent bias, which can cause VDG models to learn spurious correlations between questions and answers. |
| Approach: | They propose to extend the counterfactual reasoning from the information entropy perspective to the generative task, which can effectively reduce the question-related bias in the auto-regressive generation task. |
| Outcome: | The proposed method can reduce question-related bias in the auto-regressive generation task by using counterfactual entropy as an external loss. |
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding (2024.emnlp-main)
Copied to clipboard
Weilin Zhao, Yuxiang Huang, Xu Han, Wang Xu, Chaojun Xiao, Xinrong Zhang, Yewei Fang, Kaihuo Zhang, Zhiyuan Liu, Maosong Sun
| Challenge: | Speculative decoding is a widely used method that accelerates the generation process of large language models (LLMs) drafting efficiency has become a bottleneck in the final speedup of speculative drafting, therefore generating longer drafts at less cost can lead to better speedup. |
| Approach: | They propose a method that uses existing model to drafting and target LLM to verify draft in a low-cost parallel manner. |
| Outcome: | The proposed method can achieve speedups of up to 2.4 over speculative decoding and 3.9 over vanilla decoding without fine-tuning draft and target models. |
Emergent Modularity in Pre-trained Transformers (2023.findings-acl)
Copied to clipboard
Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Chaojun Xiao, Xiaozhi Wang, Xu Han, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Jie Zhou
| Challenge: | Existing studies on pre-trained Transformers show that they learn fine-grained neuron functions. |
| Approach: | They examine the presence of modularity in pre-trained Transformers . they focus on Mixture-of-Experts, a promising candidate for modularity . |
| Outcome: | The proposed structure stabilizes at the early stage, which is faster than neuron stabilization. |
Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing jailbreak attacks primarily utilize scenario camouflage techniques, however their explicit mention of malicious intent will be easily recognized and defended by LLMs. |
| Approach: | They propose an indirect jailbreak attack approach, Puzzler, which can bypass LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query. |
| Outcome: | The proposed approach can bypass the LLM’s defensive strategies and obtain malicious response by implicitly providing LLMs with some clues about the original malicious query. |
CAR: Empowering Agents with Dynamic Tool Synthesis and Global Trajectory Rectification (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM agents are brittle in open-ended environments due to two limitations: 1) a closed action space; 2) myopic error recovery. |
| Approach: | They propose a novel architecture that augments the action space and revises global strategies by adding a reflective replanning mechanism to the system. |
| Outcome: | Experiments show that CAR outperforms baselines in a diagnostic benchmark with pruned toolsets to simulate tool scarcity. |
FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation (D18-1)
Copied to clipboard
| Challenge: | Empirical results show that even the most competitive few-shot learning models struggle on this task, especially as compared with humans. |
| Approach: | They propose a Few-Shot Relation Classification Dataset consisting of 70, 000 sentences on 100 relations derived from Wikipedia and annotated by crowdworkers. |
| Outcome: | The proposed methods perform well on the most competitive few-shot learning models, especially as compared with humans. |
CLEVE: Contrastive Pre-training for Event Extraction (2021.acl-long)
Copied to clipboard
| Challenge: | Existing EE methods do not model event characteristics from large unsupervised data. |
| Approach: | They propose a contrastive pre-training framework for event extraction to better learn event knowledge from large unsupervised data and their semantic structures. |
| Outcome: | The proposed framework improves on ACE 2005 and MAVEN datasets on event extraction tasks. |
Automatic Construction of Sememe Knowledge Bases via Dictionaries (2021.findings-acl)
Copied to clipboard
| Challenge: | Sememe knowledge bases (SKBs) are used to analyze natural language processing. |
| Approach: | They propose a method to build sememe knowledge bases from an existing dictionary . they propose to use existing dictionaries to build an English and a French SKB . |
| Outcome: | The proposed method is superior to HowNet, the most widely used SKB that takes decades to build manually. |
Adversarial Multi-lingual Neural Relation Extraction (C18-1)
Copied to clipboard
| Challenge: | Existing models cannot capture consistency and diversity of relation patterns in different languages. |
| Approach: | They propose an adversarial multi-lingual neural relation extraction model which considers consistency and diversity among languages. |
| Outcome: | The proposed model outperforms the state-of-the-art models on real-world datasets. |
DeepNote: Note-Centric Deep Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
Ruobing Wang, Qingfei Zhao, Yukun Yan, Daren Zha, Yuxuan Chen, Shi Yu, Zhenghao Liu, Yixuan Wang, Shuo Wang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | . - (EN) |
| Approach: | . - (EN) |
| Outcome: | . - (EN) |
MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization (2024.findings-acl)
Copied to clipboard
Zhiyu Yang, Zihan Zhou, Shuo Wang, Xin Cong, Xu Han, Yukun Yan, Zhenghao Liu, Zhixing Tan, Pengyuan Liu, Dong Yu, Zhiyuan Liu, Xiaodong Shi, Maosong Sun
| Challenge: | Scientific data visualization is an essential process in research, but its use of large language models remains unexplored. |
| Approach: | They propose a model-agnostic LLM agent framework to automate scientific data visualization tasks. |
| Outcome: | The proposed framework improves performance of commercial and open-source models. |
SimPBL: A Multi-Agent Framework for Project-Based Learning (2026.acl-long)
Copied to clipboard
Daniel Zhang-Li, Joy Jia Yin Lim, Binglin Liu, Shangqing Tu, Zijun Yao, Hao Peng, Jifan Yu, Haoxuan Li, Zhanxin Hao, Ye He, Zekun Li, Jiangyi Wang, Lei Hou, Bin Xu, Xin Cong, Zhiyuan Liu, Huiqin Liu, Yu Zhang, Juanzi Li
| Challenge: | Existing LLMs provide partial assistance without modeling these roles, and overly comprehensive help can reduce learner autonomy. |
| Approach: | They propose a multi-agent framework with an orchestrator agent that provides adaptive scaffolding from interaction logs and collaborator agents that support project work through boundary-aware collaboration. |
| Outcome: | The proposed framework improves learner examination scores by 14% . it is based on a multi-agent framework with an orchestrator agent . |
Diagnosing Hidden Instabilities in Model Editing via Uncertainty Quantification (2026.acl-long)
Copied to clipboard
Zihan Gu, TianYi Zhang, Xinyan Zhang, Zhiyuan Wang, Han Zhang, Yuhao Wei, Jiacheng Lu, Tianyi Ma, Xingsheng Zhang, Hua Zhang, Yue Hu
| Challenge: | Existing methods to update large language models (LLMs) without expensive retraining are fragile under single-edit evaluation protocols. |
| Approach: | They propose a framework that characterizes activation-based editing as a constrained intervention on intermediate representations. |
| Outcome: | The proposed method reveals local knowledge conflicts invisible to existing benchmarks. |
Comprehensive Benchmarking of Long-Form Speech Generation in Diverse Scenarios (2026.findings-acl)
Copied to clipboard
Changhao Pan, Rui Yang, Han Wang, Zhuan Zhou, Xuming He, Wenxiang Guo, Ziyue Jiang, Ruiqi Li, Yu Zhang, Chenyuhao Wen, Ke Lei, Xiang Yin, Jingyu Lu, Zhiyuan Zhu, Zhou Zhao
| Challenge: | Existing evaluation benchmarks for long-form speech are limited to limited domains, creating a significant gap with the diverse downstream applications. |
| Approach: | They propose a benchmark that decomposes "long-form speech quality" into specific, disentangled dimensions. |
| Outcome: | The proposed benchmark decomposes “long-form speech quality” into specific, disentangled dimensions. |
INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair (2024.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that INTERVENOR surpasses baseline models, exhibiting improvements of approximately 18% and 4.3% over GPT-3.5 in code generation and code translation tasks. |
| Approach: | They propose a system that prompts Large Language Models to play distinct roles during the code repair process, functioning as both a Code Learner and a code teacher. |
| Outcome: | The proposed system surpasses baseline models in code generation and code translation tasks and improves on syntax errors and assertion errors. |
MOOCCube: A Large-scale Data Repository for NLP Applications in MOOCs (2020.acl-main)
Copied to clipboard
Jifan Yu, Gan Luo, Tong Xiao, Qingyang Zhong, Yuquan Wang, Wenzheng Feng, Junyi Luo, Chenyu Wang, Lei Hou, Juanzi Li, Zhiyuan Liu, Jie Tang
| Challenge: | Massive open online courses (MOOCs) are a popular educational platform for advanced research. |
| Approach: | They propose to use MOOCCube to build a large-scale data repository of over 700 MOOC courses, 100k concepts, 8 million student behaviors with an external resource. |
| Outcome: | The proposed datasets show that they can facilitate research in MOOCs. |
CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases (2025.naacl-long)
Copied to clipboard
Xiangyan Liu, Bo Lan, Zhiyuan Hu, Yang Liu, Zhicheng Zhang, Fei Wang, Michael Qizhe Shieh, Wenmeng Zhou
| Challenge: | Large Language Models excel in stand-alone code tasks but struggle with handling entire code repositories. |
| Approach: | They propose a system that integrates LLM agents with graph database interfaces extracted from code repositories. |
| Outcome: | The proposed system integrates LLM agents with graph database interfaces extracted from code repositories. |
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning System (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to attack Large Language Model (LLM) tool-learning systems are black-box oriented and rely on static commands that cannot adapt flexibly to the changes in user queries and the invocation chain. |
| Approach: | They propose a dynamic attack comment generation approach for information theft attacks in LLM tool-learning systems that mimics the familiar by inferring the information utilized by upstream tools. |
| Outcome: | The proposed approach outperforms baselines with +13.2% ASRTheft and can be generalized to new tool-learning systems to expose their information leakage risks. |
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling (2025.acl-long)
Copied to clipboard
Weilin Zhao, Tengyu Pan, Xu Han, Yudi Zhang, Sun Ao, Yuxiang Huang, Kaihuo Zhang, Weilun Zhao, Yuxuan Li, Jie Zhou, Hao Zhou, Jianyong Wang, Maosong Sun, Zhiyuan Liu
| Challenge: | Speculative sampling is an efficient way to accelerate the auto-regressive generation process of large language models. |
| Approach: | They propose a frequency-ranked speculative sampling framework that optimizes draft candidate selection through vocabulary space compression. |
| Outcome: | Experiments show that FR-Spec reduces LM Head computation overhead by 75% while ensuring the equivalence of the final output distribution. |
AHVE-CNER: Aligned Hanzi Visual Encoding Enhance Chinese Named Entity Recognition with Multi-Information (2025.coling-main)
Copied to clipboard
| Challenge: | Existing glyph-based models neglect the relationship between pictorial elements and radicals for Named Entity Recognition (NER) tasks. |
| Approach: | They propose a model that integrates multi-source visual and phonetic information of Hanzi . they propose combining pictographic features with radicals to facilitate integration . |
| Outcome: | The proposed model improves performance on benchmark datasets. |
LeanK: Learnable K Cache Channel Pruning for Efficient Decoding (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing efforts to optimize the key-value (KV) cache include: (1) Eviction, which discards cache of less important tokens; (2) Selection, which retains the full KV cache but selectively reads relevant entries. |
| Approach: | They propose a learning-based method that prunes unimportant key (K) cache channels by leveraging static channel sparsity. |
| Outcome: | Experiments show that LeanK reduces GPU memory and accelerates decoding without sacrificing accuracy. |
MAVEN-ERE: A Unified Large-scale Dataset for Event Coreference, Temporal, Causal, and Subevent Relation Extraction (2022.emnlp-main)
Copied to clipboard
Xiaozhi Wang, Yulin Chen, Ning Ding, Hao Peng, Zimu Wang, Yankai Lin, Xu Han, Lei Hou, Juanzi Li, Zhiyuan Liu, Peng Li, Jie Zhou
| Challenge: | Existing datasets only cover limited relation types at once, which prevents models from taking full advantage of relation interactions. |
| Approach: | They construct a large-scale human-annotated ERE dataset with improved annotation schemes to address these drawbacks. |
| Outcome: | The proposed dataset is larger than existing datasets of all the ERE tasks by at least an order of magnitude. |
Train No Evil: Selective Masking for Task-Guided Pre-Training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models can't capture domain-specific and task-specific patterns because of the task-agnostic pre-training stage. |
| Approach: | They propose a task-guided pre-training stage with selective masking between general pre-train and fine-tuning to learn domain-specific patterns. |
| Outcome: | The proposed method can achieve comparable or even better performance with less than 50% of computation cost. |
ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling (2026.findings-eacl)
Copied to clipboard
Zhipeng Xu, Zhenghao Liu, Yukun Yan, Shuo Wang, Shi Yu, Zheni Zeng, Chaojun Xiao, Zhiyuan Liu, Ge Yu, Chenyan Xiong
| Challenge: | Large Language Models (LLMs) exhibit suboptimal behaviors and inconsistencies when exposed to unfamiliar external information, underscoring their limitations in effectively leveraging such knowledge. |
| Approach: | They propose a framework that enhances the external knowledge utilization of Large Language Models through a two-stage constructivist cognitive modeling process. |
| Outcome: | The proposed framework achieves a 10% improvement over baseline methods on various question-answering benchmarks. |
Memorize Step by Step: Efficient Long-Context Prefilling with Incremental Memory and Decremental Chunk (2024.emnlp-main)
Copied to clipboard
Zhiyuan Zeng, Qipeng Guo, Xiaoran Liu, Zhangyue Yin, Wentao Shu, Mianqiu Huang, Bo Wang, Yunhua Zhou, Linlin Li, Qun Liu, Xipeng Qiu
| Challenge: | Existing methods to optimize LLM for long sequences for long documents are slow and consume memory. |
| Approach: | They propose a method that starts with a small memory size and gradually increases it . they propose Decremental Chunk based on Incremental Memory (IMDC) which reduces chunk size while increasing memory size . |
| Outcome: | The proposed method is faster (1.45x) and reduces GPU memory consumption by 23.3% compared to fixed-size memory. |
AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage (2026.acl-long)
Copied to clipboard
Xuanle Zhao, Zilin Sang, Yuxuan Li, Qi Shi, Weilun Zhao, Shuo Wang, Duzhen Zhang, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Efficient reproduction of research papers requires deep domain expertise. |
| Approach: | They propose a framework that systematically mines implicit knowledge from the cited literature to reproduce experimental code in a complete, end-to-end manner. |
| Outcome: | The proposed framework surpasses baselines across all metrics and reproduces experimental code in a complete, end-to-end manner. |
SedarEval: Automated Evaluation using Self-Adaptive Rubrics (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluation paradigms rely on generic scoring rubrics that fail to consider the specificities of each question and its problem-solving process. |
| Approach: | They propose a new evaluation paradigm based on self-adaptive rubrics that mimic a human evaluator's analytical process. |
| Outcome: | The proposed evaluation paradigm achieves higher concordance rate with human graders than existing paradigms, including GPT-4. |
Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs (2026.acl-long)
Copied to clipboard
| Challenge: | Experiments on 13 Omni-LLMs reveal systematic weaknesses in cross-modal coreference . cross-module coreference is a crucial missing piece for advancing robust omni-modal reasoning. |
| Approach: | They propose a cross-modal coreference problem to evaluate and enhance Omni-LLMs' reasoning capabilities. |
| Outcome: | Experiments on 13 Omni-LLMs show they lack coreference-aware thinking patterns . the CROSSOMNI dataset yields significant performance gains and generalizes well to collaborative reasoning tasks. |
LoRE: Enhancing Search Relevance with Progressive Chain-of-Thought and Preference Alignment (2026.findings-acl)
Copied to clipboard
Chenji Lu, Zhuo Chen, Hui Zhao, Zhiyuan Zeng, Gang Zhao, Junjie Ren, null Lihaoran, Songyan Liu, Pengjie Wang, Chuan Yu, Jian Xu, Bo Zheng
| Challenge: | E-commerce search relevance is a critical component of retrieval systems. |
| Approach: | They propose a large-generative model for search relevance that trains reasoning knowledge, multi-modal understanding and rule awareness into three core competencies. |
| Outcome: | The proposed model outperforms GPT-5 in Macro-F1 and achieves 27% online gain. |
On Transferability of Prompt Tuning for Natural Language Processing (2022.naacl-main)
Copied to clipboard
Yusheng Su, Xiaozhi Wang, Yujia Qin, Chi-Min Chan, Yankai Lin, Huadong Wang, Kaiyue Wen, Zhiyuan Liu, Peng Li, Juanzi Li, Lei Hou, Maosong Sun, Jie Zhou
| Challenge: | Pre-trained language models (PLMs) can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but require much more training time than fine-timing. |
| Approach: | They empirically investigate the transferability of soft prompts across different downstream tasks and PLMs to determine what decides prompt transferability. |
| Outcome: | The proposed method can achieve comparable performance to full-parameter fine-tuning by tuning a few soft prompts, but requires much more training time than fine-timing. |
Plug-and-Play Knowledge Injection for Pre-trained Language Models (2023.acl-long)
Copied to clipboard
Zhengyan Zhang, Zhiyuan Zeng, Yankai Lin, Huadong Wang, Deming Ye, Chaojun Xiao, Xu Han, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
| Challenge: | Existing knowledge injection methods are not suitable for enhancing pre-trained language models with external knowledge bases. |
| Approach: | They propose a plug-and-play knowledge injection method where knowledge bases are injected into frozen existing downstream models by a knowledge plugin. |
| Outcome: | The proposed method improves the performance of knowledge injection on knowledge-driven tasks while keeping model parameters frozen. |
FPT: Improving Prompt Tuning Efficiency via Progressive Training (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent prompt tuning (PT) has gained increasing attention as a parameter-efficient way of tuning pre-trained language models (PLMs). |
| Approach: | They propose a prompt tuning algorithm that uses a small-scale partial PLM and progressively expands its depth and width until the full-model size. |
| Outcome: | The proposed method could save over 30% of training computations while achieving comparable performance. |
Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for multimodal retrieval-augmented generation rely on semantic relevance or surface-level similarity, which are often misaligned with the actual utility of visual evidence for downstream reasoning. |
| Approach: | They propose a latent notion of evidence usefulness and propose 'surrogate-accelerated' framework that efficiently estimates evidence utility using lightweight multimodal models. |
| Outcome: | The proposed framework outperforms state-of-the-art models while achieving substantial reductions in computational cost. |
The Devil is in the Details: On the Pitfalls of Event Extraction Evaluation (2023.findings-acl)
Copied to clipboard
| Challenge: | Event extraction (EE) is a fundamental information extraction task aimed at extracting events from plain texts. |
| Approach: | They propose to specify data preprocessing, standardize outputs, and provide pipeline evaluation results to avoid these pitfalls. |
| Outcome: | The results show that the evaluations are reliable and lack pipeline evaluations. |
EvolveBench: A Comprehensive Benchmark for Assessing Temporal Awareness in LLMs on Evolving Knowledge (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have explored how LLMs perceive time, but they often overlook the critical aspect of knowledge utilization. |
| Approach: | They propose a benchmark that evaluates temporal competence along five key dimensions: Cognition, Awareness, Trustworthiness and reasoning. |
| Outcome: | EvolveBench measures temporal competence along five key dimensions: Cognition, Awareness, Trustworthiness, Understanding and reasoning. |
Finding Skill Neurons in Pre-trained Transformer-based Language Models (2022.emnlp-main)
Copied to clipboard
| Challenge: | Pre-trained language models have demonstrated superior performance on various natural language processing tasks. |
| Approach: | They find that after prompt tuning, some neurons encode task-specific skills . they also show that skill neurons are most likely generated in pre-training . |
| Outcome: | The neurons are highly predictive of task labels after prompt tuning for specific tasks. |
Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memory (2026.acl-long)
Copied to clipboard
| Challenge: | Existing literature on dialog memory systems is inconsistent on their effectiveness . empirical findings on graph structures are difficult to attribute to specific design choices . |
| Approach: | They propose a framework that decomposes dialog memory systems into core components . they conduct stage-wise experiments on LongMemEval and HaluMeM, and compare implementation details . |
| Outcome: | The proposed framework compares graph-based and non-graph memory architectures on long-term dialog memory systems. |
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger (2021.acl-long)
Copied to clipboard
| Challenge: | Existing methods for textual backdoor attacks insert additional contents into normal samples as triggers, causing detection and blocking of backdoors. |
| Approach: | They propose to use syntactic structure as trigger in textual backdoor attacks . they propose to achieve similar attack performance but have higher invisibility . |
| Outcome: | The proposed method achieves almost 100% success rate but has higher invisibility and stronger resistance to defenses than the insertion-based methods. |
ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework (2026.acl-long)
Copied to clipboard
Kai Qin, Liangxin Liu, Yu Liang, Longzheng Wang, null Wangyan, Zhang Yueyang, Long Xia, Zhiyuan Sun, Houde Liu, Daiting Shi
| Challenge: | Existing methods for generating reward models focus on outcome-level supervision, neglecting analytical process quality, which constrains their potential. |
| Approach: | They propose a novel reward model that leverages self-reflection to assess analytical quality and enhance preference modeling. |
| Outcome: | The proposed model improves performance on four benchmarks and significantly mitigates positional bias. |
GUICourse: From General Vision Language Model to Versatile GUI Agent (2025.acl-long)
Copied to clipboard
Wentong Chen, Junbo Cui, Jinyi Hu, Yujia Qin, Junjie Fang, Yue Zhao, Chongyi Wang, Jun Liu, Guirong Chen, Yupeng Huo, Yuan Yao, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Graphical User Interfaces (GUIs) are a pivotal medium for human-computer interaction. |
| Approach: | They propose a series of datasets for training visual-based GUI agents using general VLMs. |
| Outcome: | The proposed GUICourse datasets show that even a small-sized GUI agent performs better on GUI tasks. |
Integrating Representation Subspace Mapping with Unimodal Auxiliary Loss for Attention-based Multimodal Emotion Recognition (2024.lrec-main)
Copied to clipboard
Xulong Du, Xingnan Zhang, Dandan Wang, Yingying Xu, Zhiyuan Wu, Shiqing Zhang, Xiaoming Zhao, Jun Yu, Liangliang Lou
| Challenge: | Existing methods to identify emotions rely on a large modality gap in their representations . |
| Approach: | They propose a representation subspace mapping module that maps each modality into two distinct subspaces and a cross-modality attention module that leverages auxiliary loss to remove the noise unrelated to emotion classification. |
| Outcome: | The proposed approach achieves superior performance to state-of-the-art MER methods on the IEMOCAP and MSP-Improv datasets. |
Position Engineering: Boosting Large Language Models through Positional Information Manipulation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in Large Language Models (LLMs) have demonstrated significant strides towards achieving artificial general intelligence. |
| Approach: | They propose a technique termed position engineering which alters the positional information in the prompt without modifying the text itself. |
| Outcome: | The proposed technique significantly improves on the baseline in retrieval-augmented generation and in-context learning scenarios. |
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models (2024.findings-acl)
Copied to clipboard
Zhicheng Guo, Sijie Cheng, Hao Wang, Shihao Liang, Yujia Qin, Peng Li, Zhiyuan Liu, Maosong Sun, Yang Liu
| Challenge: | Large Language Models (LLMs) have witnessed remarkable advancements in recent years, prompting the exploration of tool learning. |
| Approach: | They propose a virtual API server and stable evaluation system to assess the stability of large-scale real-time APIs. |
| Outcome: | The proposed benchmarks demonstrate the stability of the proposed system and its caching system. |
SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering? (2026.findings-acl)
Copied to clipboard
Yuxuan Sun, Yuze Zhao, Yufeng Wang, Yao Du, Zhiyuan Ma, Jinbo Wang, Mengdi Zhang, Kai Zhang, Zhenya Huang
| Challenge: | Evaluating software engineering capabilities is a core component of large language models (LLMs). |
| Approach: | They propose a benchmark to evaluate LLM-generated test suites that introduces mutated solutions that attempt to "fool" them. |
| Outcome: | The proposed test suites are based on 2,636 mutated variants derived from 800 original instances and include a multilingual subset spanning nine programming languages. |
WebCPM: Interactive Web Search for Chinese Long-form Question Answering (2023.acl-long)
Copied to clipboard
Yujia Qin, Zihan Cai, Dian Jin, Lan Yan, Shihao Liang, Kunlun Zhu, Yankai Lin, Xu Han, Ning Ding, Huadong Wang, Ruobing Xie, Fanchao Qi, Zhiyuan Liu, Maosong Sun, Jie Zhou
| Challenge: | Long-form question answering requires two procedures: information retrieval and information synthesis. |
| Approach: | They propose a Chinese long-form question answering dataset called WebCPM . the dataset is based on a web search interface that engages with a search engine in real time . |
| Outcome: | The proposed dataset generates answers that are no worse than human-written ones . the dataset is the first Chinese LFQA dataset . |
ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training (2026.acl-long)
Copied to clipboard
Yu Liang, Liangxin Liu, Longzheng Wang, null Wangyan, Zhang Yueyang, Long Xia, Zhiyuan Sun, Daiting Shi
| Challenge: | ConsistRM is a self-training framework that enables effective and stable GRM training without human annotations. |
| Approach: | They propose a self-training framework that enables effective and stable GRM training without human annotations. |
| Outcome: | The proposed framework outperforms vanilla Reinforcement Fine-Tuning (RFT) by 1.5% on five benchmark datasets. |
LEVEN: A Large-Scale Chinese Legal Event Detection Dataset (2022.findings-acl)
Copied to clipboard
Feng Yao, Chaojun Xiao, Xiaozhi Wang, Zhiyuan Liu, Lei Hou, Cunchao Tu, Juanzi Li, Yun Liu, Weixing Shen, Maosong Sun
| Challenge: | Existing legal event detection datasets only cover incomprehensive event types and have limited annotated data. |
| Approach: | They present a large-scale Chinese legal event detection dataset . they use legal events as side information to promote downstream applications . |
| Outcome: | The proposed method improves 2.2 points precision in low-resource judgment prediction and 1.5 points precision for unsupervised case retrieval. |
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis (2025.findings-acl)
Copied to clipboard
Yu Zhang, Wenxiang Guo, Changhao Pan, Dongyu Yao, Zhiyuan Zhu, Ziyue Jiang, Yuhan Wang, Tao Jin, Zhou Zhao
| Challenge: | Existing zero-shot singing voice synthesis models depend on phoneme and note boundary annotations, limiting their robustness and producing poor transitions between phonemes and notes. |
| Approach: | They propose a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts. |
| Outcome: | Experimental results show that TCSinger 2 outperforms baseline models in subjective and objective metrics across multiple related tasks. |
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation System (2025.acl-long)
Copied to clipboard
| Challenge: | Existing methods for text chunking are limited by text chunks and lack of domain-specific knowledge. |
| Approach: | They propose a dual-metric evaluation method to quantify text chunking quality . they aim to generate a structured list of chunking regular expressions . |
| Outcome: | The proposed method enables direct quantification of chunking quality . it substantiates the need to integrate LLMs into chunking process . |
Experiential Co-Learning of Software-Developing Agents (2024.acl-long)
Copied to clipboard
Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, YiFei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, Zhiyuan Liu, Maosong Sun
| Challenge: | Recent advances in large language models (LLMs) have brought significant changes to various domains, especially through autonomous agents. |
| Approach: | They propose a framework that lets agents learn shortcuts from their past tasks and use them for future task execution. |
| Outcome: | The proposed framework enables agents to tackle unseen software-developing tasks more effectively. |
Beyond ’Aha!’: Toward Systematic Meta-Abilities Alignment in Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Prior work has shown that outcome-based reinforcement learning (RL) can incidentally elicit advanced reasoning behaviors such as self-correction, backtracking, and verification. |
| Approach: | They explicitly align large reasoning models with three meta-abilities: deduction, induction, and abduction, using automatically generated, self-verifiable tasks. |
| Outcome: | The proposed model aligns models with deduction, induction, and abduction meta-abilities using automatically generated, self-verifiable tasks. |
SConU: Selective Conformal Uncertainty in Large Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Existing frameworks fail to identify outliers that violate the exchangeability assumption, leading to unbounded miscoverage rates and unactionable prediction sets. |
| Approach: | They propose a method that implements significance tests to determine whether a given sample deviates from the uncertainty distribution of the calibration set. |
| Outcome: | The proposed approach facilitates rigorous management of miscoverage rates across single-domain and interdisciplinary contexts, and enhances the efficiency of predictions. |
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models (2025.acl-long)
Copied to clipboard
Zhiyuan Hu, Yuliang Liu, Jinman Zhao, Suyuchen Wang, WangYan WangYan, Wei Shen, Qing Gu, Anh Tuan Luu, See-Kiong Ng, Zhiwei Jiang, Bryan Hooi
| Challenge: | Large language models face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences. |
| Approach: | They propose a training strategy for extending the context window of LLMs including impactful token analysis, position index transformation, and training optimization strategies. |
| Outcome: | Experiments on three types of LLMs show that LongRecipe can utilize long sequences while requiring only 30% of the target context window size. |
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems (2025.findings-emnlp)
Copied to clipboard
Zhiyuan Chang, Mingyang Li, Xiaojun Jia, Junjie Wang, Yuekai Huang, Ziyou Jiang, Yang Liu, Qing Wang
| Challenge: | Existing knowledge poisoning attacks against RAG systems require multiple poisoned documents or can only function effectively on simplistic queries. |
| Approach: | They propose a more realistic knowledge poisoning attack that poisons only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements. |
| Outcome: | The proposed attack achieves success by poisoning only a single document while remaining effective for complex multi-hop questions involving complex relationships between multiple elements. |
Prompt-learning for Fine-grained Entity Typing (2022.findings-emnlp)
Copied to clipboard
Ning Ding, Yulin Chen, Xu Han, Guangwei Xu, Xiaobin Wang, Pengjun Xie, Haitao Zheng, Zhiyuan Liu, Juanzi Li, Hong-Gee Kim
| Challenge: | Extensive experiments on fine-grained entity typing under fully supervised, few-shot, and zero-shot settings show the effectiveness of prompt-learning. |
| Approach: | They propose a prompt-learning pipeline that stimulates versatile knowledge of pre-trained language models (PLMs) by constructing entity-oriented verbalizers and templates and conducting masked language modeling. |
| Outcome: | The proposed approach can be applied to fine-grained entity typing in fully supervised, few-shot, and zero-shot scenarios. |
HMEAE: Hierarchical Modular Event Argument Extraction (D19-1)
Copied to clipboard
| Challenge: | Existing event extraction methods classify each argument role independently, ignoring conceptual correlations between different argument roles. |
| Approach: | They propose a Hierarchical Modular Event Argument Extraction model to provide inductive bias from the concept hierarchy of event argument roles. |
| Outcome: | The proposed model outperforms existing methods on real-world datasets and shows that it leverages useful knowledge from the concept hierarchy. |
bert2BERT: Towards Reusable Pretrained Language Models (2022.acl-long)
Copied to clipboard
Cheng Chen, Yichun Yin, Lifeng Shang, Xin Jiang, Yujia Qin, Fengyu Wang, Zhi Wang, Xiao Chen, Zhiyuan Liu, Qun Liu
| Challenge: | Pre-training large language models can be expensive and wasteful. |
| Approach: | They propose a method which can transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and a two-stage learning method to further accelerate the pre-training. |
| Outcome: | The proposed method can transfer the knowledge of an existing smaller pre-trained model to a large model through parameter initialization and significantly improve the pre-training efficiency of the large model. |
Mathematical Proof as a Litmus Test: Revealing Failure Modes of Advanced Large Reasoning Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large reasoning models have demonstrated remarkable mathematical problem-solving abilities, but their true reasoning shortcomings are often hidden. |
| Approach: | They propose to leverage the rigor and methodological complexity of mathematical proofs as a diagnostic tool to expose hidden failures. |
| Outcome: | The proposed model evaluation exploits the rigor and complexity of proof problems to uncover 10 fine-grained errors. |
Won’t Get Fooled Again: Answering Questions with False Premises (2023.acl-long)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are often easily deceived by tricky questions such as “How many eyes does the sun have?” . |
| Approach: | They annotate a FalseQA dataset containing 2365 human-written FPQs and find that PLMs are capable of discriminating FPqs by fine-tuning on moderate numbers. |
| Outcome: | The proposed model can discriminate on FPQs by fine-tuning on moderate numbers of examples and generate reasonable explanations for false premise questions. |
Progressive Self-Training with Discriminator for Aspect Term Extraction (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to extract aspect terms from review sentences are limited due to lack of annotated data. |
| Approach: | They propose to refine conventional self-training to progressive self-teaching to reduce noise . they use a discriminator to filter the noisy pseudo-labels. |
| Outcome: | The proposed model outperforms baseline models and achieves state-of-the-art performance on four SemEval datasets. |
TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization (2026.findings-acl)
Copied to clipboard
Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang
| Challenge: | Large Language Models (LLMs) can solve complex tasks through iterative information retrieval. |
| Approach: | They propose a turn-level stage-aware policy optimization approach to solve this problem . they introduce a first-occurrence latent reward mechanism to allocate partial rewards . |
| Outcome: | Experiments show that TSPO outperforms state-of-the-art models on Qwen2.5-3B and 7B models. |
All Changes May Have Invariant Principles: Improving Ever-Shifting Harmful Meme Detection via Design Concept Reproduction (2026.acl-long)
Copied to clipboard
Ziyou Jiang, Mingyang Li, Junjie Wang, Yuekai Huang, Jie Huang, Zhiyuan Chang, Zhaoyang Li, Qing Wang
| Challenge: | Existing methods for harmful meme detection only learn the combination of harmful elements and lack understanding of these implicit expressions. |
| Approach: | They propose a method that detects harmful memes by replicating the design concept of malicious users. |
| Outcome: | The proposed method achieves the highest accuracy with 81.1% and has slight accuracy decreases when generalized to type-shifting and temporal-evolving memes. |
CALM: Unleashing the Cross-Lingual Self-Aligning Ability of Language Model Question Answering (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are pre-trained on extensive multilingual corpora to acquire both language-specific cultural knowledge and general knowledge. |
| Approach: | They propose to use the **C**ross-Lingual Self-**Aligning ability of **L**anguage **M**odels to align knowledge across languages. |
| Outcome: | The proposed model performs well in both zero-shot and retrieval-augmented settings. |
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning (2026.findings-acl)
Copied to clipboard
Zhiyuan Chang, Mingyang Li, Yuekai Huang, Ziyou Jiang, Xiaojun Jia, Qian Xiong, Junjie Wang, Zhaoyang Li, Qing Wang
| Challenge: | Large language model (LLM)-integrated applications face security vulnerabilities from prompt injection (PI) attacks. |
| Approach: | They propose a model enhancement method that synthesizes diverse training data and employs instruction-level chain-of-thought fine-tuning to enable LLMs to effectively identify and reject malicious instructions regardless of their source or position in the context. |
| Outcome: | The proposed method outperforms baselines in three critical dimensions while maintaining utility performance without degradation. |
MALoRA: Mixture of Asymmetric Low-Rank Adaptation for Enhanced Multi-Task Learning (2025.findings-naacl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can be fine-tuned to new tasks, but in multi-task scenarios, training imbalance and seesaw effect often arise. |
| Approach: | They propose a flexible fine-tuning framework that leverages asymmetric optimization among LoRA experts to reduce training imbalance and improve performance. |
| Outcome: | The proposed framework outperforms baseline methods in inter- and intra-task learning scenarios. |
HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks (2026.findings-acl)
Copied to clipboard
| Challenge: | Medical large vision-language models suffer from factual inaccuracies and unreliable outputs. |
| Approach: | They propose a framework that enhances Med-LVLMs through heterogeneous knowledge sources. |
| Outcome: | The proposed framework improves Med-LVLMs through heterogeneous knowledge sources. |
Enhancing Distantly Supervised Named Entity Recognition with Strong Label Guided Lottery Training (2024.lrec-main)
Copied to clipboard
| Challenge: | Named entity recognition (NER) requires a limited quantity of strongly labeled data . weakly labeles can be acquired through distant supervision, but can cause noise . |
| Approach: | They propose a noise-robust learning framework where safe parameters can be identified . they conduct extensive experiments on multiple datasets and show it outperforms the state-of-the-art methods. |
| Outcome: | The proposed framework outperforms the state-of-the-art methods on weakly labeled data. |
End-to-End Optimization for Multimodal Retrieval-Augmented Generation via Reward Backpropagation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | MM-RAG is a promising approach for enhancing the reliability and factuality of large vision-language models . current methods focus on component-level optimizations and necessitate extensive component-specific training datasets . |
| Approach: | They propose a new paradigm that backpropagates global rewards to each component . this backpropage transforms local losses into specific local losses . |
| Outcome: | The proposed paradigm achieves high training efficiency on knowledge-intensive multimodal benchmarks. |
UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset (2024.acl-long)
Copied to clipboard
Haoyu Wang, Shuo Wang, Yukun Yan, Xujia Wang, Zhiyu Yang, Yuzhuang Xu, Zhenghao Liu, Liner Yang, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun
| Challenge: | Open-source large language models (LLMs) have gained strength across diverse fields, but the majority of studies focus on English. |
| Approach: | They propose a knowledge-grounded data augmentation approach to elicit more language-specific knowledge of LLMs by enhancing their ability to serve users from different countries. |
| Outcome: | The proposed method can prune the language-agnostic supervised fine-tuning dataset without any performance degradation. |
RealMem: Benchmarking LLMs in Real-World Memory-Driven Interaction (2026.findings-acl)
Copied to clipboard
Haonan Bian, Zhiyuan Yao, Sen Hu, Zishan Xu, Shaolei Zhang, Yifu Guo, Ziliang Yang, Xueran Han, Huacan Wang, Ronghao Chen
| Challenge: | Existing benchmarks focus on casual conversation or task-oriented dialogue, failing to capture “long-term project-oriented” interactions where agents must track evolving goals. |
| Approach: | They propose a benchmark that simulates the dynamic evolution of memory in real-world projects. |
| Outcome: | The proposed benchmarks simulate the dynamic evolution of memory in real-world projects. |
ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees (2024.findings-emnlp)
Copied to clipboard
Zhiyuan Wang, Jinhao Duan, Lu Cheng, Yue Zhang, Qingni Wang, Xiaoshuang Shi, Kaidi Xu, Heng Tao Shen, Xiaofeng Zhu
| Challenge: | Uncertainty quantification (UQ) in natural language generation tasks remains an open challenge . however, black-box uncertainty measures require investigating with the proliferation of LLMs served via APIs. |
| Approach: | They propose a conformal uncertainty measure and a method to transform heuristic uncertainty notions into rigorous prediction sets. |
| Outcome: | Empirical results show that the proposed method outperforms state-of-the-art methods and can provide reliable guarantees for open-ended NLG tasks. |
COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis (2025.findings-naacl)
Copied to clipboard
Weiqing Yang, Hanbin Wang, Zhenghao Liu, Xinze Li, Yukun Yan, Shuo Wang, Yu Gu, Minghe Yu, Zhiyuan Liu, Ge Yu
| Challenge: | Existing code debugging benchmarks focus on the Code Repair stage of the code generation process. |
| Approach: | They propose a framework to evaluate the debugging abilities of large language models by emulating the human debug process. |
| Outcome: | The proposed framework outperforms human-curated and GPT-4-generated training data, enabling 7B-scale LLMs to achieve comparable debugging performance to GPT-3.5. |
ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research (2025.acl-industry)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have shown promising results in various domains, but their practical application in industry-relevant operations research presents significant challenges and opportunities. |
| Approach: | They propose a cognitive-inspired framework that enhances optimization through counterfactual reasoning . they use a workflow that transforms requirements into mathematical models and executable solver code . |
| Outcome: | Experiments show that ORMind outperforms existing methods in the NL4Opt dataset and ComplexOR dataset. |
Exploring the Potential of Dense Information in Multimodal Alignment (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to enhance captions have limitations such as insufficient detail and excessive hallucinations, resulting in compromised alignment and masking the true potential of dense information. |
| Approach: | They propose a pipeline that generates highly detailed captions for images that facilitates in-depth analysis of the potential for dense information in multimodal alignment. |
| Outcome: | The proposed pipeline significantly improves multimodal alignment and compositional reasoning abilities, surpassing hard negative samples. |
MAXS: Meta-Adaptive Exploration with LLM Agents (2026.findings-acl)
Copied to clipboard
Jian Zhang, Zhiyuan Wang, Zhangqi Wang, Yu He, Haoran Luo, li Yuan, Lingling Zhang, Rui Mao, Qika Lin, Jun Liu
| Challenge: | Existing methods for inference are often myopic and have divergent reasoning paths . a meta-adaptive reasoning framework is proposed to improve the efficiency of LLM agents . |
| Approach: | They propose a meta-adaptive reasoning framework that integrates tool execution and reasoning planning. |
| Outcome: | The proposed framework outperforms existing methods in performance and inference efficiency. |
Course Concept Expansion in MOOCs with External Knowledge and Interactive Game (P19-1)
Copied to clipboard
| Challenge: | Existing methods to expand course concepts in MOOCs suffer from semantic drifts and lack of knowledge guidance. |
| Approach: | They propose to use a boundary search method to search for new concepts via external knowledge base and then use heterogeneous features to verify the results. |
| Outcome: | The proposed method improves on the datasets from Coursera and XuetangX. |
Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for OOD detection are overconfident for OD samples . lack of labeled OOD examples leads to poor prior knowledge about these unknown intents, making it challenging to detect OOD samples. |
| Approach: | They propose a Bayesian OOD detection framework to calibrate distribution uncertainty using Monte-Carlo Dropout. |
| Outcome: | The proposed framework gains 33.33% OOD F1 improvements with increasing only 0.41% inference time compared to previous methods. |
Better Robustness by More Coverage: Adversarial and Mixup Data Augmentation for Robust Finetuning (2021.findings-acl)
Copied to clipboard
| Challenge: | Pretrained language models perform poorly under adversarial attacks due to the large search space. |
| Approach: | They propose a method to cover a much larger proportion of the attack search space by adding textual adversarial examples during training. |
| Outcome: | The proposed method covers a much larger proportion of the attack search space. |
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models (2025.acl-long)
Copied to clipboard
Zihan Zhou, Chong Li, Xinyi Chen, Shuo Wang, Yu Chao, Zhili Li, Haoyu Wang, Qi Shi, Zhixing Tan, Xu Han, Xiaodong Shi, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing studies have focused on extending the context length of large language models (LLMs) due to their quadratic computational complexity and a lack of high-quality long training examples, most LLMs are trained with a limited window size. |
| Approach: | They propose a training-free framework that enables large language models to effectively process long texts using a divide-and-conquer strategy for comprehensive document understanding. |
| Outcome: | The proposed framework outperforms open-source and commercial long-context LLMs and is compatible with several models. |
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs (2026.findings-acl)
Copied to clipboard
Zhiyuan Hu, Yucheng Wang, Yufei He, Jiaying Wu, Yilun Zhao, See-Kiong Ng, Cynthia Breazeal, Anh Tuan Luu, Hae Won Park, Bryan Hooi
| Challenge: | Reinforcement learning (RL) is a paradigm for post-training large language models, but it suffers from exploration collapse . a new study finds that RL fails to reward correct solutions that exhibit rare high-level strategies . |
| Approach: | They propose a method that rewards correct solutions that exhibit rare high-level strategies by clustering rollouts according to their high- level solution strategies. |
| Outcome: | The proposed approach improves pass@k across large sampling budgets and increases area under the pass@K curve (AUC@K) without sacrificing pass@1. |
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models (2024.lrec-main)
Copied to clipboard
Zhangyue Yin, Qiushi Sun, Qipeng Guo, Zhiyuan Zeng, Xiaonan Li, Tianxiang Sun, Cheng Chang, Qinyuan Cheng, Ding Wang, Xiaofeng Mou, Xipeng Qiu, Xuanjing Huang
| Challenge: | Recent advances in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks. |
| Approach: | They propose a hierarchical reasoning aggregation framework to address this problem . they propose dynamic sampling to adjust the number of reasoning chains . |
| Outcome: | The proposed framework outperforms existing ensemble methods on complex reasoning tasks. |
Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats (2026.acl-industry)
Copied to clipboard
Pengxiang Zhao, Hui-Ling Zhen, Xing Li, Han Bao, Weizhe Lin, Zhiyuan Yang, Yu Zi Wei, Xin Wang, Mingxuan Yuan, Xianzhi Yu, Zhenhua Dong
| Challenge: | Low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. |
| Approach: | They evaluate HiFloat (HiF8 and HiF4), a family of floating-point formats tailored for Ascend NPUs. |
| Outcome: | The proposed formats excel with high-variance data and are compatible with state-of-the-art quantization frameworks. |
Enhancing Open-Domain Task-Solving Capability of LLMs via Autonomous Tool Integration from GitHub (2025.acl-long)
Copied to clipboard
Bohan Lyu, Xin Cong, Heyang Yu, Pan Yang, Cheng Qian, Zihe Wang, Yujia Qin, Yining Ye, Yaxi Lu, Chen Qian, Zhong Zhang, Yukun Yan, Yankai Lin, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing approaches lack flexibility to address diverse and ever-evolving user queries in open domains. |
| Approach: | They propose to evaluate LLMs on open-domain knowledge that requires tools to solve diverse and ever-evolving user queries. |
| Outcome: | The proposed system outperforms baselines in the open domain task-solving benchmark. |
LEGENT: Open Platform for Embodied Agents (2024.acl-demos)
Copied to clipboard
Zhili Cheng, Zhitong Wang, Jinyi Hu, Shengding Hu, An Liu, Yuge Tu, Pengkai Li, Lei Shi, Zhiyuan Liu, Maosong Sun
| Challenge: | Existing integrations of large language models and large multimodal models are limited . Existing platforms for developing embodied agents are limited and limited based on open-source software. |
| Approach: | They propose an open platform for developing embodied agents using LLMs and LMMs. |
| Outcome: | The proposed platform surpasses GPT-4V in embodied tasks with its model training on LEGENT data. |