Papers by Xiong Wang
POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Positional bias (PB) manifests as non-uniform sensitivity across contextual locations . previous studies have addressed PB by modifying the underlying architectures or employing extensive contextual awareness training. |
| Approach: | They propose a position-to-position knowledge distillation framework that leverages position-induced disparities to counteract PB. |
| Outcome: | The proposed framework reduces positional bias and improves performance on retrieval and reasoning tasks. |
HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing question answering datasets focus on dealing with homogeneous information, but using homogenous information alone might lead to coverage problems. |
| Approach: | They propose a large-scale question-answering dataset that requires reasoning on heterogeneous information. |
| Outcome: | The proposed model can achieve an EM score of 40% while the existing model is far behind human performance. |
Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) can solve reasoning and mathematical problems using the Chain-of-Thought technique, but require costly and long CoT data and fine-tuning. |
| Approach: | They propose a method that uses Sparse Autoencoders to extract interpretable features from vanilla CoT and use them to steer the LLM's internal states. |
| Outcome: | The proposed method uses Sparse Autoencoders (SAEs) to extract interpretable features from vanilla CoT and steer the LLM's internal states during generation. |
Watch Out Your Industrial Copilots: Stealthy Backdoor Attack Against LLM-Based PLC Code Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are being used to generate PLC code from natural language. |
| Approach: | They propose a stealthy backdoor attack framework targeting LLM-based PLC code generation . they incorporate six malicious logic injection patterns and a pipeline to refine stealthiness . |
| Outcome: | The proposed framework achieves 82.92% success rate while remaining stealthy . it bypasses quality validation and is difficult to detect . |
A Deep Learning-Based System for PharmaCoNER (D19-57)
Copied to clipboard
Ying Xiong, Yedan Shen, Yuanhang Huang, Shuai Chen, Buzhou Tang, Xiaolong Wang, Qingcai Chen, Jun Yan, Yi Zhou
| Challenge: | Efficient access to mentions of clinical entities is very important for using clinical text. |
| Approach: | They developed a pipeline system based on deep learning methods for this shared task . it achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average LSTM score of 0.8391 on track 2 . |
| Outcome: | The proposed system achieves a micro-average F1-score of 0.9105 on track 1 and a mini-average score of 0.8391 on track 2. |
Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Reasoning Models (LRMs) often display unstable behaviors, e.g., hallucinating unsupported premises, overthinking simple tasks, and displaying higher sensitivity to prompt variations. |
| Approach: | They propose a graph-based analytical framework that clusters long, verbose CoT outputs into semantically coherent reasoning steps, then constructs directed reasoning graphs to capture contextual and logical dependencies among these steps. |
| Outcome: | The proposed framework enables quantitative evaluation of internal reasoning structure and quality beyond conventional metrics and provides practical insights for prompt engineering and cognitive analysis of LLMs. |
LightSeq: A High Performance Inference Library for Transformers (2021.naacl-industry)
Copied to clipboard
| Challenge: | Existing inference frameworks for natural language processing are not the best choice for online service of sequence processing problems. |
| Approach: | They propose a highly efficient inference library for Transformer models that includes GPU optimization techniques to streamline computation and reduce memory footprint. |
| Outcome: | The proposed library achieves 14x speedup compared with TensorFlow and 1.4x speed up compared to a concurrent CUDA implementation. |
Direct Judgement Preference Optimization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing judge models are largely trained with supervised finetuning on small data scales to perform limited types of evaluation tasks, limiting generalization. |
| Approach: | They propose to train judge models at large data scales with direct preference optimization . they use four training tasks to form three types of preference pairs targeting different aspects of evaluation . |
| Outcome: | The proposed model outperforms GPT-4o and other similar models on 13 benchmarks. |
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts (2024.findings-acl)
Copied to clipboard
Ganesh Jawahar, Haichuan Yang, Yunyang Xiong, Zechun Liu, Dilin Wang, Fei Sun, Meng Li, Aasish Pappu, Barlas Oguz, Muhammad Abdul-Mageed, Laks Lakshmanan, Raghuraman Krishnamoorthi, Vikas Chandra
| Challenge: | Neural architecture search (NAS) uses weight-sharing supernets to generate diverse subnetworks without retraining. |
| Approach: | They propose a weight-sharing supernet that leverages mixture-of-experts to enhance supernet model expressiveness with minimal training overhead. |
| Outcome: | The proposed method achieves state-of-the-art (SoTA) performance in NAS for fast machine translation models, surpassing NAS-BERT and AutoDistil across various model sizes. |
Self-Supervised Learning for Contextualized Extractive Summarization (P19-1)
Copied to clipboard
| Challenge: | Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss . previous work builds an end-to-end system to learn to choose sentences without explicitly modeling document context . |
| Approach: | They propose three auxiliary pre-training tasks that learn to capture the document context in a self-supervised fashion. |
| Outcome: | The proposed models outperform existing models on a CNN/DM dataset. |
Simple yet Effective Bridge Reasoning for Open-Domain Multi-Hop Question Answering (D19-58)
Copied to clipboard
| Challenge: | Existing work on open-domain multi-hop question answering relies on off-the-shelf information retrieval techniques to retrieve answer passages. |
| Approach: | They propose a new subproblem for open-domain multi-hop question answering . they aim to recognize the anchor from a set of start passages with a reading comprehension model . |
| Outcome: | The proposed method significantly improves the baseline method on the open-domain hotpotQA benchmark. |
CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Modern software development demands code that is maintainable, testable, and scalable by organizing the implementation into modular components with iterative reuse of existing codes. |
| Approach: | They propose a benchmark to evaluate LLMs' ability to perform codeflow by reusing existing functions over multiple turns. |
| Outcome: | The proposed benchmarks show that LLMs perform significantly worse in multi-turn codeflow scenarios and that their performance inversely correlates with dependency complexity. |
LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin (2024.acl-long)
Copied to clipboard
Shihan Dou, Enyu Zhou, Yan Liu, Songyang Gao, Wei Shen, Limao Xiong, Yuhao Zhou, Xiao Wang, Zhiheng Xi, Xiaoran Fan, Shiliang Pu, Jiang Zhu, Rui Zheng, Tao Gui, Qi Zhang, Xuanjing Huang
| Challenge: | Experimental results show that, as the instruction data increases, LoRAMoE can significantly improve the ability to process downstream tasks, while maintaining the world knowledge stored in the LLM. |
| Approach: | They propose a framework that introduces several low-rank adapters and integrates them by using a router network to freeze the backbone model and force a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks. |
| Outcome: | The proposed framework freezes the backbone model and forces a portion of LoRAs to focus on leveraging world knowledge to solve downstream tasks, to alleviate world knowledge forgetting. |
Neural Topic Modeling with Cycle-Consistent Adversarial Training (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances on deep generative models have attracted significant interest in neural topic modeling. |
| Approach: | They propose an adversarial-neural topic model which uses Dirichlet prior to capture the semantic patterns in latent topics. |
| Outcome: | The proposed models outperform competing models on unsupervised/supervised topic modeling and text classification. |
AdaST: Dynamically Adapting Encoder States in the Decoder for End-to-End Speech-to-Text Translation (2021.findings-acl)
Copied to clipboard
| Challenge: | End-to-end speech translation models learn acoustic representations from the encoder, which is not desirable for cross-modal and cross-lingual translation. |
| Approach: | They propose an adaptive speech-to-text translation model that dynamically adapts acoustic states in the decoder. |
| Outcome: | The proposed model outperforms state-of-the-art speech translation models on two widely-used datasets. |
UHGEval: Benchmarking the Hallucination of Chinese Large Language Models via Unconstrained Generation (2024.acl-long)
Copied to clipboard
Xun Liang, Shichao Song, Simin Niu, Zhiyu Li, Feiyu Xiong, Bo Tang, Yezhaohui Wang, Dawei He, Cheng Peng, Zhonghao Wang, Haiying Deng
| Challenge: | Large language models (LLMs) produce hallucinated text, compromising their practical utility in professional contexts. |
| Approach: | They have developed an unconstrained hallucination generation evaluation benchmark that contains hallucines generated by large language models with minimal restrictions. |
| Outcome: | The proposed benchmarks are based on a Chinese-language dataset that is lacking in the field. |
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective (2022.acl-long)
Copied to clipboard
Xiao Wang, Shihan Dou, Limao Xiong, Yicheng Zou, Qi Zhang, Tao Gui, Liang Qiao, Zhanzhan Cheng, Xuanjing Huang
| Challenge: | Named Entity Recognition models are feature-engineering and machine learning based. |
| Approach: | They propose a new NER learning framework that uses entity mentions to improve model performance. |
| Outcome: | The proposed model achieves better performance on OOV entities on various settings and datasets. |
AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories (2024.findings-emnlp)
Copied to clipboard
Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li
| Challenge: | Existing studies focus on specialized agents designed for particular tasks. |
| Approach: | They propose to scale annotated interaction trajectories and fine-tune LLMs on AgentBank to get a series of agent models, Samoyed. |
| Outcome: | The proposed model can scale to get generalized agent capabilities. |
ActionStudio: A Lightweight Framework for Data and Training of Large Action Models (2025.emnlp-main)
Copied to clipboard
Jianguo Zhang, Thai Quoc Hoang, Ming Zhu, Zuxin Liu, Shiyu Wang, Tulika Manoj Awalgaonkar, Akshara Prabhakar, Haolin Chen, Weiran Yao, Zhiwei Liu, Juntao Tan, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
| Challenge: | Existing infrastructure for efficient agentic data processing and model training remains underdeveloped. |
| Approach: | They propose a lightweight and extensible data and training framework for large action models . they propose to unify diverse agent trajectories using Unified Format 2.0 . |
| Outcome: | The proposed framework shows 9 higher throughput than existing frameworks and performs well across public and realistic agent benchmarks. |
ExpertIVS: Sociological Expert Driven Individual Value Simulation in Large Language Models (2026.findings-acl)
Copied to clipboard
Zhen Wang, Yuqi Ren, Yuehan Cui, Hongxiang Wang, Jianxiang Peng, Zhaoxia Zhang, Bingkun Zhu, Tongxuan Zhang, Dezhi Tong, Deyi Xiong
| Challenge: | Existing methods for social simulations mechanically stitch survey responses into prompts, which suffer from semantic fragmentation, failing to capture the internal coherence of human value systems. |
| Approach: | They propose a framework employing 14 Sociological Expert Agents to interpret World Values Survey responses through structured professional perspectives rather than direct responses concatenation. |
| Outcome: | Experiments on 480 individuals from 12 countries show that ExpertIVS outperforms baselines in value generalization and significantly outperfies the existing methods. |
From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models (2026.acl-long)
Copied to clipboard
Ling Shi, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Yangyang Liu, Linlong Xu, Longyue Wang, Deyi Xiong, Weihua Luo
| Challenge: | Recent research in mechanistic interpretability has revealed that Large Language models contain disentangled, human-understandable components. |
| Approach: | They propose a framework that first identifies causal task features through frequency recall and interventional filtering, then selects “Feature-Resonant Data” that maximally activates task features for fine-tuning. |
| Outcome: | The proposed framework outperforms existing models on mathematical reasoning, summarization, and translation tasks while using only 50% of the data. |
LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Currently, large language models (LLMs) train on short text segments due to the computational overhead quadratic in the input lengths of their Transformer architectures. |
| Approach: | They propose a method that allows LLMs pre-trained with 2K or 4K-long segments to generalize to up to 200M length inputs while retaining perplexity. |
| Outcome: | The proposed method achieves 2.7 decoding speed up and 7.5 memory saving over the original model. |
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent (2025.findings-emnlp)
Copied to clipboard
Junda Wu, Yuxin Xiong, Xintong Li, Yu Xia, Ruoyu Wang, Yu Wang, Tong Yu, Sungchul Kim, Ryan A. Rossi, Lina Yao, Jingbo Shang, Julian McAuley
| Challenge: | Existing fine-tuning and continual learning methods compress visual representations and emphasize task alignment over visual retention. |
| Approach: | They propose a modality-decoupled gradient descent (MDGD) that regulates gradient updates to preserve effective rank of visual features and explicitly disentangles visual learning from task-specific alignment. |
| Outcome: | The proposed model reduces visual forgetting and improves visual retention . it disentangles visual learning from task-specific alignment and preserves effective rank . |
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models (2026.findings-acl)
Copied to clipboard
Hengyuan Zhang, Zhihao Zhang, Ercong Nie, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Xufeng Duan, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So, Hinrich Schuetze, Xuanjing Huang, Qi Zhang, Ngai Wong
| Challenge: | Existing literature on mechanistic interpretation (MI) treats it as an observational science, leaving practical applications underexplored. |
| Approach: | They propose a survey structured around the pipeline to identify and improve MI models. |
| Outcome: | The proposed framework enables tangible improvements in Alignment, Capability, and Efficiency. |
Z-Code++: A Pre-trained Language Model Optimized for Abstractive Summarization (2023.acl-long)
Copied to clipboard
Pengcheng He, Baolin Peng, Song Wang, Yang Liu, Ruochen Xu, Hany Hassan, Yu Shi, Chenguang Zhu, Wayne Xiong, Michael Zeng, Jianfeng Gao, Xuedong Huang
| Challenge: | Z-Code++ is a pre-trained language model optimized for abstractive text summarization. |
| Approach: | They propose a pre-trained language model optimized for abstractive text summarization that uses a two-phase pre-training technique to improve model's performance. |
| Outcome: | The proposed model outperforms the competing models on low-resource summarization tasks in zero-shot and few-shot settings. |
PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data (2025.findings-acl)
Copied to clipboard
Juntao Tan, Liangwei Yang, Zuxin Liu, Zhiwei Liu, Rithesh R N, Tulika Manoj Awalgaonkar, Jianguo Zhang, Weiran Yao, Ming Zhu, Shirley Kokane, Silvio Savarese, Huan Wang, Caiming Xiong, Shelby Heinecke
| Challenge: | Existing research lacks direct access to such data, making benchmarking difficult due to privacy concerns. |
| Approach: | They propose a synthetic data pipeline that generates realistic user profiles and private documents and a benchmark to evaluate models' ability to understand personal information. |
| Outcome: | The proposed pipeline generates realistic user profiles and private documents, enabling PersonaBench, a benchmark for evaluating models’ ability to understand personal information. |
VD-BERT: A Unified Vision and Dialog Transformer with BERT (2020.emnlp-main)
Copied to clipboard
| Challenge: | Prior work focused on attention mechanisms to model complex interactions in visual dialog . a new framework for visual dialog is based on pretrained BERT language models . |
| Approach: | They propose a framework for a vision-dialog Transformer that leverages pretrained BERT language models for Visual Dialog tasks. |
| Outcome: | The proposed framework achieves the top position on the visual dialog leaderboard without pretraining on external vision-language data. |
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)
Copied to clipboard
Linzi Xing, Xinglu Wang, Yuxi Feng, Zhenan Fan, Jing Xiong, Zhijiang Guo, Xiaojin Fu, Rindra Ramamonjison, Mahdi Mostajabdaveh, Xiongwei Han, Zirui Zhou, Yong Zhang
| Challenge: | Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers. |
| Approach: | They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification. |
| Outcome: | The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification. |
BatchMixup: Improving Training by Interpolating Hidden States of the Entire Mini-batch (2021.findings-acl)
Copied to clipboard
| Challenge: | a data augmentation technique is used to augment data, but it has two drawbacks. |
| Approach: | They propose a new mixup paradigm that generates new points scattered throughout the whole mini-batch. |
| Outcome: | The proposed model improves the performance of NLP tasks while using different ratios of training data. |
Joint Intent Detection and Entity Linking on Spatial Domain Queries (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Spatial domain queries have unique properties making them more challenging for language understanding than common conversational queries. |
| Approach: | They propose a language understanding framework for spatial domain queries that jointly learns the intent detection and entity linking tasks on a voice assistant service. |
| Outcome: | The proposed framework outperforms baseline methods with a significant margin. |
Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration (2026.acl-long)
Copied to clipboard
Yang Zhao, Yangou Ouyang, Xiao Ding, Hepeng Wang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Existing data arbitration strategies for large language model training rely on surface-level heuristics that fail to diagnose intrinsic learning needs. |
| Approach: | They propose a framework that arbitrates data based on its degree of cognitive conflict with the model's existing knowledge. |
| Outcome: | Extensive experiments on WebShop and ALFWorld show that PRISM outperforms state-of-the-art hybrid methods while reducing computational costs by up to 3.22 . |
Do Multi-hop Readers Dream of Reasoning Chains? (D19-58)
Copied to clipboard
| Challenge: | Existing models for multihop reasoning are limited in their performance . multi-hop reasoning requires the ability to gather information from multiple passages . |
| Approach: | They propose a method that provides the full reasoning chain of multiple passages instead of just one final passage where the answer appears. |
| Outcome: | The proposed model improves on existing models by providing the full reasoning chain of multiple passages instead of just one final passage where the answer appears. |
LORE: Continual Logit Rewriting Fosters Faithful Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Using aspect-oriented summarization as a case study, we propose **LOgit REwriting**, a new controlled generation paradigm which can be faithful to external knowledge and to the LLM’s intentions. |
| Approach: | They propose a controlled generation paradigm which can be faithful to external knowledge and to the LLM's intentions. |
| Outcome: | The proposed paradigm can be faithful to external knowledge and to the LLM's intentions while balancing that with accuracy. |
Coarse-to-Fine Contrastive Learning in Image-Text-Graph Space for Improved Vision-Language Compositionality (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have highlighted severe limitations of contrastive learning models in their ability to perform compositional reasoning over objects, attributes, and relations. |
| Approach: | They propose a graph decomposition framework and negative mining techniques to improve attribute binding and relation understanding of scene graphs. |
| Outcome: | The proposed approach improves attribute binding, relation understanding, generalization, and productivity on multiple benchmarks. |
A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition (2023.findings-acl)
Copied to clipboard
Limao Xiong, Jie Zhou, Qunxi Zhu, Xiao Wang, Yuanbin Wu, Qi Zhang, Tao Gui, Xuanjing Huang, Jin Ma, Ying Shan
| Challenge: | Existing models for named entity recognition (NER) are based on large-scale labeled datasets, which always obtain using crowdsourcing. |
| Approach: | They propose a CONfidence-based partial Label Learning method to integrate prior and posterior confidences for crowd-annotated named entity recognition models. |
| Outcome: | The proposed model improves on real-world and synthetic datasets compared with baselines. |
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)
Copied to clipboard
Changxin Ke, Rui Zhang, Jiaming Guo, Yuanbo Wen, Li Ding, Shuo Wang, Xuyuan Zhu, Xiong Peng, Di Huang, Zidong Du, Xing Hu, Qi Guo, Yunji Chen
| Challenge: | Existing approaches to program repair are based on correctness alone. |
| Approach: | They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits. |
| Outcome: | The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing. |
Beyond Similarity: A Gradient-based Graph Method for Instruction Tuning Data Selection (2025.acl-long)
Copied to clipboard
Yang Zhao, Li Du, Xiao Ding, Yangou Ouyang, Hepeng Wang, Kai Xiong, Jinglong Gao, Zhouhao Sun, Dongliang Xu, Qing Yang, Dongchen Li, Bing Qin, Ting Liu
| Challenge: | Existing methods for selecting training data from general datasets fail to account for the joint distribution of instructions, resulting in inefficient learning and suboptimal knowledge transfer. |
| Approach: | They propose a method that constructs a mixed gradient-based instruction graph to capture the joint distribution and interdependencies among instructions. |
| Outcome: | The proposed method outperforms existing methods on domain adaptation tasks and in complex, data-scarce scenarios. |
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)
Copied to clipboard
Run Luo, Haonan Zhang, Longze Chen, Ting-En Lin, Xiong Liu, Yuchuan Wu, Min Yang, Yongbin Li, Minzheng Wang, Pengpeng Zeng, Lianli Gao, Heng Tao Shen, Yunshui Li, Hamid Alinejad-Rokny, Xiaobo Xia, Jingkuan Song, Fei Huang
| Challenge: | a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling . |
| Approach: | They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution. |
| Outcome: | The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data. |
Federated LoRA Fine-Tuning with Pipelined Error-Mitigated Aggregation and Matrix-Wise Freezing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for fine-tuning large language models often suffer from biased model aggregation and are hindered by significant communication and computation burden. |
| Approach: | They propose a Federated low-rank adaptation system for large language models that leverages pipelined error-mitigated model aggregation and adaptive matrix-wise parameter freezing to mitigate aggregations. |
| Outcome: | The proposed system improves time-to-target by 2.17-8.48 on real-world datasets. |
Mitigating the Alignment Tax of RLHF (2024.emnlp-main)
Copied to clipboard
Yong Lin, Hangyu Lin, Wei Xiong, Shizhe Diao, Jianmeng Liu, Jipeng Zhang, Rui Pan, Haoxiang Wang, Wenbin Hu, Hanning Zhang, Hanze Dong, Renjie Pi, Han Zhao, Nan Jiang, Heng Ji, Yuan Yao, Tong Zhang
| Challenge: | Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax. |
| Approach: | They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms. |
| Outcome: | The proposed method achieves the strongest alignment-forging Pareto front among competing methods. |
ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods to shorten CoTs use length penalties or global entropy reduction . Existing approaches to CoT reasoning have significant practical drawbacks . |
| Approach: | They propose a method that shortens CoTs by length penalties or global entropy reduction . they integrate ETR into Group Relative Policy Optimization and evaluate it . |
| Outcome: | The proposed objective improves accuracy–efficiency trade-off by +9.9% while reducing CoT length by 67% across four benchmarks. |
MemeQA: Holistic Evaluation for Meme Understanding (2025.acl-long)
Copied to clipboard
Khoi P. N. Nguyen, Terrence Li, Derek Lou Zhou, Gabriel Xiong, Pranav Balu, Nandhan Alahari, Alan Huang, Tanush Chauhan, Harshavardhan Bala, Emre Guzelordu, Affan Kashfi, Aaron Xu, Suyesh Shrestha, Megan Vu, Jerry Wang, Vincent Ng
| Challenge: | Existing benchmarks for meme understanding only concern narrow aspects of meme semantics. |
| Approach: | They propose to use multiple-choice questions to evaluate meme comprehension . they use a dataset of over 9,000 multiple-question questions to assess meme comprehension. |
| Outcome: | The proposed model outperforms existing models on meme comprehension . the model makes many errors on memes where proper understanding requires going beyond sentiment . |
ChatHLS: Towards Systematic Design Automation and Optimization for High-Level Synthesis (2026.acl-long)
Copied to clipboard
| Challenge: | High-Level Synthesis (HLS) is a hardware design tool that can be used to design hardware from C-like languages, but its widespread adoption is limited by strict coding constraints and design-specific optimizations. |
| Approach: | They propose a multi-agent HLS design framework that leverages specialized LLMs for automated debugging and directive tuning. |
| Outcome: | The proposed framework outperforms Gemini-3-pro in debugging and speedups across various HLS kernels and neural network accelerators. |
One-Shot Relational Learning for Knowledge Graphs (D18-1)
Copied to clipboard
| Challenge: | Existing studies on knowledge graph completion require a large number of positive examples for each relation, but long-tail relations are more common in KGs and those newly added relations do not have many known triples for training. |
| Approach: | They propose a one-shot relational learning framework that utilizes the knowledge distilled by embedding models and learns a matching metric by considering both the learned embeddments and one-hop graph structures. |
| Outcome: | The proposed framework improves on existing embedding models and eliminates the need for retraining when dealing with newly added relations. |
Multi-Granularity Semantic Revision for Large Language Model Distillation (2026.acl-long)
Copied to clipboard
Xiaoyu Liu, Yun Zhang, Wei Li, Simiao Li, Xudong Huang, Hanting Chen, Yehui Tang, Jie Hu, Zhiwei Xiong, Yunhe Wang
| Challenge: | Existing methods for generating large language models rely on student-generated outputs, which introduce generation errors and misguide the distillation process. |
| Approach: | They propose a multi-granularity semantic revision method for LLM distillation that corrects errors using teacher-generated tokens and re-generates the sequence to minimize errors. |
| Outcome: | The proposed method reduces errors and misguides distillation on student models and improves consistency between teacher and student outputs. |
Multi-Programming Language Sandbox for LLMs (2025.acl-demo)
Copied to clipboard
Shihan Dou, Jiazheng Zhang, Jianxiang Zang, Yunbo Tao, Weikang Zhou, Haoxiang Jia, Shichun Liu, Yuming Yang, Shenxi Wu, Zhiheng Xi, Muling Wu, Rui Zheng, Changze Lv, Limao Xiong, Shaoqing Zhang, Lin Zhang, Wenyu Zhan, Rongxiang Weng, Jingang Wang, Xunliang Cai, Yueming Wu, Ming Wen, Yixin Cao, Tao Gui, Xipeng Qiu, Qi Zhang, Xuanjing Huang
| Challenge: | MPLSandbox is an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). |
| Approach: | They propose a multi-programming language sandbox that provides unified feedback from compilers and analysis tools for Large Language Models. |
| Outcome: | The proposed multi-language sandbox can provide comprehensive feedback from compilers and analysis tools for large language models (LLMs). |
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection (2026.findings-acl)
Copied to clipboard
Yibo Yan, Shen Wang, Jiahao Huo, Hang Li, Boyan Li, Jiamin Su, Xiong Gao, YiFan Zhang, Tianlong Xu, Zhendong Chu, Aoxiao Zhong, Kun Wang, Hui Xiong, Philip S. Yu, Xuming Hu, Qingsong Wen
| Challenge: | Current mathematical benchmarks focus on evaluating MLLMs’ problem-solving ability, yet there is a crucial gap in addressing more complex scenarios such as error detection. |
| Approach: | They propose to evaluate multimodal error detection by evaluating two sub-tasks error step identification and error categorization. |
| Outcome: | The proposed task evaluates MLLMs' ability to handle multimodal questions compared to text-only models. |
CoCoID: Learning Contrastive Representations and Compact Clusters for Semi-Supervised Intent Discovery (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing approaches to intent discovery cluster novel intents with prior knowledge from intent-labeled data in a semi-supervised way. |
| Approach: | They propose a semi-supervised intent discovery framework CoCoID with two components . they propose to discriminate user utterance representation learning and intra-cluster knowledge distillation . |
| Outcome: | The proposed framework outperforms state-of-the-art intent discovery models by over 1.4 ACC and ARI points and 1.1 NMI points across four datasets. |
Multi-Agent Collaboration via Cross-Team Orchestration (2025.findings-acl)
Copied to clipboard
Zhuoyun Du, Chen Qian, Wei Liu, Zihao Xie, YiFei Wang, Rennai Qiu, Yufan Dang, Weize Chen, Cheng Yang, Ye Tian, Xuantang Xiong, Lei Han
| Challenge: | Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. |
| Approach: | They propose a framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation. |
| Outcome: | Experiments show that the framework can generate better software quality compared to state-of-the-art frameworks. |
APPSI-139: A Parallel Corpus of English Application Privacy Policy Summarization and Interpretation (2026.acl-long)
Copied to clipboard
Pengyun Zhu, Qiheng Sun, Long Wen, Yanbo Wang, Yang Cao, Junxu Liu, Deyi Xiong, Jinfei Liu, Zhibo Wang, Kui Ren
| Challenge: | a lack of high-quality English privacy policy corpus optimized for legal clarity and readability is limiting translation of privacy policies . 139 privacy policies are often considered "incomprehensible" due to technical jargon, legal language, and convoluted grammatical structures. |
| Approach: | They propose a high-quality English privacy policy corpus annotated by domain experts . they propose APPSI-139 to summarize and interpret privacy policies in English . |
| Outcome: | The proposed framework outperforms large language models in terms of readability and accuracy. |
ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)
Copied to clipboard
Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng
| Challenge: | Existing studies on large language model-based agents focus on evaluation benchmarks without training support. |
| Approach: | They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents. |
| Outcome: | The proposed model performs poorly in a large-scale and challenging shopping environment in China. |
A Comprehensive Evaluation of Quantization Strategies for Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Quantization studies have focused on instruction-tuned LLMs, leaving their performance on other benchmarks unclear. |
| Approach: | They propose a framework to evaluate quantized large language models using four dimensions . they propose to reduce the bits needed for model weights or activations with minimal performance loss . |
| Outcome: | The proposed framework can retain comparable performance to non-quantized LLMs on most benchmarks. |
Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance (2025.emnlp-industry)
Copied to clipboard
Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song
| Challenge: | Existing approaches to identifying inappropriate content require extensive human-labeled data and lack cross-issue generalization. |
| Approach: | They propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection. |
| Outcome: | The proposed model improves the MLLM's performance in both zero-shot and supervised fine-tuning settings and shows strong generalization capabilities to emergent, previously unseen issues. |
Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification (D19-1)
Copied to clipboard
| Challenge: | Existing models for multi-label classification ignore complexity and dependencies among labels . Experimental results show that our method can obtain more accurate multi-lab classification results. |
| Approach: | They propose a meta-learning method to capture complex label dependencies . they use a Meta-learner to jointly learn the training policies and prediction policies for different labels. |
| Outcome: | The proposed method can capture complex label dependencies on fine-grained entity typing and text classification tasks. |
FLAG-TRADER: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Trading (2025.findings-acl)
Copied to clipboard
Guojun Xiong, Zhiyang Deng, Keyi Wang, Yupeng Cao, Haohang Li, Yangyang Yu, Xueqing Peng, Mingquan Lin, Kaleb E Smith, Xiao-Yang Liu, Jimin Huang, Sophia Ananiadou, Qianqian Xie
| Challenge: | Large language models (LLMs) have impressive reasoning capabilities in financial tasks, but struggle with multi-step, goal-oriented scenarios in interactive financial markets. |
| Approach: | They propose a framework that integrates large language models with gradient-driven reinforcement learning (RL) policy optimization. |
| Outcome: | The proposed framework improves performance in trading and other financial domain tasks. |
STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (P19-1)
Copied to clipboard
Mingbo Ma, Liang Huang, Hao Xiong, Renjie Zheng, Kaibo Liu, Baigong Zheng, Chuanqiang Zhang, Zhongjun He, Hairong Liu, Xing Li, Hua Wu, Haifeng Wang
| Challenge: | Simultaneous translation is notoriously dif- ficult due to word-order differences. |
| Approach: | They propose a prefix-to-prefix framework that implicitly learns to anticipate in a single translation model. |
| Outcome: | The proposed framework achieves low latency and reasonable qual- ity on 4 directions. |
Certified Robustness to Word Substitution Attack with Differential Privacy (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that adversarial examples can be easily fooled by DNNs, making the robustness and security of NLP models significantly important. |
| Approach: | They propose a differential privacy-based algorithm to achieve certified robustness against word substitution at- tacks in text classification via differential privacy. |
| Outcome: | The proposed model achieves higher accuracy and more than 30X efficiency improvement over existing defense algorithms. |
Visually-Guided Policy Optimization for Multimodal Reasoning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing RLVRs lack visual faithfulness due to text-dominated reasoning . a novel framework to reinforce visual focus during policy optimization is proposed . |
| Approach: | They propose a framework to reinforce visual focus during policy optimization using visual attention compensation mechanism. |
| Outcome: | The proposed framework exhibits better visual activation and superior performance in multimodal reasoning and visual-dependent tasks. |
InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have identified the severe performance decrease on analogous classes as a key factor for catastrophic forgetting. |
| Approach: | They propose a replay-based continual text classification method that uses fast-slow and current-past contrastive learning to perform mutual information maximization and better recover previously learned representations. |
| Outcome: | The proposed method achieves state-of-the-art on three text classification tasks. |
Sentence Embedding Alignment for Lifelong Relation Extraction (N19-1)
Copied to clipboard
| Challenge: | Existing approaches to relation extraction require a fixed set of relations . Existing methods assume a closed set of relationships and perform once-and-for-all training on a set of datasets. |
| Approach: | They propose to improve the stochastic gradient methods with a replay memory to alleviate the forgetting problem by anchoring the sentence embedding space. |
| Outcome: | The proposed method outperforms state-of-the-art methods on multiple benchmarks. |
Anti-Length Shift: Dynamic Outlier Truncation for Training Efficient Reasoning Models (2026.acl-long)
Copied to clipboard
Wei Wu, Liyi Chen, Congxi Xiao, Tianfu Wang, Qimeng Wang, Chengqiang Lu, Yan Gao, null Yiwu, Yao Hu, Hui Xiong
| Challenge: | Existing efficient reasoning methods rely on explicit length penalties for excessive verbosity on simple queries. |
| Approach: | They propose a training-time intervention that selectively suppresses redundant tokens . they find length shift occurs when models generate unnecessary reasoning on trivial inputs - a phenomenon that is often unexplored . |
| Outcome: | The proposed method reduces inference token usage by 78% while increasing accuracy compared to the initial policy and surpasses state-of-the-art efficient reasoning methods. |
Balanced Joint Adversarial Training for Robust Intent Detection and Slot Filling (2020.coling-main)
Copied to clipboard
| Challenge: | Existing joint models for intent detection and slot filling show insufficient robustness . however, some small changes of inputs can fool the models to produce wrong predictions . |
| Approach: | They propose a joint adversarial training model that generates adversarials to attack the joint model and trains the model to defend against the adversarial examples. |
| Outcome: | The proposed model achieves significantly higher scores and improves robustness on two datasets. |
TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on large language models (LLMs) focus on basic plan validity, but neglect critical aspects such as route efficiency, POI appeal, and real-time adaptability. |
| Approach: | They propose a benchmark for retrieval-augmented, spatiotemporal-aware travel planning that integrates retrieved trajectories with LLMs’ intrinsic reasoning. |
| Outcome: | The proposed framework improves spatial efficiency and POI rationality while challenging universality and robustness due to conflicting references and noisy data. |
MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval (2025.acl-long)
Copied to clipboard
Junjie Zhou, Yongping Xiong, Zheng Liu, Ze Liu, Shitao Xiao, Yueze Wang, Bo Zhao, Chen Jason Zhang, Defu Lian
| Challenge: | despite the growing demand for multimodal retrieval, there is a lack of training data. |
| Approach: | They propose a data synthesis method that leverages vision language models and open-domain images to generate high-quality data. |
| Outcome: | The proposed method outperforms baseline models on 70 more datasets and can scale up. |
TRIGO: Benchmarking Formal Mathematical Proof Reduction for Generative Language Models (2023.emnlp-main)
Copied to clipboard
Jing Xiong, Jianhao Shen, Ye Yuan, Haiming Wang, Yichun Yin, Zhengying Liu, Lin Li, Zhijiang Guo, Qingxing Cao, Yinya Huang, Chuanyang Zheng, Xiaodan Liang, Ming Zhang, Qun Liu
| Challenge: | Automated theorem proving (ATP) benchmarks focus on symbolic inference but rarely involve understanding complex number combination reasoning. |
| Approach: | They propose a benchmark that requires a model to reduce a trigonometric expression with step-by-step proof and evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms. |
| Outcome: | The proposed benchmark evaluates a generative LM’s reasoning ability on formulas and ability to manipulate, group, and factor number terms. |
ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents (2025.acl-long)
Copied to clipboard
Zhigen Li, Jianxiang Peng, Yanmeng Wang, Yong Cao, Tianhao Shen, Minghui Zhang, Linxi Su, Shang Wu, Yihang Wu, YuQian Wang, Ye Wang, Wei Hu, Jianfeng Li, Shaojun Wang, Jing Xiao, Deyi Xiong
| Challenge: | Existing models that use Large Language Models (LLMs) show superior performance in various tasks, but lack of controllability leads to unfocused conversations or task failure. |
| Approach: | They propose a standard operating procedure (SOP) framework to regulate dialogue flow by integrating Chain of Thought reasoning and supervised fine-tuning for SOP prediction. |
| Outcome: | The proposed method achieves a 27.95% improvement in action accuracy compared to baseline models based on GPT-3.5 and also shows notable gains for open-source models. |
SocialEval: Evaluating Social Intelligence of Large Language Models (2025.acl-long)
Copied to clipboard
Jinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang, Leqi Lei, Yi Feng, Zexuan Xiong, Miao Yan, Xunzhi Wang, Yaru Cao, Jianing Yin, Shuai Wang, Quanyu Dai, Zhenhua Dong, Hongning Wang, Minlie Huang
| Challenge: | Existing work on LLMs does not address their social intelligence (SI) and their discrepancy with humans. |
| Approach: | They propose a script-based bilingual SI benchmark that integrates outcome-oriented goal achievement evaluation and process-oriented interpersonal ability evaluation by manually crafting narrative scripts. |
| Outcome: | The proposed model is based on a script-based bilingual evaluation paradigm that integrates outcome- and process-oriented evaluation by manually crafting narrative scripts. |
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI (2024.findings-eacl)
Copied to clipboard
Jianguo Zhang, Kun Qian, Zhiwei Liu, Shelby Heinecke, Rui Meng, Ye Liu, Zhou Yu, Huan Wang, Silvio Savarese, Caiming Xiong
| Challenge: | DialogStudio is the largest and most diverse collection of dialogue datasets . existing datasets lack diversity and comprehensiveness, authors say . |
| Approach: | They introduce DialogStudio: the largest and most diverse collection of dialogue datasets . DialogStuio aggregates more than 80 diverse dialogue dataset . |
| Outcome: | a new dataset is created to improve the quality and diversity of dialogue datasets . DialogStudio is the largest and most diverse collection of dialogue data . |
The Box is in the Pen: Evaluating Commonsense Reasoning in Neural Machine Translation (2020.findings-emnlp)
Copied to clipboard
| Challenge: | a test suite to evaluate commonsense reasoning capability of neural machine translation is presented . language models pretrained on large-scale corpora achieve a commonsensing accuracy of lower than 72% on target translations of this test suite. |
| Approach: | They propose a test suite to evaluate the commonsense reasoning capability of neural machine translation. |
| Outcome: | The proposed test suite performs poorly on commonsense reasoning of the three ambiguity types in terms of reasoning accuracy and reasoning consistency. |
DVMap: Fine-Grained Pluralistic Value Alignment via High-Consensus Demographic-Value Mapping (2026.acl-long)
Copied to clipboard
| Challenge: | Current Large Language Models (LLMs) rely on coarse-grained national labels for pluralistic value alignment. |
| Approach: | They propose a framework for fine-grained pluralistic value alignment using demographic constraints. |
| Outcome: | The proposed framework can identify groups with predictable, high-consensus value preference . it achieves 48.6% accuracy, surpassing open-source LLM DeepSeek-v3.2 . |
PKAG-DDI: Pairwise Knowledge-Augmented Language Model for Drug-Drug Interaction Event Text Generation (2025.acl-long)
Copied to clipboard
| Challenge: | Drug-drug interactions arise when multiple drugs are administered concurrently. |
| Approach: | They propose a pairwise knowledge-augmented generative method for DDIE text generation that integrates biological functions from a knowledge set into a language model. |
| Outcome: | The proposed method outperforms existing methods in DDIE text generation on two professional datasets. |
Reinforcement Learning on Pre-Training Data (2026.acl-long)
Copied to clipboard
Siheng Li, Kejiao Li, Zenan Xu, Guanhua Huang, Kun Li, Haoyuan Wu, null Wujiajia, Zihao Zheng, Chenchen Zhang, Kun Shi, Xue Gong, Qi Yi, Ruibin Xiong, Tingqiang Xu, Yuhao Jiang, Jianfeng Yan, Yuyuan Zeng, Guanghui Xu, Jinbao Xue, Zhijiang xu, Zheng Fang, Shuai LI, Qibin Liu, Xiaoxue Li, Zhuoyu Li, Yangyu Tao, Fei Gao, Cheng Jiang, Bochao Wang, Kai Liu, Jianchen Zhu, Wai Lam, Bo Zhou, Di Wang
| Challenge: | Recent progress in large language models is driven by scaling of training compute through pre-training with nexttoken prediction (NTP) or post-training (RL) Pre-training using NTP enables models to acquire extensive knowledge and skills from general data, but it suffers from data inefficiency and catastrophic forgetting in continual learning settings. |
| Approach: | They propose to scale training compute through pre-training with next-token prediction (NTP) or post-training by scaling reinforcement learning (RL) to improve learning from general data. |
| Outcome: | Experiments on multiple benchmarks and models show that the proposed approach improves continual pre-training and provides a strong foundation for post-training on Qwen3-8B-Base. |
KeFVP: Knowledge-enhanced Financial Volatility Prediction (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Current studies ignore the role of financial metrics knowledge in earnings calls and little consideration is given to integrating text and price information. |
| Approach: | They propose to integrate financial metrics knowledge into text comprehension by knowledge-enhanced adaptive pre-training and effectively incorporating text and price information by introducing a conditional time series prediction module. |
| Outcome: | The proposed method outperforms state-of-the-art methods on three real-world datasets and is effective and reliable. |
MAESTRO: Meta-learning Adaptive Estimation of Scalarization Trade-offs for Reward Optimization (2026.acl-long)
Copied to clipboard
Yang Zhao, Hepeng Wang, Xiao Ding, Yangou Ouyang, Bibo Cai, Kai Xiong, Jinglong Gao, Zhouhao Sun, Li Du, Bing Qin, Ting Liu
| Challenge: | Group-Relative Policy Optimization (GRPO) has emerged as an efficient paradigm for aligning Large Language Models (LLMs), but its efficacy is confined to domains with verifiable ground truths. |
| Approach: | They propose a meta-cognitive orchestration layer that treats reward scalarization as a dynamic latent policy, leveraging the model’s terminal hidden states as 'a semantic bottleneck' . Across seven benchmarks, MAESTRO consistently outperforms single-reward and static multi-objective baselines while preserving the efficiency advantages of GRPO. |
| Outcome: | The proposed model outperforms single-reward and static multi-objective baselines while preserving efficiency advantages. |
Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader (P19-1)
Copied to clipboard
| Challenge: | Existing models that use incomplete knowledge bases and text data to answer open-domain questions are insufficient to cover full evidence. |
| Approach: | They propose a model which learns to aggregate answer evidence from incomplete knowledge bases and text snippets. |
| Outcome: | The proposed model improves on the widely-used KBQA benchmark WebQSP across settings with different extents of incompleteness. |
Zero-shot Fact Verification by Claim Generation (2021.acl-short)
Copied to clipboard
| Challenge: | Existing methods for fact verification require large datasets, which can be expensive. |
| Approach: | They propose a framework for training a robust fact verification model by using automatically generated claims that can be supported, refuted, or unverifiable from evidence from Wikipedia. |
| Outcome: | The proposed framework reduces the demand for human-annotated training data and improves a model's F1 from 50% to 77%, equivalent in performance to 2K+ manually-curated examples. |
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan (2026.acl-long)
Copied to clipboard
Lei Yang, Leiyu Pan, Bojian Xiong, Renren Jin, Shaowei Zhang, Yue Chen, Ling Shi, Jiang Zhou, Junru Wu, Zhen Wang, Jianxiang Peng, Juesi Xiao, Tianyu Dong, Zhuowen Han, Zhuo Chen, Yuqi Ren, Deyi Xiong
| Challenge: | Large language models have achieved remarkable success across a wide range of tasks, yet their performance remains heavily biased toward high-resource languages. |
| Approach: | They propose a pipeline for advancing Tibetan language modeling through multilingual continual pre-training with Tibetan, Chinese, and English. |
| Outcome: | The proposed model outperforms open-source and Tibetan-focused models on diverse tasks. |
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay (2024.emnlp-main)
Copied to clipboard
Yihuai Lan, Zhiqiang Hu, Lei Wang, Yang Wang, Deheng Ye, Peilin Zhao, Ee-Peng Lim, Hui Xiong, Hao Wang
| Challenge: | Existing studies on LLM agents' social behaviors are lacking . previous studies focused on positive social behaviors, leaving research on negative social behaviors relatively scarce. |
| Approach: | They propose a framework that features a multi-agent system facilitating efficient communication and interaction with LLM agents. |
| Outcome: | The proposed framework is based on Avalon and evaluates on game success and analyzes agents’ social behaviors. |
Controlled Text Generation for Large Language Model with Dynamic Attribute Graphs (2024.findings-acl)
Copied to clipboard
| Challenge: | Controlled Text Generation (CTG) aims to produce texts that exhibit specific desired attributes. |
| Approach: | They propose a pluggable CTG framework for Large Language Models to control text . they use attribute scorers to evaluate attributes of sentences and construct dynamic attribute graphs . |
| Outcome: | The proposed framework achieves a peak improvement of 19.29% over baseline methods in two tasks. |
Composition-based Heterogeneous Graph Multi-channel Attention Network for Multi-aspect Multi-sentiment Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for Aspect-based sentiment analysis (ABSA) focus on aspect terms with the same sentiment polarity . current methods focus on sentences with only one aspect term or multiple aspect terms . |
| Approach: | They propose a novel method to model inter-aspect relationships and aspect-context relationships simultaneously using a heterogeneous graph. |
| Outcome: | The proposed method can predict sentiments towards the given aspect term in a sentence . it can provide more detailed predictions compared with sentence-level sentiment analysis. |
Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward (2026.findings-acl)
Copied to clipboard
Guanhua Huang, Tingqiang Xu, Mingze Wang, Qi Yi, Xue Gong, Siheng Li, Ruibin Xiong, Kejiao Li, Yuhao Jiang, Bo Zhou
| Challenge: | Recent studies show that RLVR training is slow and results plateau as policy entropy collapses . low-probability regularization (Lp-Reg) reduces the number of low-quality exploratory tokens induced by RL training . |
| Approach: | They propose a method to reduce RLVR over-penalization by eliminating low-probability exploratory tokens . they propose 'Low-provability Regularization' to reduce the gradual elimination of low-quality exploratory entropy tokens. |
| Outcome: | The proposed method eliminates low-probability exploratory tokens and prevents suppression of potentially valuable low-property candidates. |
Adaptive Structure Induction for Aspect-based Sentiment Analysis with Spectral Perspective (2023.findings-emnlp)
Copied to clipboard
| Challenge: | incorporating structure information can enhance the performance of aspect-based sentiment analysis. |
| Approach: | They propose to use pre-trained language models to induct latent structures from a spectrum perspective. |
| Outcome: | The proposed model shortens Aspects-sentiment Distance and improves structure induction ability. |
Elevating Legal LLM Responses: Harnessing Trainable Logical Structures and Semantic Knowledge with Legal Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing approaches to large language models focus on semantic similarity, neglecting the intricate logical structures and reasoning essential for addressing complex legal issues. |
| Approach: | They propose a Logical-Semantic Integration Model (LSIM) that bridges semantic and logical coherence and a supervised framework that integrates semantic features with in-context learning. |
| Outcome: | The proposed framework significantly improves accuracy and reliability on a real-world legal QA dataset. |
LLM-ForcedAligner: A Non-Autoregressive and Accurate LLM-Based Forced Aligner for Multilingual and Long-Form Speech (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for forcing alignment are language-specific and prone to temporal shifts. |
| Approach: | They propose a slot-filling paradigm that uses time indices to predict slot positions. |
| Outcome: | The proposed method reduces accumulated temporal shifts by 69% compared with prior methods. |
AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing LLMs are delicate and elusive in prompt words and styles. |
| Approach: | They propose an LLM-acquainted prompting technique that includes proficient "native-speaking" they propose to use in-context learning to prompt LLMs to perform high-performance reasoning . |
| Outcome: | The proposed technique achieves step-wise prompts in zero-shot scenarios while maintaining the prompt quality. |
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are a good starting point for downstream applications, but it is difficult to generalize them to new tasks given a few labeled samples. |
| Approach: | They propose to use Relation Graph augmented learning to improve the performance of few-shot natural language understanding tasks by rewriting the input sequence into a cloze question with masks. |
| Outcome: | Extensive experiments show that Relation Graph augmented learning (RGL) improves performance of prompt-based tuning strategies. |
Unsupervised Multi-hop Question Answering by Question Generation (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing training data for multi-hop question answering (QA) is time-consuming and resource-intensive. |
| Approach: | They propose an unsupervised framework that generates human-like multi-hop training data from homogeneous and heterogeneously data sources. |
| Outcome: | The proposed framework achieves 61% and 83% of the supervised learning performance for the HybridQA and HotpotQA datasets. |
Vulnerability of LLMs to Vertically Aligned Text Manipulations (2025.acl-long)
Copied to clipboard
| Challenge: | Recent research shows that vertical text input significantly degrades the accuracy of large language models (LLMs) in text classification tasks. |
| Approach: | They investigate the impact of vertical text input on the performance of LLMs . they find that chain of thought reasoning does not help LLM recognize vertical input . |
| Outcome: | The proposed model can significantly mislead models, posing a risk of bypassing detection in real-world scenarios involving harmful or sensitive information. |
Does ChatGPT Know That It Does Not Know? Evaluating the Black-Box Calibration of ChatGPT (2024.lrec-main)
Copied to clipboard
| Challenge: | Recent performance of ChatGPT in downstream tasks is questionable, but does it know that it does not know? |
| Approach: | They propose to use three types of proxy confidence to evaluate ChatGPT's black-box calibration ability. |
| Outcome: | The proposed model exhibits a positive correlation with accuracy in TruthfulQA and a negative correlation in the ModAr dataset. |
Towards Linear Time Neural Machine Translation with Capsule Networks (D19-1)
Copied to clipboard
| Challenge: | Neural Machine Translation (NMT) is an endto-end learning approach to machine translation. |
| Approach: | They propose a capsule network with dynamic routing for linear time Neural Machine Translation . they map the source sentence into a matrix with pre-determined size and apply a deep LSTM network to decode the target sequence from the source representation. |
| Outcome: | The proposed network achieves comparable results with the Transformer system on English-German and English-French tasks. |
Efficient and Accurate Prompt Optimization: the Benefit of Memory in Exemplar-Guided Reflection (2025.acl-long)
Copied to clipboard
Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaopu Wu, Kai Xiong, Qingsong Liu, Guoliang Kang, Yangyang Kang
| Challenge: | Recent work utilizes feedbacks generated from erroneous cases to guide prompt optimization . previous methods rely on computational resources and powerful GPUs . |
| Approach: | They propose an automatic prompt engineering method that leverages feedbacks from erroneous cases to guide prompt optimization. |
| Outcome: | The proposed method surpasses state-of-the-art methods with less steps and lower computational resources. |
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards (2024.acl-long)
Copied to clipboard
| Challenge: | Reinforcement Learning from Human Feedback (RLHF) relies on scalar rewards to capture user preferences. |
| Approach: | They propose a framework that integrates multi-objective reward modeling to represent diverse preference profiles. |
| Outcome: | The proposed method improves performance across reward objectives and targets. |
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. |
Unsupervised Paraphrasing with Pretrained Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Paraphrase generation has benefited from recent advances in the design of training objectives and model architectures, but previous studies focused on supervised methods that require a large amount of labeled data that is costly to collect. |
| Approach: | They propose a transfer learning approach that enables pre-trained language models to generate high-quality paraphrases in an unsupervised setting. |
| Outcome: | The proposed model performs state-of-the-art on the Quora Question Pair and ParaNMT datasets and is robust to domain shift between the two datasets. |
Bridging the Training-Inference Gap for Dense Phrase Retrieval (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for building dense retrievers are often misaligned and do not reflect retrieval scenario at inference time. |
| Approach: | They propose a way to validate dense retrievers using a small subset of the entire corpus. |
| Outcome: | The proposed model improves top-1 phrase retrieval accuracy by 2 3 points and top-20 passage retrieval by 2 4 points for open-domain question answering. |
RAGViz: Diagnose and Visualize Retrieval-Augmented Generation (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Large language models (LLMs) lack domain-specific knowledge and can cause hallucinations. |
| Approach: | They propose a RAG diagnosis tool that visualizes the attentiveness of the generated tokens in retrieved documents. |
| Outcome: | RAGViz provides token and document-level attention visualization and generation comparison upon context document addition and removal. |
Multi-agent Learning for Neural Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Experimental results show that training with more than one agent improves translation quality and improves accuracy. |
| Approach: | They propose to introduce diverse agents in an in- teractive updating process to train NMT models with an additional agent. |
| Outcome: | The proposed approach improves on NIST Chinese-English, IWSLT 2014 German- English, WMT 2014 English-German translation tasks and shows competitive performance on all tasks. |
Hey, That’s My Data! Token-Only Dataset Inference in Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing dataset inference methods require logit access, but many modern LLMs restrict such access. |
| Approach: | They propose a token-only dataset inference framework that allows models to overwrite prior knowledge when trained on new data. |
| Outcome: | The proposed framework overwrites prior knowledge when trained on new data. |
GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion (2025.findings-acl)
Copied to clipboard
Kangyang Luo, Yuzhuo Bai, Cheng Gao, Shuzheng Si, Zhu Liu, Yingli Shen, Zhitong Wang, Cunliang Kong, Wenhao Li, Yufei Huang, Ye Tian, Xuantang Xiong, Lei Han, Maosong Sun
| Challenge: | Existing knowledge graphs lack the ability to integrate structural information into LLMs and output predictions deterministically. |
| Approach: | They propose a method which encodes structural information of KGs and merges it with LLMs to enhance KGC performance. |
| Outcome: | The proposed method improves the performance of KG Completion datasets on KGs by integrating structural information with LLMs. |
Autocorrect in the Process of Translation — Multi-task Learning Improves Dialogue Machine Translation (2021.naacl-industry)
Copied to clipboard
| Challenge: | Existing neural machine translation models are not able to translate dialogues in real life scenarios. |
| Approach: | They propose a joint learning method to identify omission and typos and utilize context to translate dialogue utterances. |
| Outcome: | The proposed method improves translation quality by 3.2 BLEU over baselines and recovers omitted pronouns by 47.16%. |
HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have incorporated reward models to guide response selection or decoding, aiming to obtain higher-quality data. |
| Approach: | They propose a Hierarchical Sampling framework for self-taught reasoners that allocates a fixed sampling budget to problem boundary-level problems and then reallocates the remaining budget toward high-utility problems during a re-sampling phase. |
| Outcome: | The proposed framework outperforms baseline models without additional sampling budgets across multiple reasoning benchmarks and backbone LLMs. |
Interpretable Preferences via Multi-Objective Reward Modeling and Mixture-of-Experts (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Reinforcement learning from human feedback (RLHF) is the primary method for aligning large language models with human preferences. |
| Approach: | They propose to train an Absolute-Rating Multi-Objective Reward Model with multi-dimensional absolute-rating data. |
| Outcome: | The proposed model outperforms the LLM-as-a-judge method on RewardBench . it achieves state-of-the-art performance on the benchmark . |
Progressively Pretrained Dense Corpus Index for Open-Domain Question Answering (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing open-domain question answering systems are insufficient to capture deep semantic matching that goes beyond lexical overlaps. |
| Approach: | They propose a sample-efficient method to pretrain the paragraph encoder using an existing pretraining model instead of heuristically created pseudo question-paragraph pairs. |
| Outcome: | The proposed method outperforms a strong dense retrieval baseline that uses 6 times more computation for training. |
JanusMM: A Benchmark for Self-Deprecation Understanding in Real-World Multimodal Conversations (2026.acl-long)
Copied to clipboard
Xinyi Xu, Bingguang Hao, Yongyi Xiong, Zimo Chen, Xinchen Liu, Hongxin Guo, Xuelong Wang, Silin Zhou, Shihan Dou
| Challenge: | Multimodal large language models (MLLMs) are a common communicative strategy in human society, often using image-text interplay to express emotions and intentions. |
| Approach: | They propose to evaluate multimodal large language models (MLLMs)' understanding of self-deprecation in real-world conversations using 2,016 bilingual memes. |
| Outcome: | The proposed framework evaluates MLLMs' understanding of self-deprecation in real-world conversations. |
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)
Copied to clipboard
Sebastian Gehrmann, Abhik Bhattacharjee, Abinaya Mahendiran, Alex Wang, Alexandros Papangelis, Aman Madaan, Angelina Mcmillan-major, Anna Shvets, Ashish Upadhyay, Bernd Bohnet, Bingsheng Yao, Bryan Wilie, Chandra Bhagavatula, Chaobin You, Craig Thomson, Cristina Garbacea, Dakuo Wang, Daniel Deutsch, Deyi Xiong, Di Jin, Dimitra Gkatzia, Dragomir Radev, Elizabeth Clark, Esin Durmus, Faisal Ladhak, Filip Ginter, Genta Indra Winata, Hendrik Strobelt, Hiroaki Hayashi, Jekaterina Novikova, Jenna Kanerva, Jenny Chim, Jiawei Zhou, Jordan Clive, Joshua Maynez, João Sedoc, Juraj Juraska, Kaustubh Dhole, Khyathi Raghavi Chandu, Laura Perez Beltrachini, Leonardo F . R. Ribeiro, Lewis Tunstall, Li Zhang, Mahim Pushkarna, Mathias Creutz, Michael White, Mihir Sanjay Kale, Moussa Kamal Eddine, Nico Daheim, Nishant Subramani, Ondrej Dusek, Paul Pu Liang, Pawan Sasanka Ammanamanchi, Qi Zhu, Ratish Puduppully, Reno Kriz, Rifat Shahriyar, Ronald Cardenas, Saad Mahamood, Salomey Osei, Samuel Cahyawijaya, Sanja Štajner, Sebastien Montella, Shailza Jolly, Simon Mille, Tahmid Hasan, Tianhao Shen, Tosin Adewumi, Vikas Raunak, Vipul Raheja, Vitaly Nikolaev, Vivian Tsai, Yacine Jernite, Ying Xu, Yisi Sang, Yixin Liu, Yufang Hou
| Challenge: | Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work. |
| Approach: | They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations. |
| Outcome: | The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work. |
DT-Solver: Automated Theorem Proving with Dynamic-Tree Sampling Guided by Proof-level Value Function (2023.acl-long)
Copied to clipboard
Haiming Wang, Ye Yuan, Zhengying Liu, Jianhao Shen, Yichun Yin, Jing Xiong, Enze Xie, Han Shi, Yujun Li, Lin Li, Jian Yin, Zhenguo Li, Xiaodan Liang
| Challenge: | Recent advances in neural theorem-proving resort to large language models and tree searches. |
| Approach: | They propose a Dynamic-Tree Driven Theorem Solver to accommodate general theoremes by guiding the search procedure with state confidence and proof-level values. |
| Outcome: | The proposed method outperforms state-of-the-art methods on two popular theorem-proving datasets with a 6.65% improvement on average in terms of success rate. |
Cross-modality Data Augmentation for End-to-End Sign Language Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | End-to-end sign language translation (SLT) aims to convert sign language videos into spoken language texts without intermediate representations. |
| Approach: | They propose a cross-modality data-augmented framework to transfer gloss-to-text translation capabilities to end-to end sign language translation. |
| Outcome: | The proposed framework outperforms baseline models on two widely used SLT datasets. |
IPS: In-Prompt Process Supervision for Short Video Content Moderation (2026.acl-industry)
Copied to clipboard
| Challenge: | Multimodal large language models (MLLMs) capture semantics of short video content but fail to account for policy-specific details. |
| Approach: | They propose a framework that integrates In-prompt Process Supervision into MLLMs . they propose sequential reasoning over ancillary questions during fine-tuning . |
| Outcome: | IPS outperforms baseline MLLMs on public and proprietary benchmarks . replacing human-annotated ancillary labels with MLML-generated ones results in performance degradation. |
MultiFinBen: Benchmarking Large Language Models for Multilingual and Multimodal Financial Application (2026.acl-long)
Copied to clipboard
Xueqing Peng, Lingfei Qian, Yan Wang, Ruoyu Xiang, Yueru He, Yang Ren, Mingyang Jiang, Vincent Jim Zhang, Yuqing Guo, Jeff Zhao, Huan He, Yi Han, Yun Feng, Yuechen Jiang, Yupeng Cao, Haohang Li, Yangyang Yu, Xiaoyu Wang, Penglei Gao, Shengyuan Lin, Keyi Wang, Shanshan Yang, Yilun Zhao, Zhiwei Liu, Peng Lu, Jerry Huang, Suyuchen Wang, Triantafillos Papadopoulos, Polydoros Giannouris, Efstathia Soufleri, Nuo Chen, Zhiyang Deng, Heming Fu, Yijia Zhao, Mingquan Lin, Meikang Qiu, Kaleb E Smith, Arman Cohan, Xiao-Yang Liu, Jimin Huang, Guojun Xiong, Alejandro Lopez-Lira, Xi Chen, Junichi Tsujii, Jian-Yun Nie, Sophia Ananiadou, Qianqian Xie
| Challenge: | Existing evaluations of LLMs in finance are text-only, monolingual, and largely saturated by current models. |
| Approach: | They propose a multilingual and multimodal benchmark for evaluating LLMs in real financial contexts. |
| Outcome: | The first expert-annotated multilingual and multimodal benchmark is released . it evaluates 21 leading LLMs and shows they perform better in multilingual settings . |
GenDis: Generative-Discriminative Dual-View Co-Training for Generalized Category Discovery (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods rely on one-hot discriminative supervision, leading to overfitting on seen classes and poor generalization to unseen ones. |
| Approach: | They propose a Generative–Discriminative Dual-View Co-Training framework that unifies discriminative classification and semantic label generation within an LLM. |
| Outcome: | The proposed framework outperforms existing methods on five benchmarks on the generalized category discovery (GCD) task. |
Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation (2025.acl-industry)
Copied to clipboard
Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong
| Challenge: | Effective content moderation is essential for video platforms to safeguard user experience and uphold community standards. |
| Approach: | They propose a method to transform a generative MLLM into a multimodal classifier using minimal discriminative training data. |
| Outcome: | The proposed method improves F1 score by 66.50% over traditional classifiers while requiring only 2% of the fine-tuning data. |
Secoco: Self-Correcting Encoding for Neural Machine Translation (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Neural machine translation (NMT) is a challenging field due to the wide variety of noises in real-world scenarios. |
| Approach: | They propose a framework that explicitly deals with noisy inputs for robust neural machine translation by introducing self-correcting predictors. |
| Outcome: | The proposed framework can correct noisy inputs and delete specific errors with the translation decoding process. |
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Rapid advances in Large Language Models have spurred demand for processing extended context sequences . however, performance degradation due to sequence lengths out-of-distribution and excessively long inference times are limiting LLMs in long-context scenarios. |
| Approach: | They propose a training-free method for efficient and accurate long-context inference . they selectively involves a few critical KV cache tokens in attention calculation . |
| Outcome: | The proposed method speeds up attention computation and accelerates inference time while reducing selection overhead. |
Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking (2020.starsem-1)
Copied to clipboard
| Challenge: | Existing methods for dialog state tracking are ontology-based and ontologie-free . however, it is not clear enough which slots are better handled by either of the two methods . |
| Approach: | They propose a dual-strategy model that integrates both ontology-based and ontological-free methods. |
| Outcome: | The proposed model outperforms the existing model on noisy and cleaner datasets. |
Adversarial Preference Learning for Robust LLM Alignment (2025.findings-acl)
Copied to clipboard
Yuanfu Wang, Pengyu Wang, Chenyang Xi, Bo Tang, Junyi Zhu, Wenqiang Wei, Chen Chen, Chao Yang, Jingfeng Zhang, Chaochao Lu, Yijun Niu, Keming Mao, Zhiyu Li, Feiyu Xiong, Jie Hu, Mingchuan Yang
| Challenge: | Modern language models rely on Reinforcement Learning from Human Feedback (RLHF) to encourage safe behaviors, but they remain vulnerable to adversarial attacks due to three key limitations: (1) the inefficiency and high cost of human annotation; (2) the vast diversity of potential adversarials; and (3) the risk of feedback bias and reward hacking. |
| Approach: | They propose an iterative adversarial training method that incorporates three key innovations to address these challenges. |
| Outcome: | Experiments on Mistral-7B-Instruct-v0.3 show that the proposed method significantly enhances robustness and reduces harmful outputs from 5.88% to 0.43%. |
Exploring Semantic Capacity of Terms (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing models that measure semantic capacity of terms are not all considered equal . a good command of semantic capacity will give us more insight into the granularity of terms . |
| Approach: | They propose a model that evaluates semantic capacity of terms if text corpus can provide enough co-occurrence information of terms. |
| Outcome: | The proposed model can evaluate semantic capacity of terms if the corpus can provide enough co-occurrence information of terms. |
Long Document Ranking with Query-Directed Sparse Transformer (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to document ranking require long documents to be broken to fit in pretrained models. |
| Approach: | They propose a Query-Directed Sparse attention model that induces IR-axiomatic structures in transformer self-attention. |
| Outcome: | The proposed model enforces the principle properties desired in ranking while also enjoying efficiency from sparsity. |
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback (2025.findings-acl)
Copied to clipboard
Thai Quoc Hoang, Kung-Hsiang Huang, Shirley Kokane, Jianguo Zhang, Zuxin Liu, Ming Zhu, Jake Grigsby, Tian Lan, Michael S Ryoo, Chien-Sheng Wu, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong, Juan Carlos Niebles
| Challenge: | Large Action Models (LAMs) face challenges due to the need for high-quality training data, especially for multi-steps tasks that involve planning, executing tool calls, and responding to feedback. |
| Approach: | They propose a framework for online exploration of agentic tasks with high-quality feedback . they use a dynamic task query generator and an extensive collection of tools to create a high-level feedback environment for LLM Agents. |
| Outcome: | The proposed framework achieves 49.3% performance improvement over baselines on toolbench and CRMArena. |
Efficient Cluster-Based k-Nearest-Neighbor Machine Translation (2022.acl-long)
Copied to clipboard
| Challenge: | k-Nearest-Neighbor Machine Translation (kNN-MT) is a non-parametric solution for domain adaptation . previous studies have shown that kNN retrieval is at the expense of high latency . |
| Approach: | They propose to use clustering to improve retrieval efficiency by combining a non-parametric MT with an in-domain feature-based retrieval module. |
| Outcome: | The proposed method reduces translation latency by 57% while maintaining the most useful information of the original datastore. |
Watch Every Step! LLM Agent Learning via Iterative Step-level Process Refinement (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent approaches to enhance agent performance focus on outcome rewards, which may lead to errors or suboptimal actions due to the absence of process supervision signals. |
| Approach: | They propose a step-level framework that provides detailed step-by-step guidance to enhance agent training by using Monte Carlo methods. |
| Outcome: | The proposed framework outperforms strong baselines on three tasks and shows that it is effective in augmenting efficiency and its applicability to diverse models. |
MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation (2025.findings-acl)
Copied to clipboard
Zhongwei Wan, Che Liu, Xin Wang, Chaofan Tao, Hui Shen, Jing Xiong, Rossella Arcucci, Huaxiu Yao, Mi Zhang
| Challenge: | Recent studies have focused on classifying cardiac conditions using ECG data but have overlooked ECG report generation, which is time-consuming and requires clinical expertise. |
| Approach: | They propose a Multimodal ECG Instruction Tuning framework that extends the capability of large language models (LLMs) for the task. |
| Outcome: | The proposed framework outperforms open-source LLMs and LLM backbones across two large-scale ECG datasets. |
A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing models are vulnerable to adversarial attacks, but their vulnerability is underexplored. |
| Approach: | They propose to concatenate a perturbed but semantically similar tweet into a model that fools stock prediction models. |
| Outcome: | The proposed method achieves consistent success rates and causes significant monetary loss in trading simulation by simply concatenating a perturbed but semantically similar tweet. |
LATTE: Learning to Think with Vision Specialists (2025.emnlp-main)
Copied to clipboard
Zixian Ma, Jianguo Zhang, Zhiwei Liu, Jieyu Zhang, Juntao Tan, Manli Shu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Caiming Xiong, Ranjay Krishna, Silvio Savarese
| Challenge: | Open-source vision-language models excel on simple question-answering tasks, but struggle with complex questions that require both perception and reasoning. |
| Approach: | They propose a family of vision-language models that have LeArned to Think wiTh vision spEcialists by offloading perception to state-of-the-art vision models. |
| Outcome: | The proposed model achieves 4-5% gains over baselines across 6 benchmarks covering both perception and reasoning abilities. |
MDC-Bench: A Multidisciplinary Causal Benchmark Based on Causal Structures for Evaluating Large Language Models (2026.findings-acl)
Copied to clipboard
Peng Wang, Yuxiong Yan, Xiao Ding, Kai Xiong, Bibo Cai, Chao Peng, Yutai Hou, Dandan Tu, Bing Qin, Ting Liu
| Challenge: | Existing causal datasets focus on the commonsense domain, but LLMs perform poorly when answering complex questions. |
| Approach: | They propose a multidisciplinary causal evaluation benchmark to assess LLMs' knowledge and skills. |
| Outcome: | The proposed model improves in domain specialization, structural diversity, and task complexity. |
Linking Adaptive Structure Induction and Neuron Filtering: A Spectral Perspective for Aspect-based Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | incorporating structure information can improve the performance of aspect-based sentiment analysis. |
| Approach: | They propose a method to conduct neuron-level manipulations on word representations in the frequency domain. |
| Outcome: | The proposed method can achieve or come close to state-of-the-art in ABSA. |
HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depth (2025.findings-emnlp)
Copied to clipboard
Yan Liu, Minghui Zhang, Bojian Xiong, Yifan Xiao, Yinong Sun, Yating Mei, Longyu Zeng, Jingchao Yang, Yang Wang, Deyi Xiong
| Challenge: | a gap in math models' accuracy has been widened with the development of large language models (LLMs) . a new study aims to bridge this gap by evaluating a set of high-level math reasoning models . |
| Approach: | They propose to evaluate large language models on existing math benchmarks to bridge this gap . they collect 5,293 problems from Chinese senior high school mathematics exams . |
| Outcome: | The proposed model is based on o1-like models and a high-level model. |
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 . |
RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for evicting KV pairs rely on the "persistence of importance" hypothesis . visual tokens display "deferred importance" but become pivotal during later decoding, authors say . |
| Approach: | They propose an entropy-driven method that reformulates KV eviction from "discrete context truncation" to "continuous memory evolution" they propose to prune visual tokens with "deferred importance" visual token exhibiting low salience but becoming pivotal during later decoding . |
| Outcome: | The proposed method achieves 5.0 KV cache compression and 1.5 decoding acceleration. |
MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models (2025.emnlp-demos)
Copied to clipboard
Zhiwei Liu, Jielin Qiu, Shiyu Wang, Jianguo Zhang, Zuxin Liu, Roshan Ram, Haolin Chen, Weiran Yao, Shelby Heinecke, Silvio Savarese, Huan Wang, Caiming Xiong
| Challenge: | Existing evaluation frameworks suffer from limitations such as static task benchmarks, limited scope, and inadequate integration with practical applications. |
| Approach: | They propose an open-source, Model Context Protocol-based evaluation framework specifically tailored for comprehensive and systematic assessment of LLM-powered agents. |
| Outcome: | The proposed framework uncovers nuanced performance patterns and identify domain-specific strengths and weaknesses, providing valuable insights beyond traditional binary success metrics. |
AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives (2026.findings-acl)
Copied to clipboard
Yanxi Chen, Wenhui Zhu, Xiwen Chen, Zhipeng Wang, Xin Li, Peijie Qiu, Hao Wang, Xuanzhao Dong, Yujian Xiong, Anderson Schneider, Yuriy Nevmyvaka, Yalin Wang
| Challenge: | Large Audio-Language Models suffer from hallucinations, e.g., generating text not grounded in the audio input. |
| Approach: | They propose a framework to address hallucination problems in large audio-language models . they use a preference dataset to test the model's accuracy . |
| Outcome: | The proposed model outperforms the latest SOTA methods in terms of performance and generalization. |
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. |
Rationale-Enhanced Language Models are Better Continual Relation Learners (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have found that catastrophic forgetting arises from the model’s lack of robustness against future analogous relations. |
| Approach: | They propose a multi-task rationale tuning strategy to help the model learn current relations robustly and conduct contrastive rationale replay to further distinguish analogous relations. |
| Outcome: | The proposed method outperforms the state-of-the-art models on two benchmarks. |
AnchorAlign: A Novel Anchor Alignment-enhanced Generative Method for Joint Named Entity Recognition and Relation Extraction (2026.findings-acl)
Copied to clipboard
| Challenge: | Named Entity Recognition and Relation Extraction are interdependent tasks in information extraction. |
| Approach: | They propose a generative method enhanced by anchor alignment to bridge NER and RE tasks . they use anchor entities as semantic pivots to align the two tasks based on their semantic representations . |
| Outcome: | The proposed method outperforms state-of-the-art models on five benchmark datasets. |
Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM-based recommenders lack explicit modeling of geographic signals . without explicit modeling geographic signals, recommenders struggle to capture core mobility patterns . |
| Approach: | They propose a framework that utilizes geography as a decision variable within the reasoning process. |
| Outcome: | The proposed framework achieves over 10% relative gains in hit rate over strongest LLM-based baselines and improves cross-city transfer. |
Effective Long-Context Scaling of Foundation Models (2024.naacl-long)
Copied to clipboard
Wenhan Xiong, Jingyu Liu, Igor Molybog, Hejia Zhang, Prajjwal Bhargava, Rui Hou, Louis Martin, Rashi Rungta, Karthik Abinav Sankararaman, Barlas Oguz, Madian Khabsa, Han Fang, Yashar Mehdad, Sharan Narang, Kshitiz Malik, Angela Fan, Shruti Bhosale, Sergey Edunov, Mike Lewis, Sinong Wang, Hao Ma
| Challenge: | Large language models (LLMs) are rapidly deployed and continue to evolve through scaling. |
| Approach: | They propose a method to train strong long-context LLMs that are capable of utilizing massive context windows of up to 32,000 tokens. |
| Outcome: | The proposed model can surpass gpt-3.5-turbo-16k's overall performance on long-context benchmarks with a cost-effective instruction tuning procedure that is free of expensive annotations. |
Text2Mem: A Unified Memory Operation Language for Memory Operating System (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing memory frameworks lack a formal, executable specification for memory control. |
| Approach: | They propose a unified memory operation language that standardizes translation of natural-language instructions into reliable execution. |
| Outcome: | The proposed language standardizes translation of natural-language instructions into reliable execution. |
Developing a Reliable, Fast, General-Purpose Hallucination Detection and Mitigation Service (2025.naacl-industry)
Copied to clipboard
| Challenge: | Hallucination is a problem in large language models that produce incorrect output . authors propose a reliable and high-speed production system to detect and rectify hallucinations . |
| Approach: | They propose a high-speed production system that detects hallucinations in LLMs . they propose NER, natural language inference, span-based detection and a rewriting mechanism . |
| Outcome: | The proposed system detects a wide range of hallucinations in LLM responses. |
PersonaAgent: Bridging Memory and Action for Personalized LLM Agents (2026.findings-acl)
Copied to clipboard
Weizhi Zhang, Xinyang Zhang, Chenwei Zhang, Liangwei Yang, Jingbo Shang, Zhepei Wei, Henry Peng Zou, Zijie Huang, Zhengyang Wang, Yifan Gao, Xiaoman Pan, Lian Xiong, Jingguo Liu, Philip S. Yu, Xian Li
| Challenge: | Existing Large Language Model (LLM) enabled agents lack flexibility to respond to users’ varying needs and preferences. |
| Approach: | They propose a test-time user-preference alignment strategy that optimizes the persona prompt, ensuring real-time preference alignment through textual loss feedback between simulated and ground-truth responses. |
| Outcome: | The proposed framework outperforms baseline methods in real-time and in real applications. |
LLM Sensitivity Evaluation Framework for Clinical Diagnosis (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies on the sensitivity of Large Language Models (LLMs) to irrelevant contexts neglect the importance of key information. |
| Approach: | They investigate the sensitivity of large language models to key medical information by introducing different perturbation strategies to investigate their sensitivity. |
| Outcome: | The proposed models are based on three LLMs, namely GPT-3.5, GPT-4, Gemini, Claude3 and LLaMA2-7b, and demonstrate their reliability and sensitivity to medical information. |
UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models (2022.emnlp-main)
Copied to clipboard
Tianbao Xie, Chen Henry Wu, Peng Shi, Ruiqi Zhong, Torsten Scholak, Michihiro Yasunaga, Chien-Sheng Wu, Ming Zhong, Pengcheng Yin, Sida I. Wang, Victor Zhong, Bailin Wang, Chengzu Li, Connor Boyle, Ansong Ni, Ziyu Yao, Dragomir Radev, Caiming Xiong, Lingpeng Kong, Rui Zhang, Noah A. Smith, Luke Zettlemoyer, Tao Yu
| Challenge: | Structured knowledge grounding (SKG) uses structured knowledge to complete user requests . since inputs and outputs of SKG tasks are heterogeneous, they have been studied separately . |
| Approach: | They propose a framework that unifies 21 SKG tasks into a text-to-text format . they use unifiedSKG to benchmark T5 with different sizes . |
| Outcome: | The proposed framework unifies 21 SKG tasks into a text-to-text format . it achieves state-of-the-art performance on almost all of the 21 tasks, the authors show . |
Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing (N19-1)
Copied to clipboard
| Challenge: | Existing entity typing systems exploit type hierarchy provided by KB schema to model label correlations. |
| Approach: | They propose a graph layer that encodes global label co-occurrence statistics and word-level similarities. |
| Outcome: | The proposed model achieves a 15.3% relative F1 improvement on a large dataset with over 10,000 free-form types. |
PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for visually-rich document information extraction are limited . Xu et al., 2020: visually rich document information is a vital aspect of document understanding . |
| Approach: | They propose a plug-and-play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents. |
| Outcome: | The proposed method outperforms fine-tuning and few-shot methods on visual-rich documents. |
Lang2Act: Fine-Grained Visual Reasoning through Self-Emergent Linguistic Toolchains (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing frameworks depend on rigid, pre-defined external tools to extend perceptual capabilities of VLMs. |
| Approach: | They propose a framework that leverages self-emergent linguistic toolchains to enhance visual perception and reasoning. |
| Outcome: | The proposed framework improves the visual perception capabilities of large language models by incorporating external visual documents to address a given query. |
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods to debias word embeddings from human-generated corpora inherit strong gender bias . prior work has suggested removing gender component from pre-trained word embeds or compressing gender information into a few dimensions of the embeddable space . |
| Approach: | They propose a technique that purifies word embeddings against inferred gender subspaces . they propose to preserve distributional semantics of pre-trained word embeds while reducing gender bias . |
| Outcome: | The proposed technique preserves distributional semantics of pre-trained word embeddings while reducing gender bias to a larger degree than prior approaches. |
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. |
StyleBART: Decorate Pretrained Model with Style Adapters for Unsupervised Stylistic Headline Generation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on unsupervised headline generation focus on a standard dataset and mono-style corpora. |
| Approach: | They propose an unsupervised approach for stylistic headline generation using a pretrained BART model decorated with adapters responsible for different styles. |
| Outcome: | The proposed method separates the task of style learning and headline generation, allowing for the generation of diverse headlines with diverse styles. |
Reasoning-Aware AIGC Detection via Alignment and Reinforcement (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to AIGC detection have relied on statistical classifiers or black-box neural models, which exploit surface-level patterns and struggle to generalize as LLMs evolve. |
| Approach: | They propose a framework that generates interpretable reasoning chains before classification using supervised fine-tuning and reinforcement learning to improve accuracy. |
| Outcome: | The proposed framework achieves state-of-the-art performance across multiple benchmarks, offering a robust and transparent solution for AIGC detection. |
Adversarially Improving NMT Robustness to ASR Errors with Confusion Sets (2022.aacl-short)
Copied to clipboard
| Challenge: | Existing methods for robustness against homophone errors are limited to homophones . substitution errors are the most common errors in NMT models . |
| Approach: | They propose an adversarial example generation method based on confusion sets that contain words easily confusable with a target word by ASR to conduct adversarially training for NMT models. |
| Outcome: | The proposed method improves on the clean test set and can be used in real-world scenarios. |
QAEncoder: Towards Aligned Representation Learning in Question Answering Systems (2025.acl-long)
Copied to clipboard
Zhengren Wang, Qinhan Yu, Shida Wei, Zhiyu Li, Feiyu Xiong, Xiaoxing Wang, Simin Niu, Hao Liang, Wentao Zhang
| Challenge: | Modern QA systems entail retrieval-augmented generation (RAG) for accurate and trustworthy responses, but the inherent gap between user queries and relevant documents hinders precise matching. |
| Approach: | They propose a retrieval-augmented generation (RAG)-based approach to bridge this gap by attaching document fingerprints to the embedding to estimate the expectation of potential queries. |
| Outcome: | Experiments across diverse datasets, languages, and embedding models confirm the proposed solution is simple-yet-effective with zero additional index storage, retrieval latency, training costs, or catastrophic forgetting and hallucination issues. |
NewsBench: A Systematic Evaluation Framework for Assessing Editorial Capabilities of Large Language Models in Chinese Journalism (2024.acl-long)
Copied to clipboard
Miao Li, Ming-Bin Chen, Bo Tang, ShengbinHou ShengbinHou, Pengyu Wang, Haiying Deng, Zhiyu Li, Feiyu Xiong, Keming Mao, Cheng Peng, Yi Luo
| Challenge: | a novel evaluation framework assesses the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. |
| Approach: | They propose to use a benchmark dataset to assess the capabilities of Large Language Models (LLMs) for editorial capabilities in Chinese journalism. |
| Outcome: | The proposed evaluation framework is based on a dataset of 1,267 test samples in 24 news domains. |
UNICORN: A Unified Causal Video-Oriented Language-Modeling Framework for Temporal Video-Language Tasks (2024.emnlp-main)
Copied to clipboard
Yuanhao Xiong, Yixin Nie, Haotian Liu, Boxin Wang, Jun Chen, Rong Jin, Cho-Jui Hsieh, Lorenzo Torresani, Jie Lei
| Challenge: | Recent advances in large multimodal models have encouraged the development of large multi-modal models . however, it is unclear how to extend these models to the more complex video domain . |
| Approach: | They propose a visual instruction tuning framework to address temporal video-language tasks . they collect a dataset and fine-tune the framework on instruction-following data . |
| Outcome: | The proposed model can perform better on established temporal video-language tasks without training objectives and intensive pre-training. |
SR-RAG: Verifiable Multi-Hop Reasoning via On-the-fly Symbolic Graph Construction (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing paradigms for multi-hop reasoning suffer from high construction costs and limited adaptability to dynamic knowledge. |
| Approach: | They propose a symbolic reasoning framework for multi-hop question answering that integrates the advantages of both paradigms by dynamically generating sub-questions, performing information retrieval and symbolic encoding based on an on-the-fly graph and using a symbol verifier to validate intermediate reasoning steps. |
| Outcome: | The proposed framework significantly improves accuracy and robustness on multiple multi-hop benchmarks and a medical dataset. |
TWEETQA: A Social Media Focused Question Answering Dataset (P19-1)
Copied to clipboard
Wenhan Xiong, Jiawei Wu, Hong Wang, Vivek Kulkarni, Mo Yu, Shiyu Chang, Xiaoxiao Guo, William Yang Wang
| Challenge: | Social media is becoming an important realtime information source, especially during natural disasters and emergencies. |
| Approach: | They present a large-scale dataset for question answering over social media data . they gather tweets used by journalists and ask human annotators to write questions upon them . |
| Outcome: | The proposed dataset shows that neural models that perform well on formal texts are limited in their performance . the proposed model is still lagging behind human performance with a large margin . |
StepCoder: Improving Code Generation with Reinforcement Learning from Compiler Feedback (2024.acl-long)
Copied to clipboard
Shihan Dou, Yan Liu, Haoxiang Jia, Enyu Zhou, Limao Xiong, Junjie Shan, Caishuang Huang, Xiao Wang, Xiaoran Fan, Zhiheng Xi, Yuhao Zhou, Tao Ji, Rui Zheng, Qi Zhang, Tao Gui, Xuanjing Huang
| Challenge: | Existing work integrates reinforcement learning with compiler feedback to enhance code generation quality but the long code generated by LLMs makes RL exploration ineffective. |
| Approach: | They propose a framework that integrates reinforcement learning and compiler feedback to enhance code generation quality. |
| Outcome: | The proposed framework outperforms state-of-the-art approaches in corresponding benchmarks and integrates reinforcement learning with compiler feedback to improve code generation quality. |
Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation (2026.acl-long)
Copied to clipboard
Jiang Zhou, Xiaohu Zhao, Xinwei Wu, Tianyu Dong, Hao Wang, Yangyang Liu, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Deyi Xiong
| Challenge: | Current systems often fall short of this goal in settings where translation hinges on culturally grounded entities such as books, films, places, songs and idioms. |
| Approach: | They propose a framework that anchors supervision on a verifiable, entity-level reward signal and incorporates lightweight structural gates to stabilize optimization. |
| Outcome: | The proposed framework improves on XC-Translate and shows that it can learn a robust reasoning process rather than imitating reference translations. |
Text-guided 3D Human Generation from 2D Collections (2023.findings-emnlp)
Copied to clipboard
| Challenge: | 3D human modeling is used for engaging interaction in gaming, film, and animation. however, the customization of characters is crucial for creativity and scalability. |
| Approach: | They propose a 3D human generation using fashion descriptions to enhance 3D geometry transformation and fine-grained consistency. |
| Outcome: | The proposed model can generate a 3D human, guided by a fashion description, with high efficiency. |
InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-training (2025.acl-long)
Copied to clipboard
Dingdong Wang, Jin Xu, Ruihang Chu, Zhifang Guo, Xiong Wang, Jincenzi Wu, Dongchao Yang, Shengpeng Ji, Junyang Lin
| Challenge: | Recent advances in speech large language models exhibit suboptimal performance in adhering to speech instructions. |
| Approach: | They propose a method to pre-train large-scale unsupervised speech-text sequences . they use text-to-speech conversion to generate textual continuations corresponding to provided speech segments . |
| Outcome: | The proposed model achieves superior or competitive results across diverse speech processing tasks. |
SAIR-Comb : A Structure-Aware Iterative Refinement Framework for Combinatorics Autoformalization (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have catalyzed advances in mathematical reasoning, propelling the development of automated theorem proving (ATP). |
| Approach: | They propose a Structure-Aware Iterative Refinement framework for Combinatorics powered by Lean 4 and LLMs. |
| Outcome: | The proposed framework achieves strong performance on the specialized CombiBench while remaining highly competitive on general-domain benchmarks. |
Neural Machine Translation with Decoding History Enhanced Attention (C18-1)
Copied to clipboard
| Challenge: | Neural machine translation with source-side attention has been criticized for its poor memory performance. |
| Approach: | They propose to use a Decoding History Enhanced Attention mechanism to render NMT models better at selecting both source-side and target-side information. |
| Outcome: | The proposed model improves by 0:9 BLEU on Chinese-English translation and the state-of-the-art on a larger task. |
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment (2026.findings-acl)
Copied to clipboard
Tianyu Dong, Yangyang Liu, Jiang Zhou, Xinwei Wu, Xiaohu Zhao, Hao Wang, Heng Liu, Linlong Xu, Longyue Wang, Weihua Luo, Shaolin Zhu, Deyi Xiong
| Challenge: | Low-resource language tokens are often routed to different experts than those activated by high-resourced inputs, which hinders their efficacy in multilingual contexts. |
| Approach: | They propose a framework to transfer specialized capabilities from high-resource languages as anchors to low-resourced languages by using a symmetric Jensen-Shannon constraint. |
| Outcome: | The proposed framework outperforms standard instruction tuning on 5 low-resource languages and 3 benchmarks. |
MedCite: Can Language Models Generate Verifiable Text for Medicine? (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing LLM-based medical question answering systems lack citation generation and evaluation capabilities, raising concerns about their adoption in practice. |
| Approach: | They propose a framework that facilitates the design and evaluation of LLM citations for medical tasks and a retrieval-citation method that generates high-quality citation. |
| Outcome: | The proposed method achieves superior citation precision and recall improvements compared to strong baseline methods and correlates well with annotation results from professional experts. |
SPE: Symmetrical Prompt Enhancement for Fact Probing (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work probes PLMs for the extent of factual knowledge through prompts . however, these methods do not consider symmetry of the task: object and subject prediction. |
| Approach: | They propose a continuous prompt-based method that leverages symmetry of the task by constructing symmetrical prompts for subject and object prediction. |
| Outcome: | The proposed method improves on a popular factual probing dataset on lAMA. |
CRMArena: Understanding the Capacity of LLM Agents to Perform Professional CRM Tasks in Realistic Environments (2025.naacl-long)
Copied to clipboard
Kung-Hsiang Huang, Akshara Prabhakar, Sidharth Dhawan, Yixin Mao, Huan Wang, Silvio Savarese, Caiming Xiong, Philippe Laban, Chien-Sheng Wu
| Challenge: | Existing benchmarks for evaluating CRM agents on work-related tasks are limited due to data privacy concerns. |
| Approach: | They propose a benchmark to evaluate AI agents on real-world CRM tasks . they use 16 commonly used industrial objects with high interconnectivity to simulate real data distributions. |
| Outcome: | The new benchmark evaluates AI agents on real-world customer service tasks . it includes 16 commonly used industrial objects with high interconnectivity . the results highlight the need for enhanced agent capabilities in function-calling and rule-following . |
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser Use (2025.acl-long)
Copied to clipboard
Xueyu Hu, Tao Xiong, Biao Yi, Zishu Wei, Ruixuan Xiao, Yurun Chen, Jiasheng Ye, Meiling Tao, Xiangxin Zhou, Ziyu Zhao, Yuhuai Li, Shengze Xu, Shenzhi Wang, Xinchen Xu, Shuofei Qiao, Zhaokai Wang, Kun Kuang, Tieyong Zeng, Liang Wang, Jiwei Li, Yuchen Eleanor Jiang, Wangchunshu Zhou, Guoyin Wang, Keting Yin, Zhou Zhao, Hongxia Yang, Fan Wu, Shengyu Zhang, Fei Wu
| Challenge: | a new generation of (M)LLMs is enabling the creation of superintelligent AI assistants . OS Agents can complete tasks autonomously and have the potential to significantly enhance the lives of billions of users worldwide. |
| Approach: | They propose to build OS Agents that operate within operating systems' GUIs and GUIs . they examine evaluation metrics and benchmarks to identify promising directions . |
| Outcome: | The proposed agents are based on operating systems (OS) and operating systems frameworks. |
Interpret and Control Dense Retrieval with Sparse Latent Features (2025.naacl-short)
Copied to clipboard
| Challenge: | Dense embeddings deliver strong retrieval performance but lack interpretability and controllability. |
| Approach: | They propose a novel approach using sparse autoencoders to interpret and control dense embeddings via latent sparsity. |
| Outcome: | The proposed approach retains the same retrieval accuracy as the original dense vectors, affirming their faithfulness. |
xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)
Copied to clipboard
Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
| Challenge: | Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks. |
| Approach: | They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance. |
| Outcome: | The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks. |
Learning to Synthesize Data for Semantic Parsing (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing methods for synthesizing data for semantic parsing require handcrafted rules to synthesize new programs or utterance-program pairs. |
| Approach: | They propose to use a (non-neural) PCFG to model the composition of programs and a BART-based translation model to map a program to an utterance to learn a generative model from existing data. |
| Outcome: | The proposed model can be efficiently learned from existing data on benchmarks of GeoQuery and Spider. |
Decoding at the Speed of Thought: Harnessing Parallel Decoding of Lexical Units for LLMs (2024.lrec-main)
Copied to clipboard
Chenxi Sun, Hongzhi Zhang, Zijia Lin, Jingyuan Zhang, Fuzheng Zhang, Zhongyuan Wang, Bin Chen, Chengru Song, Di Zhang, Kun Gai, Deyi Xiong
| Challenge: | Large language models have demonstrated exceptional capability in natural language understanding and generation, but their generation speed is limited by the inherently sequential nature of their decoding process. |
| Approach: | They propose a method that accelerates decoding process without sacrificing quality . they propose lexical unit decoding, which can be integrated with other methods . |
| Outcome: | The proposed method significantly reduces decoding time while maintaining quality while maintaining output quality. |
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features (N19-2)
Copied to clipboard
Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin
| Challenge: | e-commerce companies often have the option of escalating complaints by filing grievances with a government authority . this is detrimental to an ecommerce company, but this problem is challenging to solve by integrating recurrent neural networks with manually-engineered features. |
| Approach: | They propose a model that integrates recurrent neural networks with manually-engineered features to identify cases where the customer expresses such an intent. |
| Outcome: | The proposed model outperforms baseline models and provides better recall and triage for specialized agents. |
Variational Knowledge Graph Reasoning (N18-1)
Copied to clipboard
| Challenge: | Existing knowledge graphs have large amount of missing links, which limits their application . a recent study has proposed to design an automated inference model to complete the missing links in large knowledge graph. |
| Approach: | They propose to use variation inference to solve missing links in knowledge graphs . they use a posterior approximator, prior (path finder) and likelihood (path reasoner) |
| Outcome: | The proposed model achieves state-of-the-art on multiple datasets and is highly accurate. |
HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Traditional retrieval systems focus on lexical or semantic similarity rather than logical relevance. |
| Approach: | They propose a new RAG framework that augments retrieval with logical reasoning . hopRAG uses a retrieve-reason-prune mechanism to explore multi-hop neighbors . |
| Outcome: | The proposed framework outperforms conventional retrieval systems and state-of-the-art benchmarks on multi-hop QA tasks. |
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following (2026.acl-long)
Copied to clipboard
Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, Yuanhao Xiong, Nanshu Wang, Xiaoliang Peng, Beibin Li, Shengjie Bi, Shishir G Patil, Qi Qi, Shengyu Feng, Julian Katz-Samuels, Richard Yuanzhe Pang, Sujan Kumar Gonugondla, Hunter Lang, Yue Yu, Yundi Qian, Maryam Fazel-Zarandi, Licheng Yu, Amine Benhalloum, Hany Hassan Awadalla, Manaal Faruqui
| Challenge: | Recent advances in large language models (LLMs) have shown impressive performance on a range of tasks, yet advanced instruction following (IF) remains a significant challenge. |
| Approach: | They propose a benchmark that features over 1,600 prompts and expert-curated rubrics that assess LLMs’ ability to follow complex, multi-turn, and system-level instructions. |
| Outcome: | The proposed framework improves instruction-following abilities of large language models, achieving a 6.7% gain on AdvancedIF and strong results on public benchmarks. |
Understand User Opinions of Large Language Models via LLM-Powered In-the-Moment User Experience Interviews (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing large language models (LLMs) are difficult to evaluate and often lack the ability to capture user opinions. |
| Approach: | They propose an LLM-powered interviewer that conducts in-the-moment user experience interviews right after users interact with LLMs and automatically gathers insights about user opinions from massive interview logs. |
| Outcome: | The proposed interviewer captures interesting user opinions, e.g., bipolar views on the displayed reasoning process of DeepSeek-R1 and demands for information freshness and multi-modality. |
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model (2025.acl-long)
Copied to clipboard
Xun Liang, Simin Niu, Zhiyu Li, Sensen Zhang, Hanyu Wang, Feiyu Xiong, Zhaoxin Fan, Bo Tang, Jihao Zhao, Jiawei Yang, Shichao Song, Mengwei Wang
| Challenge: | Existing approaches to integrating external knowledge into large language models (LLMs) however, the incorporation of external knowledge increases the vulnerability of LLMs . |
| Approach: | They propose a benchmark to evaluate the RAG security using a dataset . they classify attack tasks into silver noise, inter-context conflict, soft ad, and white Denial-of-Service . |
| Outcome: | The proposed benchmark evaluates the security of RAG against 14 representative RAG components. |
Open-Domain Question-Answering for COVID-19 and Other Emergent Domains (2021.emnlp-demo)
Copied to clipboard
| Challenge: | a system for open-domain question-answering is developed for COVID-19 . small data size allows system to retrieve answers from large corpus of scientific papers . |
| Approach: | They propose an open-domain question-answering system that can retrieve answers from large corpus of COVID-19 papers. |
| Outcome: | The proposed open-domain question-answering system can retrieve answers from large corpus of COVID-19 scientific papers. |
SlackAgents: Scalable Collaboration of AI Agents in Workspaces (2025.emnlp-demos)
Copied to clipboard
Zhiwei Liu, Weiran Yao, Zuxin Liu, Juntao Tan, Jianguo Zhang, Frank Wang, Sukhandeep Nahal, Huan Wang, Shelby Heinecke, Silvio Savarese, Caiming Xiong
| Challenge: | Existing open-source frameworks like LangChain and LlamaIndex fail to integrate into daily workflows, resulting in limited daily usage for work. |
| Approach: | They propose a multi-agent library for scalable management and collaboration of AI agents on Slack. |
| Outcome: | The proposed framework offers instant AI integration into organizational workflows and facilitates scalable collaboration, allowing for effective communication and task orchestration. |
OntoGuard: Enforcing Action Admissibility for LLM Agents in Complex Interactive Environments (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to large language models (LLMs) are limited by their ability to enforce environmental and behavioral admissibility. |
| Approach: | They propose an ontological framework to guard LLM agents by enforcing environmental and behavioral admissibility. |
| Outcome: | Experiments on ScienceWorld and VirtualHome show that OntoGuard can enforce environmental and behavioral admissibility while preventing invalid actions. |
Contrastive Multi-document Question Generation (2021.eacl-main)
Copied to clipboard
Woon Sang Cho, Yizhe Zhang, Sudha Rao, Asli Celikyilmaz, Chenyan Xiong, Jianfeng Gao, Mengdi Wang, Bill Dolan
| Challenge: | Multi-document question generation focuses on generating a question that covers the common aspect of multiple documents, but a naive model trained only using the targeted document set may generate too generic questions that cover a larger scope than delineated by the document set. |
| Approach: | They propose a contrastive learning strategy where given ‘positive’ and ‘negative’ sets of documents, generate a question that is closely related to the ‘positive' set but far away from the ‘negative' set. |
| Outcome: | The proposed model significantly outperforms several strong baselines, as measured by automatic metrics and human evaluation. |
Explaining Length Bias in LLM-Based Preference Evaluations (2025.findings-emnlp)
Copied to clipboard
Zhengyu Hu, Linxin Song, Jieyu Zhang, Zheyuan Xiao, Tianfu Wang, Zhengyu Chen, Nicholas Jing Yuan, Jianxun Lian, Kaize Ding, Hui Xiong
| Challenge: | a preference evaluation metric is often biased towards longer responses, revealing a reliability problem . a decomposition of the preference evaluation into two components is needed to understand this bias. |
| Approach: | They propose to decompose the preference evaluation metric into two key components . the first component is length-dependent and related to trustworthiness . |
| Outcome: | The proposed evaluation metric is based on two components: desirability and information mass. |
TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards (2026.acl-long)
Copied to clipboard
| Challenge: | Existing approaches to training multi-turn attackers to probe model safety vulnerabilities rely on turn-level optimization, which is insufficient for learning long-term attack strategies. |
| Approach: | They propose a multi-turn reinforcement learning problem that optimizes the harmfulness of the final-turn response as the outcome reward. |
| Outcome: | The proposed approach improves attack success rates across multiple models and benchmarks, highlighting the effectiveness of the proposed approach. |
Neural Topic Modeling with Bidirectional Adversarial Training (2020.acl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that neural topic models for automatic topic extraction avoid complicated mathematical derivations for model inference. |
| Approach: | They propose a bidirectional adversarial topic model which uses a generator and an encoder to infer topic distribution. |
| Outcome: | The proposed model outperforms baselines and competitive models in three benchmark corpora. |
Nash CoT: Multi-Path Inference with Preference Equilibrium (2024.emnlp-main)
Copied to clipboard
| Challenge: | Multi-path inference is an improvement on multi-path reasoning, but there is no optimal setting for the number of inference paths. |
| Approach: | They propose to use question-related role templates to guide LLMs into relevant roles to reduce the dependence on the number of inference paths. |
| Outcome: | The proposed system can achieve comparable or better results than self-consistency with the same number of paths. |