ERROR PROPAGATION

A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing (2020.tacl-1)

Challenge:	Existing approaches to event detection ignore the trigger discrepancy and cause errors.
Approach:	They propose a unified model which converts a few-shot tagging problem into a single-shot model by using a Gaussian distribution.
Outcome:	The proposed model performs better than existing identifythen-classify models on a few-shot tagging problem with a double-part taging scheme.

Copied to clipboard

Hang Yan, Xipeng Qiu, Xuanjing Huang

KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks onWAT 2019 (D19-52)

Challenge:	Chinese word segmentation and dependency parsing suffer from error propagation . a graph-based model can integrate both tasks, but it suffers from performance limitations .
Approach:	They propose a graph-based model to integrate Chinese word segmentation and dependency parsing . their model achieves better performance than previous joint models .
Outcome:	The proposed model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing.

Copied to clipboard

Cheoneum Park, Young-Jun Jung, Kihoon Kim, Geonyeong Kim, Jae-Won Jeon, Seongmin Lee, Junseok Kim, Changki Lee

Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)

Challenge:	We submitted our transformer-based neural machine translation system to the translation tasks of the 6th workshop on Asian Translation (WAT 2019).
Approach:	They propose a transformer-based neural machine translation system for Chinese-Japanese, English-Japanese, and Korean->Japanoise translation tasks.
Outcome:	The proposed system performed well on the two translation tasks and was ranked first in terms of the BLEU scores in all the JPC2 subtasks.

Copied to clipboard

Peixin Huang, Xiang Zhao, Minghao Hu, Yang Fang, Xinyi Li, Weidong Xiao

Named Entity Recognition

Challenge:	Existing studies treat named entity recognition as a sequential labeling problem.
Approach:	They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted .
Outcome:	The proposed framework outperforms competing models on four benchmark datasets.

Equipping Language Models with Tool Use Capability for Tabular Data Analysis in Finance (2024.eacl-short)

Copied to clipboard

Adrian Theuma, Ehsan Shareghi

Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLP (2020.findings-emnlp)

Challenge:	Large language models (LLMs) have an array of reasoning capabilities but face limitations such as error propagation and hallucination.
Approach:	They propose to use a LLAMA-2 13B CHAT model to act as a task router and task solver to offload certain reasoning steps to external tools that are more suited for the task.
Outcome:	The proposed model improves by 35.2% and 5.06% over baseline models and strong GPT-3.5 results.

Copied to clipboard

Hao Fei, Yafeng Ren, Donghong Ji

Non-Parametric Domain Adaptation for End-to-End Speech Translation (2022.emnlp-main)

Challenge:	Existing work on integrating syntactic information into neural networks uses a single tree, such as a constituency or a dependency tree.
Approach:	They propose a method to integrate heterogeneous structure knowledge into a unified sequential LSTM encoder.
Outcome:	The proposed method outperforms tree encoders on four syntax-dependent tasks and is efficient and accurate.

Copied to clipboard

Yichao Du, Weizhi Wang, Zhirui Zhang, Boxing Chen, Tong Xu, Jun Xie, Enhong Chen

Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks (2020.coling-main)

Challenge:	End-to-end speech translation (E2E-ST) systems have received increasing attention due to its less error propagation, lower latency and fewer parameters.
Approach:	They propose a non-parametric method that leverages in-domain text translation corpus to achieve domain adaptation for E2E-ST systems.
Outcome:	The proposed method outperforms the existing in-domain fine-tuning strategies on the Europarl-ST benchmark.

Copied to clipboard

Guimin Chen, Yuanhe Tian, Yan Song

Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction (D19-1)

Challenge:	End-to-end aspect-based sentiment analysis uses two sub-tasks to extract aspect terms . experimental results demonstrate the effectiveness of our approach on all datasets .
Approach:	They propose to combine aspect extraction and sentiment analysis with encoding syntactic information to improve model's representation of input sentences.
Outcome:	The proposed approach achieves state-of-the-art on three benchmark datasets.

Copied to clipboard

Rujun Han, Qiang Ning, Nanyun Peng

Event Extraction by Answering (Almost) Natural Questions (2020.emnlp-main)

Challenge:	Existing systems treat this task as a pipeline of two separate subtasks, i.e., event extraction and temporal relation classification.
Approach:	They propose a joint event and temporal relation extraction model with shared representation learning and structured prediction.
Outcome:	The proposed method improves both event extraction and temporal relation extraction over state-of-the-art systems.

Copied to clipboard

Xinya Du, Claire Cardie

Dependency Parsing with Backtracking using Deep Reinforcement Learning (2022.tacl-1)

Challenge:	Existing work in event argument extraction relies heavily on entity recognition as a preprocessing/concurrent step, causing error propagation.
Approach:	They propose a question answering task that extracts event arguments in an end-to-end manner.
Outcome:	The proposed framework outperforms prior work on the ACE 2005 task on event argument extraction.

Copied to clipboard

Franck Dary, Maxime Petit, Alexis Nasr

OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning (2024.findings-naacl)

Challenge:	Greedy algorithms for NLP such as transition-based parsing are prone to error propagation.
Approach:	They propose to allow transition-based parsing to backtrack in cases where evidence contradicts the current solution.
Outcome:	The proposed behavior can be implemented on POS tagging and dependency parsing . it shows that backtracking is an effective means to fight error propagation .

Copied to clipboard

Fei Yu, Anningzhe Gao, Benyou Wang

Correctable-DST: Mitigating Historical Context Mismatch between Training and Inference for Improved Dialogue State Tracking (2022.emnlp-main)

Challenge:	Large language models (LLMs) struggle with maintaining accuracy throughout multiple reasoning steps, especially in mathematical reasoning where an error in earlier steps can propagate to subsequent ones and ultimately leading to an incorrect answer.
Approach:	They propose an Outcome-supervised Value Model (OVM) that employs outcome supervision for training a value model, which prioritizes steps that lead to accurate conclusions.
Outcome:	The proposed model performs better on two multi-step reasoning datasets, GSM8K and Game of 24.

Copied to clipboard

Hongyan Xie, Haoxiang Su, Shuangyong Song, Hao Huang, Bo Zou, Kun Deng, Jianghua Lin, Zhihui Zhang, Xiaodong He

Dialogue Systems & Conversational Agents

Challenge:	Existing dialogue state tracking approaches predict the dialogue state of a target turn sequentially based on the ground-truth previous dialogue state.
Approach:	They propose a method that predicts dialogue state sequentially based on previous dialogue state . they propose generating a previously “predicted” dialogue state using ground-truth previous dialogue states .
Outcome:	The proposed method achieves 67.51%, 68.24%, 70.30%, 71.38%, and 81.27% joint goal accuracy on MultiWOZ 2.0-2.4 datasets.

NAG-NER: a Unified Non-Autoregressive Generation Framework for Various NER Tasks (2023.acl-industry)

Copied to clipboard

Xinpeng Zhang, Ming Tan, Jingfan Zhang, Wei Zhu

Neural Open Information Extraction (P18-2)

Challenge:	Existing models for general NER tasks require entities to be generated in a predefined order, causing error propagation and inefficient decoding.
Approach:	They propose a non-autoregressive generation framework for general NER tasks that generates entities as a set instead of a sequence, avoiding error propagation and inefficient decoding.
Outcome:	The proposed model outperforms state-of-the-art models on three benchmark NER datasets and two of our proprietary NER tasks.

Copied to clipboard

Lei Cui, Furu Wei, Ming Zhou

Template Filling with Generative Transformers (2021.naacl-main)

Challenge:	Existing Open IE systems are built on hand-crafted patterns from syntactic parsing, yet they face errors in propagation and compounding at each stage.
Approach:	They propose a neural Open IE approach with an encoder-decoder framework . they propose to learn highly confident arguments and relation tuples bootstrapped from a state-of-the-art Open ie system.
Outcome:	The proposed approach outperforms baseline methods while maintaining comparable computational efficiency.

Copied to clipboard

Xinya Du, Alexander Rush, Claire Cardie

Meta Self-Refinement for Robust Learning with Weak Supervision (2023.eacl-main)

Challenge:	Template filling tasks are usually tackled by a pipeline of two separate systems, one for role-filler extraction and another for template/event recognition.
Approach:	They propose a framework that naturally models the dependence between entities within a single event and across multiple events described in a document.
Outcome:	The proposed framework outperforms pipeline-based approaches and other neural baselines that do not model between-event dependencies on documents containing multiple events.

Copied to clipboard

Dawei Zhu, Xiaoyu Shen, Michael Hedderich, Dietrich Klakow

Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach (2021.naacl-main)

Challenge:	Recent methods leverage self-training to build noise-resistant models . however, the teacher trained under weak supervision may have fitted a substantial amount of noise and therefore produce incorrect pseudo-labels.
Approach:	They propose a framework that encourages teacher to refine its pseudo-labels to effectively combat label noise from weak supervision.
Outcome:	The proposed framework outperforms state-of-the-art methods by 11.4% in accuracy and 9.26% in F1 score on eight NLP benchmarks.

Copied to clipboard

Yue Yu, Simiao Zuo, Haoming Jiang, Wendi Ren, Tuo Zhao, Chao Zhang

A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation (2024.acl-long)

Challenge:	Fine-tuned pre-trained language models (LMs) have enormous success in many natural language processing tasks, but they still require excessive labeled data in the fine-tuning stage.
Approach:	They propose a framework to enable fine-tuning pre-trained language models with weak supervision without any labeled data.
Outcome:	The proposed framework outperforms the strongest baseline and achieves competitive performance with fully-supervised fine-tuning methods.

Copied to clipboard

Zhengrui Ma, Qingkai Fang, Shaolei Zhang, Shoutao Guo, Yang Feng, Min Zhang

Towards Robust Real-World Spreadsheet Understanding with Multi-Agent Multi-Format Reasoning (2026.acl-long)

Challenge:	Existing translation pipelines require additional cascade components to achieve speech-to-speech translation.
Approach:	They propose a non-autoregressive generation framework for simultaneous speech translation . it integrates both text-to-text and speech-tospeech tasks into a unified framework .
Outcome:	The proposed framework outperforms state-of-the-art models in speech-to-text and speech- to-speech tasks.

Copied to clipboard

Houxing Ren, Mingjie Zhan, Zimu Lu, Ke Wang, Yunqiao Yang, Haotian Hou, Hongsheng Li

Robustness in NLP

Challenge:	Spreadsheets are among the most widely used data formats in real-world applications . existing large language models treat tables as plain text, overlooking layout cues and visual semantics.
Approach:	They propose a two-stage multi-agent framework for spreadsheet understanding that adopts a step-by-step reading and reasoning paradigm.
Outcome:	Extensive experiments on two spreadsheet datasets show the proposed framework outperforms existing methods on Spreadsheet Bench.

Generative Multi-hop Retrieval (2022.emnlp-main)

Copied to clipboard

Hyunji Lee, Sohee Yang, Hanseok Oh, Minjoon Seo

Non-Projective Dependency Parsing with Non-Local Transitions (N18-2)

Challenge:	A bi-encoder approach to text retrieval has limitations in multi-hop settings; the reformulated query gets longer as the number of hops increases, which further tightens the embedding bottleneck of the query vector.
Approach:	They propose an encoder-decoder model that performs multi-hop retrieval by simply generating the entire text sequences of the retrieval targets.
Outcome:	The proposed model achieves comparable or higher performance than bi-encoder models in five datasets while demonstrating superior GPU memory and storage footprint.

Copied to clipboard

Daniel Fernández-González, Carlos Gómez-Rodríguez

Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations (N19-1)

Challenge:	Existing greedy transition-based parsers are prone to error propagation when creating arcs involving multiple transitions.
Approach:	They propose a greedy transition-based parser that introduces non-local transitions that create arcs involving nodes to the left of the current focus positions.
Outcome:	The proposed system outperforms the original version and achieves the best accuracy on the Stanford Dependencies conversion of the Penn Treebank among greedy transition-based parsers.

Copied to clipboard

Meishan Zhang, Zhenghua Li, Guohong Fu, Min Zhang

Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction (2021.findings-acl)

Challenge:	Syntax integration has been demonstrated highly effective in neural machine translation (NMT).
Approach:	They propose a method to integrate source-side syntax implicitly for neural machine translation . they use hidden representations of a well-trained end-to-end dependency parser to concatenate them with ordinary word embeddings to enhance basic NMT models.
Outcome:	The proposed method outperforms existing methods on two translation tasks . it can be easily integrated into the widely-used sequence-to-sequence (Seq2Sequen) framework .

Copied to clipboard

Zhexue Chen, Hong Huang, Bang Liu, Xuanhua Shi, Hai Jin

PriMeSRL-Eval: A Practical Quality Metric for Semantic Role Labeling Systems Evaluation (2023.findings-eacl)

Challenge:	Existing approaches to extract triplets from sentences neglect the mutual information between aspects and have the problem of error propagation.
Approach:	They propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model to exploit the syntactical and semantic relationships between the triplet elements and jointly extract them.
Outcome:	The proposed model outperforms existing methods on four benchmark datasets and significantly outperformed existing approaches.

Copied to clipboard

Ishan Jindal, Alexandre Rademaker, Khoi-Nguyen Tran, Huaiyu Zhu, Hiroshi Kanayama, Marina Danilevsky, Yunyao Li

BiSPN: Generating Entity Set and Relation Set Coherently in One Pass (2023.findings-emnlp)

Challenge:	Existing evaluation scripts for semantic role labeling do not consider error propagation . existing evaluation script does not consider argument independent of predicate sense .
Approach:	They propose a more strict SRL evaluation metric PriMeSRL to address these issues . they propose to use a metric that measures the quality of the underlying SRL models .
Outcome:	The proposed metric reduces quality evaluation of all SoTA SRL models and penalizes failures.

Copied to clipboard

Yuxin He, Buzhou Tang

Towards End-to-End Open Conversational Machine Reading (2023.findings-eacl)

Challenge:	Existing approaches to extract entities and relation triples from text are limited.
Approach:	They propose a bipartite set prediction network to generate entity set and relation set in parallel.
Outcome:	The proposed model can generate entity set and relation set in parallel, while maintaining coherence between the predicted entities and relation sets.

Copied to clipboard

Sizhe Zhou, Siru Ouyang, Zhuosheng Zhang, Hai Zhao

Natural Language Interfaces

Challenge:	Existing approaches to the problem of open-retrieval conversational machine reading (OR-CMR) use two separate modules to approach the problem's two successive sub-tasks.
Approach:	They propose to model OR-CMR as a unified text-to-text task in a fully end-to end style and propose to use a text-based approach to solve the problem.
Outcome:	Experiments on the ShARC and OR-ShARC dataset show that the proposed framework can generalize to different backbone models.

How Does Response Length Affect Long-Form Factuality (2025.findings-acl)

Copied to clipboard

James Xu Zhao, Jimmy Z.j. Liu, Bryan Hooi, See-Kiong Ng

Challenge:	Despite growing attention to LLM factuality, the effect of response length on factual accuracy remains underexplored.
Approach:	They propose an automatic and bi-level long-form factuality evaluation framework which achieves high agreement with human annotations while being cost-effective.
Outcome:	The proposed framework achieves high agreement with human annotations while being cost-effective.

Japanese Zero Anaphora Resolution Can Benefit from Parallel Texts Through Neural Transfer Learning (2021.findings-emnlp)

Copied to clipboard

Masato Umakoshi, Yugo Murawaki, Sadao Kurohashi

End-to-End Chinese Speaker Identification (2022.naacl-main)

Challenge:	Using a pretraining model, we find that the performance of Japanese zero anaphora resolution (ZAR) is improved by using machine translation.
Approach:	They propose to inject machine translation as an intermediate task between pretraining and ZAR by injecting machine translation into a pretrained BERT model and injecting it into MT.
Outcome:	The proposed framework shows that Japanese zero anaphora resolution (ZAR) can be improved by transfer learning from machine translation (MT).

Copied to clipboard

Dian Yu, Ben Zhou, Dong Yu

BORT: Back and Denoising Reconstruction for End-to-End Task-Oriented Dialog (2022.findings-naacl)

Challenge:	Existing methods for speaker identification in texts are incomplete and introduce errors that propagate and seriously affect the final output.
Approach:	They propose to use speaker identification (SI) in texts to identify the speaker(s) for each utterance in texts.
Outcome:	The proposed model can achieve comparable or better than previous state-of-the-art methods on all public SI datasets for Chinese.

Copied to clipboard

Haipeng Sun, Junwei Bao, Youzheng Wu, Xiaodong He

Dialogue Systems & Conversational Agents

Challenge:	Existing task-oriented dialog systems suffer from error propagation from inaccurate dialog states and responses.
Approach:	They propose a back reconstruction approach for end-to-end task-oriented dialog system . they use back reconstruction to reconstruct the original input context from the generated dialog states .
Outcome:	Extensive experiments on MultiWOZ 2.0 and CamRest676 show the effectiveness of the proposed model.

Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning (2025.naacl-long)

Copied to clipboard

Junzhi Chen, Juhao Liang, Benyou Wang

OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extraction (2022.coling-1)

Challenge:	Teaching large language models to use tools for solving complex problems can grant them human-like reasoning abilities.
Approach:	They propose a multi-agent system that enhances the Deep First Search Decision Tree (DFSDT) to address issues like error propagation and limited exploration in ReAct .
Outcome:	The proposed system reduces token usage by 60.9% compared to existing methods and performs on par with GPT-4-DFSDT.

Copied to clipboard

Hu Cao, Jingye Li, Fangfang Su, Fei Li, Hao Fei, Shengqiong Wu, Bobo Li, Liang Zhao, Donghong Ji

Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning (2020.emnlp-main)

Challenge:	Event extraction (EE) is an essential task of information extraction, which aims to extract structured event information from unstructured text.
Approach:	They propose a tagging scheme and a model to form EE as word-word relation recognition using parallel grid tapping.
Outcome:	The proposed model achieves state-of-the-art on 3 overlapped and nested EE benchmarks and faster than baselines.

Copied to clipboard

Tsvetomila Mihaylova, Vlad Niculae, André F. T. Martins

Uncertainty-Aware Label Refinement for Sequence Labeling (2020.emnlp-main)

Challenge:	Latent structure models can mitigate the error propagation and annotation bottleneck in pipeline systems, while uncovering linguistic insights about the data.
Approach:	They propose a latent structure model with a pullback of the downstream learning objective.
Outcome:	The proposed model outperforms the known and proposed model in the same family and yields new insights for practitioners and revealing intriguing failure cases.

Copied to clipboard

Tao Gui, Jiacheng Ye, Qi Zhang, Zhengyan Li, Zichu Fei, Yeyun Gong, Xuanjing Huang

Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER (2022.acl-long)

Challenge:	Conditional random fields (CRF) for label decoding have been a problem for many tasks.
Approach:	They propose a two-stage label decoding framework that model long-term label dependencies while being much more computationally efficient.
Outcome:	The proposed method outperforms the CRF-based methods and greatly accelerates the inference process.

Copied to clipboard

Dong-Ho Lee, Akshen Kadakia, Kangmin Tan, Mahak Agarwal, Xinyu Feng, Takashi Shibuya, Ryosuke Mitani, Toshiyuki Sekiya, Jay Pujara, Xiang Ren

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training (2026.acl-long)

Challenge:	Recent advances in prompt-based learning have shown strong results on few-shot text classification by using cloze-style templates.
Approach:	They propose a demonstration-based learning method which lets the input be prefaced by task demonstrations for in-context learning.
Outcome:	The proposed method improves on in-domain learning and domain adaptation in low-resource settings.

Copied to clipboard

Yifan Yang, Bing Han, Hui Wang, Wei Wang, Ziyang Ma, Long Zhou, Zengrui Jin, Guanrou Yang, Tianrui Wang, Xu Tan, Xie Chen

How Time Matters: Learning Time-Decay Attention for Contextual Spoken Language Understanding in Dialogues (N18-1)

Challenge:	Existing models for fine-grained speaking styles are limited in terms of accuracy, coverage, and naturalness.
Approach:	They propose a model that pre-trains with coarse captions and annotates with a pipeline that grounds captions in audio.
Outcome:	The proposed model outperforms existing models with fine-grained style annotations . it integrates global and fine-granular supervision, enabling unified representations based on the proposed model .

Copied to clipboard

Shang-Yu Su, Pei-Chieh Yuan, Yun-Nung Chen

Natural Language Interfaces

Challenge:	Spoken language understanding (SLU) is an essential component in conversational systems.
Approach:	They propose a universal time-decay attention mechanism that can be used to decay utterances on the sentence-level and speaker-level.
Outcome:	The proposed model significantly improves the state-of-the-art model for contextual understanding performance on the benchmark Dialogue State Tracking Challenge (DSTC4) dataset.

Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation (2021.emnlp-main)

Copied to clipboard

Xin Tan, Longyin Zhang, Guodong Zhou

SetGNER: General Named Entity Recognition as Entity Set Generation (2022.emnlp-main)

Challenge:	ZP-annotated natural language generation (NLG) corpora are scarce in pro-drop languages . despite efforts to bridge the discrepancy between human and machine, zero pronouns still persist in pro -drop tasks.
Approach:	They propose a highly adaptive two-stage approach to couple context modeling with ZP recovering to mitigate the ZP problem in NLG tasks.
Outcome:	The proposed approach can improve translation, question answering, and summarization tasks.

Copied to clipboard

Yuxin He, Buzhou Tang

ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QA (2025.emnlp-main)

Challenge:	Named entity recognition (NER) is a fundamental task in the field of information extraction and has played an important role in the development of natural language processing.
Approach:	They propose a method that treats each entity as a sequence and is capable of recognizing discontinuous mentions.
Outcome:	The proposed model outperforms state-of-the-art generative NER models on two discontinuous NER datasets, two nested NER and one flat NER.

Copied to clipboard

Zhao Xinjie, Fan Gao, Xingyu Song, Yingjian Chen, Rui Yang, Yanran Fu, Yuyang Wang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li

A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding (D19-1)

Challenge:	Multi-hop question answering (QA) is a central challenge in natural language processing . early mistakes can cause errors and undermine the final result, authors say .
Approach:	They propose a reversible multi-agent reasoning framework that backtracks to earlier valid states when conflicts arise.
Outcome:	Empirical evaluation shows that the framework improves on forward-only benchmarks by 6% . the approach enables agents to backtrack to valid states when conflicts arise .

Copied to clipboard

Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, Ting Liu

Aspect-based Sentiment Analysis as Machine Reading Comprehension (2022.coling-1)

Challenge:	Intent detection and slot filling are two main tasks for building a spoken language understanding system.
Approach:	They propose a framework to incorporate intent information into slot filling tasks . they use a joint model with Stack-Propagation to capture intent semantic knowledge .
Outcome:	The proposed model outperforms existing models on two publicly available datasets and outperformed existing models by a large margin.

Copied to clipboard

Yifei Yang, Hai Zhao

End-to-End Reinforcement Learning for Automatic Taxonomy Induction (P18-1)

Challenge:	Existing approaches to aspect-based sentiment analysis stack multiple modules and result in severe error propagation.
Approach:	They propose a MRC-PrOmpt mOdeL framework where multiple sentiment aspects are elicited by a machine reading comprehension model and their corresponding sentiment polarities are classified in a prompt learning way.
Outcome:	The proposed framework significantly outperforms existing state-of-the-art models or achieves comparable performance on widely-used benchmark datasets.

Copied to clipboard

Yuning Mao, Xiang Ren, Jiaming Shen, Xiaotao Gu, Jiawei Han

Challenge:	Existing methods for automating taxonomy induction often divide the problem into two subtasks . a novel end-to-end reinforcement learning approach is proposed to improve the accuracy of such methods.
Approach:	They propose an end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms.
Outcome:	The proposed approach outperforms state-of-the-art methods on two public datasets of different domains.

Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction (2020.findings-emnlp)

Copied to clipboard

Zhen Wu, Chengcan Ying, Fei Zhao, Zhifang Fan, Xinyu Dai, Rui Xia

PILOT: Planning via Internalized Latent Optimization Trajectories for Large Language Models (2026.acl-long)

Challenge:	Aspect-oriented Fine-grained Opinion Extraction (AFOE) aims to extract aspect terms and opinion terms from review text in the form of opinion pairs or opinion triplets.
Approach:	They propose a grid-based AFOE tagging scheme to address the task in an end-to-end fashion only with one unified grid tracking task.
Outcome:	The proposed tagging scheme outperforms baselines and achieves state-of-the-art performance.

Copied to clipboard

Haoyu Zheng, Yun Zhu, Yuqian Yuan, Bo Yuan, Wenqiao Zhang, Siliang Tang, Jun Xiao

Multi-Task Learning for Conversational Question Answering over a Large-Scale Knowledge Base (D19-1)

Challenge:	Large Language Models lack the capacity to formulate global strategies due to latency and availability constraints.
Approach:	They propose a framework to internalize the strategic oversight of large models into intrinsic Latent Guidance by synthesizing a query-conditioned Latent Guide.
Outcome:	The proposed framework outperforms strong baselines on mathematical and coding benchmarks with negligible inference latency.

Copied to clipboard

Tao Shen, Xiubo Geng, Tao Qin, Daya Guo, Duyu Tang, Nan Duan, Guodong Long, Daxin Jiang

Low-Resource Comparative Opinion Quintuple Extraction by Data Augmentation with Prompting (2023.findings-emnlp)

Challenge:	Recent approaches to handle large knowledge base decompose tasks into subtasks and solve them sequentially.
Approach:	They propose a multi-task learning framework that resolves coreference in conversations . they propose enabling shared supervisions and type-aware entity detection model .
Outcome:	The proposed framework improves overall F1 score from 67% to 79% on a large-scale conversational question answering dataset.

Copied to clipboard

Qingting Xu, Yu Hong, Fubang Zhao, Kaisong Song, Yangyang Kang, Jiaxiang Chen, Guodong Zhou

MetaTS: Meta Teacher-Student Network for Multilingual Sequence Labeling with Minimal Supervision (2021.emnlp-main)

Challenge:	Comparative Opinion Quintuple Extraction (COQE) aims to predict comparative opinion quintuples from comparative sentences.
Approach:	They propose a low-resource approach to extract comparative opinion quintuples from comparative sentences . they propose augmentation using ChatGPT and a data-centric approach .
Outcome:	The proposed approach improves the existing pipeline-based method and achieves state-of-the-art results.

Copied to clipboard

Zheng Li, Danqing Zhang, Tianyu Cao, Ying Wei, Yiwei Song, Bing Yin

URG: A Unified Ranking and Generation Method for Ensembling Language Models (2024.findings-acl)

Challenge:	Sequence labeling aims to predict fine-grained sequences of labels for text, but lack of token-level annotated data hinders the effectiveness of supervised methods.
Approach:	They propose a Meta Teacher-Student (MetaTS) Network to alleviate data scarcity by leveraging large multilingual unlabeled data.
Outcome:	The proposed meta learning method alleviates data scarcity by leveraging large multilingual unlabeled data.

Copied to clipboard

Bo Lv, Chen Tang, Yanan Zhang, Xin Liu, Ping Luo, Yue Yu

Original Semantics-Oriented Attention and Deep Fusion Network for Sentence Matching (D19-1)

Challenge:	Existing approaches to rank and generate large language models have limited performance due to time-intensive nature of ranking process and lack of error propagation.
Approach:	They propose a framework that jointly ranks the outputs of Large Language Models and generates fine-grained fusion results.
Outcome:	The proposed framework achieves state-of-the-art (SOTA) performance on ranking and generation tasks.

Copied to clipboard

Mingtong Liu, Yujie Zhang, Jinan Xu, Yufeng Chen

Challenge:	Sentence matching is a key issue in natural language inference and paraphrase identification.
Approach:	They propose a semantics-oriented attention and deep fusion network (OSOA-DFN) that is oriented to the original semantic representation of another sentence and propagates attention information at each matching layer.
Outcome:	The proposed model can model sentence matching more precisely on three sentence matching benchmark datasets.

Comprehensive Multi-Modal Interactions for Referring Image Segmentation (2022.findings-acl)

Copied to clipboard

Kanishk Jain, Vineet Gandhi

Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning (2021.findings-acl)

Challenge:	Existing methods for RIS compute different forms of interactions sequentially or ignore intra-modal interactions.
Approach:	They propose a method which outputs a segmentation map corresponding to the natural language description.
Outcome:	The proposed method performs on four benchmark datasets and shows significant performance gains over the existing state-of-the-art methods.

Copied to clipboard

Fubang Zhao, Zhuoren Jiang, Yangyang Kang, Changlong Sun, Xiaozhong Liu

ATRI: Mitigating Multilingual Audio Text Retrieval Inconsistencies by Reducing Data Distribution Errors (2025.acl-long)

Challenge:	Existing models for relational fact extraction do not analyze the output data structure from the perspective of graph representation flexibility and heterogeneity.
Approach:	They propose a relational fact extraction model based on graph-oriented analytical perspective that outperforms other models.
Outcome:	The proposed model outperforms state-of-the-art models on two benchmark datasets and shows that it is flexible and space-efficient.

Copied to clipboard

Yuguo Yin, Yuxin Xie, Wenyuan Yang, Dongchao Yang, Jinghan Ru, Xianwei Zhuang, Liming Liang, Yuexian Zou

Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings (2020.coling-main)

Challenge:	Existing multilingual audio-text retrieval schemes suffer from inconsistencies for instance similarity matching across languages.
Approach:	They propose a multilingual audio-text retrieval scheme that mitigates the impact of data distribution error on recall and consistency.
Outcome:	The proposed scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English.

Copied to clipboard

Yutao Zeng, Xiaolong Jin, Saiping Guan, Jiafeng Guo, Xueqi Cheng

Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing - A Tale of Two Parsers Revisited (D19-1)

Challenge:	Existing methods for event coreference resolution do not identify paraphrase relations between events.
Approach:	They propose a new event-specific paraphrase and argument-aware semantic Embedding model for event coreference resolution based on event-related paraphrases and argument embeddings . EPASE recognizes deep paraphrase relations in an event- specific context of sentences and can cover event paraphrase of more situations .
Outcome:	Experiments on within- and cross-document event coreference show it is superior compared to existing methods.

Copied to clipboard

Artur Kulmizev, Miryam de Lhoneux, Johannes Gontrum, Elena Fano, Joakim Nivre

Representation Learning

Challenge:	In recent years, dependency parsing has shifted from discrete features to neural networks and continuous representations.
Approach:	They propose to use deep contextualized word embeddings to pack information about global sentence structure into local feature representations to make the two approaches virtually equivalent in terms of accuracy and error profile.
Outcome:	The proposed model improves the accuracy and error profile of transition-based and graph-based dependency parsers on 13 languages.

SEAG: Structure-Aware Event Causality Generation (2023.findings-acl)

Copied to clipboard

Zhengwei Tao, Zhi Jin, Xiaoying Bai, Haiyan Zhao, Chengfeng Dou, Yongqiang Zhao, Fang Wang, Chongyang Tao

Structured Data in NLP

Challenge:	Current methods for extracting event causality are limited by the lack of cross-task dependencies and may cause error propagation.
Approach:	They propose an approach for Structure-Aware Event Causality Generation (SEAG) they generate the ECG structure using a pre-trained language model and perform structural discriminative training alongside auto-regressive generation.
Outcome:	The proposed method is effective in extracting event causality from text.

PCAD: Towards ASR-Robust Spoken Language Understanding via Prototype Calibration and Asymmetric Decoupling (2024.acl-long)

Copied to clipboard

Xianwei Zhuang, Xuxin Cheng, Liming Liang, Yuxin Xie, Zhichang Wang, Zhiqi Huang, Yuexian Zou

Robustness in NLP

Challenge:	Spoken language understanding (SLU) suffers from error propagation from automatic speech recognition (ASR) in actual scenarios.
Approach:	They propose a framework which calibrates bias and errors and achieves adaptive-balanced decoupling training by a prototype-based loss model.
Outcome:	The proposed framework outperforms existing approaches and achieves state-of-the-art performance on three datasets.

Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction (2020.acl-main)

Copied to clipboard

Penghui Wei, Jiahao Zhao, Wenji Mao

Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification (2021.emnlp-main)

Challenge:	Emotion-cause pair extraction aims to extract all emotion clauses coupled with their cause clauses from a given document.
Approach:	They propose a one-step neural approach which emphasizes inter-clause modeling to perform end-to-end extraction.
Outcome:	The proposed method outperforms existing methods in the extraction of emotion-cause pairs . it emphasizes inter-clause modeling to perform end-to-end extraction .

Copied to clipboard

Zhiwei Zhang, Jiyi Li, Fumiyo Fukumoto, Yanming Ye

Syntax-Aware Opinion Role Labeling with Dependency Graph Convolutional Networks (2020.acl-main)

Challenge:	Existing scientific claim verification models have problems of error propagation among modules and lack of sharing valuable information among modules.
Approach:	They propose an approach that jointly learns the modules for the three tasks with a machine reading comprehension framework by including claim information.
Outcome:	The proposed approach outperforms existing models on the SciFact dataset on the three tasks of abstract retrieval, rationale selection and stance prediction.

Copied to clipboard

Bo Zhang, Yue Zhang, Rui Wang, Zhenghua Li, Min Zhang

Does Joint Training Really Help Cascaded Speech Translation? (2022.emnlp-main)

Challenge:	Opinion role labeling (ORL) is a fine-grained opinion analysis task . due to the scarcity of labeled data, ORL remains challenging for data-driven methods due to its complexity and complexity.
Approach:	They propose to integrate syntactic knowledge into ORL models by comparing and integrating different representations and using dependency graph convolutional networks to encode parser information at different processing levels.
Outcome:	The proposed model achieves 4.34 higher F1 score than the current state-of-the-art.

Copied to clipboard

Viet Anh Khoa Tran, David Thulke, Yingbo Gao, Christian Herold, Hermann Ney

NCLS: Neural Cross-Lingual Summarization (D19-1)

Challenge:	Currently, in speech translation, the straightforward approach delivers state-of-the-art results, but fundamental challenges such as error propagation remain.
Approach:	They propose to combine a cascaded recognition system with a machine translation system to improve cascade speech translation.
Outcome:	The proposed methods can improve cascaded speech translation and suggest alternative training methods.

Copied to clipboard

Junnan Zhu, Qian Wang, Yining Wang, Yu Zhou, Jiajun Zhang, Shaonan Wang, Chengqing Zong

Compositional Reasoning via Joint Image and Language Decomposition (2026.findings-eacl)

Challenge:	Existing approaches to cross-lingual summarization divide the task into two steps: summarizing and translation.
Approach:	They propose to integrate two related tasks into the training process of CLS under multi-task learning to improve cross-lingual summarization.
Outcome:	The proposed framework improves on English-to-Chinese and Chinese-to English CLS human-corrected test sets.

Copied to clipboard

Dwip Dalal, Madhav Kanda, Zhenhailong Wang, Heng Ji, Unnat Jain

Seeking Common but Distinguishing Difference, A Joint Aspect-based Sentiment Analysis Model (2021.emnlp-main)

Challenge:	Existing approaches typically decompose only language queries, treating images as monolithic inputs.
Approach:	They propose a framework that decomposes both images and questions into visual sub-domains with corresponding sub-questions.
Outcome:	REDI achieves absolute accuracy improvements of 8.9%, 8.2%, and 16.0% over existing models.

Copied to clipboard

Hongjiang Jing, Zuchao Li, Hai Zhao, Shu Jiang

Complex Event Schema Induction with Knowledge-Enriched Diffusion Model (2023.findings-emnlp)

Challenge:	Existing models focus on aspect term extraction, opinion term extraction and sentiment polarity classification but ignore the difference.
Approach:	They propose a joint aspect-based sentiment analysis task that focuses on the difference between the two tasks to improve the model's robustness.
Outcome:	Empirical results show that the proposed model outperforms the previous state-of-the-art on four benchmark datasets.

Copied to clipboard

Yupu Hao, Pengfei Cao, Yubo Chen, Kang Liu, Jiexin Xu, Huaijun Li, Xiaojian Jiang, Jun Zhao

Challenge:	Existing studies on event schema induction have been hindered by errors and data quality issues.
Approach:	They propose a knowledge-enriched discrete diffusion model that distills event scenario knowledge from LLMs.
Outcome:	The proposed model achieves outstanding performance across evaluation metrics.

End-to-End AMR Coreference Resolution (2021.acl-long)

Copied to clipboard

Qiankun Fu, Linfeng Song, Wenyu Du, Yue Zhang

Joint Extraction of Entities, Relations, and Events via Modeling Inter-Instance and Inter-Label Dependencies (2022.naacl-main)

Challenge:	Existing work on AMR focuses on individual sentences, but there is a need for multi-sentence AMRs.
Approach:	They propose to use an end-to-end AMR coreference resolution model to generate multi-sentence AMRs.
Outcome:	The proposed model reduces error propagation and is more robust for both in- and out-domain situations.

Copied to clipboard

Minh Van Nguyen, Bonan Min, Franck Dernoncourt, Thien Nguyen

Translatotron-V(ison): An End-to-End Model for In-Image Machine Translation (2024.findings-acl)

Challenge:	Existing models that perform information extraction tasks manually assume heuristic dependency between the task instances and mean-field factorization for the joint distribution of instance labels.
Approach:	They propose to induce a dependency graph among task instances to boost representation learning by estimating their joint distribution via Conditional Random Fields.
Outcome:	The proposed model outperforms previous models on multiple IE tasks across 5 datasets and 2 languages.

Copied to clipboard

Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou, Min Zhang, Jinsong Su

Improving the Robustness of Distantly-Supervised Named Entity Recognition via Uncertainty-Aware Teacher Learning and Student-Student Collaborative Learning (2024.findings-acl)

Challenge:	In-image machine translation (IIMT) aims to translate an image containing texts in source language into an image with translations in target language.
Approach:	They propose an end-to-end IIMT model with four modules that translate images . they propose a two-stage training framework to assist the model in learning alignment across languages .
Outcome:	The proposed model outperforms cascaded models with only 70.9% of parameters and is highly accurate.

Copied to clipboard

Shuzheng Si, Helan Hu, Haozhe Zhao, Shuang Zeng, Kaikai An, Zefan Cai, Baobao Chang

Robustness in NLP

Challenge:	Named Entity Recognition (NER) methods require a substantial quantity of high-quality annotation for training models.
Approach:	They propose a method to reduce the number of incorrect pseudo labels in self-training . they propose 'uncertainty-aware teacher learning' and 'student-student collaboration'
Outcome:	The proposed method is superior to state-of-the-art DS-NER denoising methods.

SG-FSM: A Self-Guiding Zero-Shot Prompting Paradigm for Multi-Hop Question Answering Based on Finite State Machine (2025.findings-naacl)

Copied to clipboard

Xiaochen Wang, Junqing He, Liang Chen, Gholamreza Haffari, Yiru Wang, Zhe Yang, Xiangdi Meng, Kunhao Pan, Zhifang Sui

An Interpretable Neuro-Symbolic Reasoning Framework for Task-Oriented Dialogue Generation (2022.acl-long)

Challenge:	Multi-hop Question Answering (MHQA) is a challenging task that requires models to answer multiple questions with multiple passages.
Approach:	They propose a self-guided prompting finite state machine to improve multi-hop reasoning abilities by iterating over multiple questions and correcting itself to improve accuracy.
Outcome:	The proposed approach outperforms baselines on Musique and other datasets.

Copied to clipboard

Shiquan Yang, Rui Zhang, Sarah Erfani, Jey Han Lau

Dialogue Systems & Conversational Agents

Challenge:	Existing approaches to interpret task-oriented dialogue systems employ an implicit reasoning strategy that makes the model predictions uninterpretable to humans.
Approach:	They propose a neuro-symbolic approach that performs explicit reasoning that justifies model decisions by reasoning chains.
Outcome:	The proposed approach achieves better results and introduces an interpretable decision process.

Better, Faster, Stronger Sequence Tagging Constituent Parsers (N19-1)

Copied to clipboard

David Vilares, Mostafa Abdou, Anders Søgaard

Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet Extraction (2025.findings-emnlp)

Challenge:	Existing efforts to speed up constituent parsing have focused on chart-based or shift-reduce parsers.
Approach:	They propose to use auxiliary losses and sentence-level fine-tuning to mitigate greedy decoding issues.
Outcome:	The proposed model surpasses the performance of sequence tagging constituent parsers on the English and Chinese Penn Treebank datasets and reduces their parsing time even further.

Copied to clipboard

Xinmeng Hou, Lingyue Fu, Chenhao Meng, Kounianhua Du, Hai Hu

Explainable Question Answering based on Semantic Graph by Global Differentiable Learning and Dynamic Adaptive Reasoning (2022.emnlp-main)

Challenge:	Existing approaches to extract aspects and opinions independently, optionally adding pairwise relations, often lead to error propagation and high time complexity.
Approach:	They propose a transition-based model that performs aspect and opinion extraction jointly and integrates contrastive-augmented optimization.
Outcome:	The proposed model outperforms previous models on two out of four datasets when trained on a single dataset.

Copied to clipboard

Jianguo Mao, Wenbin Jiang, Xiangdong Wang, Hong Liu, Yu Xia, Yajuan Lyu, QiaoQiao She

Explainability & Interpretability in NLP

Challenge:	Existing models for multi-hop Question Answering have improved the implicit reasoning ability, but the black box nature of pure neural networks has hindered the construction of explainable intelligent systems.
Approach:	They propose a global differentiation strategy to explore optimal reasoning paths from latent probability space and a Dynamic Adaptive Reasoner to enhance generalization of unseen questions.
Outcome:	The proposed method achieves 17% improvements in F1-score against BreakRC and shows better interpretability.

A Transition-based Method for Complex Question Understanding (2022.coling-1)

Copied to clipboard

Yu Xia, Wenbin Jiang, Yajuan Lyu, Sujian Li

Explainability & Interpretability in NLP

Challenge:	Existing work on complex question understanding does not model intermediate states and does not provide step-wise information.
Approach:	They propose a transition-based method where a decider predicts a sequence of actions to build the graph node-by-node.
Outcome:	The proposed method parses complex questions to QDMR using atomic operators . it has transparent and human-readable intermediate results, showing improved interpretability .

Noisy Label Regularisation for Textual Regression (2022.coling-1)

Copied to clipboard

Yuxia Wang, Timothy Baldwin, Karin Verspoor

LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation? (2024.naacl-long)

Challenge:	Existing methods to regularise noisy labels are ineffective in the face of noisy data.
Approach:	They propose a method that regularises noisy labels and prevents error propagation from the input layer.
Outcome:	The proposed method regularises noisy labels and improves generalisation performance over real-world human-disagreement annotations and randomly-corrupted and data-augmented labels.

Copied to clipboard

Yuchi Wang, Shuhuai Ren, Rundong Gao, Linli Yao, Qingyan Guo, Kaikai An, Jianhong Bai, Xu Sun

StereoRel: Relational Triple Extraction from a Stereoscopic Perspective (2021.acl-long)

Challenge:	Existing models for text-to-image generation have been underperforming in image-totext generation tasks.
Approach:	They propose a framework that uses a split BERT to create a dedicated latent space for captions and integrates a regularization module to manage varying text lengths.
Outcome:	The proposed framework achieves state-of-the-art performance on the MS COCO dataset with 38.2 BLEU@4 and 126.2 CIDEr .

Copied to clipboard

Xuetao Tian, Liping Jing, Lu He, Feng Liu

MIDGARD: Self-Consistency Using Minimum Description Length for Structured Commonsense Reasoning (2024.acl-long)

Challenge:	Existing methods for relational triple extraction still face challenges, including information loss and error propagation.
Approach:	They propose a model which maps relational triples to a three-dimensional space and leverages three decoders to extract them.
Outcome:	The proposed model outperforms the baselines on five public datasets.

Copied to clipboard

Inderjeet Nair, Lu Wang

End-to-end Learning of Logical Rules for Enhancing Document-level Relation Extraction (2024.acl-long)

Challenge:	Existing approaches to generate a reasoning graph from natural language input suffer from error propagation due to autoregressive nature and single-pass-based decoding.
Approach:	They propose a method that uses minimum description length to identify consistent properties among different graph samples generated by large language models.
Outcome:	The proposed method outperforms previous approaches for generating reasoning graphs from natural language input using large language models.

Copied to clipboard

Kunxun Qi, Jianfeng Du, Hai Wan

A Pointer Network Architecture for Joint Morphological Segmentation and Tagging (2020.findings-emnlp)

Challenge:	Document-level relation extraction (DocRE) aims to extract relations between entities in a document.
Approach:	They propose a rule-based framework that jointly learns DocRE and logical rules . they parameterize a Rule reasoning module to simulate the inference of logical rule .
Outcome:	The proposed framework improves DocRE models by a significant margin on four benchmark datasets.

Copied to clipboard

Amit Seker, Reut Tsarfaty

Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter (D18-1)

Challenge:	Morphological Disambiguation (MD) is a task of decomposing tokens into morphemes . a simple pipeline is used to segment and tagging raw tokens .
Approach:	They propose a new pointer network model that combines symbolic knowledge of morphemes with the learning capacity of neural end-to-end modeling.
Outcome:	The proposed model outperforms all previous reported results on Hebrew and Turkish . it uses morphological knowledge and the learning capacity of neural end-to-end modeling .

Copied to clipboard

Lijun Wu, Xu Tan, Di He, Fei Tian, Tao Qin, Jianhuang Lai, Tie-Yan Liu

Token-level Sequence Labeling for Spoken Language Understanding using Compositional End-to-End Models (2022.findings-emnlp)

Challenge:	Neural machine translation suffers from exposure bias and error propagation problem.
Approach:	They conduct a series of analyses to deeply understand the accuracy drop problem . they find that the left part of the translated sentence is often better than its right part .
Outcome:	The results show that the left part of the translated sentence is often better than its right part in left-to-right decoding models.

Copied to clipboard

Siddhant Arora, Siddharth Dalmia, Brian Yan, Florian Metze, Alan W Black, Shinji Watanabe

Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASR (2021.findings-acl)

Challenge:	End-to-end spoken language understanding systems model sequence labeling as a sequence prediction task causing a divergence from its well-established token-level tagging formulation.
Approach:	They propose to model sequence labeling as a sequence prediction task . their systems explicitly separate the added complexity of recognizing spoken mentions from the NLU task of sequence labelling .
Outcome:	The proposed systems outperform both cascaded and direct models on a labeling task of named entity recognition across SLU benchmarks.

Copied to clipboard

Junkun Chen, Mingbo Ma, Renjie Zheng, Liang Huang

ML-LMCL: Mutual Learning and Large-Margin Contrastive Learning for Improving ASR Robustness in Spoken Language Understanding (2023.findings-acl)

Challenge:	Existing approaches to simultaneous speech-to-text translation suffer from error propagation and extra latency.
Approach:	They propose a new paradigm for simultaneous speech-to-text translation using two separate decoders . they use multitask learning to jointly learn these two tasks with a shared encoder .
Outcome:	The proposed method achieves substantially better translation quality at similar levels of latency.

Copied to clipboard

Xuxin Cheng, Bowen Cao, Qichen Ye, Zhihong Zhu, Hongxiang Li, Yuexian Zou

LGAR: Zero-Shot LLM-Guided Neural Ranking for Abstract Screening in Systematic Literature Reviews (2025.findings-acl)

Challenge:	Despite efforts to improve ASR robustness, errors from pipeline approaches can lead to error propagation.
Approach:	They propose a framework for improving ASR robustness in SLU by using mutual learning and large-margin contrastive learning.
Outcome:	The proposed framework outperforms existing models and achieves new state-of-the-art performance on three datasets.

Copied to clipboard

Christian Jaumann, Andreas Wiedholz, Annemarie Friedrich

Unsupervised Domain Adaptation for Joint Information Extraction (2022.findings-emnlp)

Challenge:	Existing methods for abstract screening focus on binary classification settings; existing question answering (QA) based ranking approaches suffer from error propagation.
Approach:	They propose a systematic literature review (SLR) method that uses large language models to evaluate the SLR's inclusion and exclusion criteria.
Outcome:	The proposed method outperforms existing question answering (QA) based methods by 5-10 pp. in mean precision.

Copied to clipboard

Nghia Ngo, Bonan Min, Thien Nguyen

Another Dead End for Morphological Tags? Perturbed Inputs and Parsing (2023.findings-acl)

Challenge:	Current JIE methods focus on standard supervised learning setting where training and test data come from the same domain.
Approach:	They propose a method to induce domain-invariant representations for the tasks in JIE by a generalized version of domain-adversarial learning.
Outcome:	The proposed method improves out-of-domain performance for current pipeline approaches for all IE tasks.

Copied to clipboard

Alberto Muñoz-Ortiz, David Vilares

Joint Entity and Relation Extraction with Span Pruning and Hypergraph Neural Networks (2023.emnlp-main)

Challenge:	Part-of-speech tags are used for word-contextualized parsers, but their impact is limited to word-based models.
Approach:	They propose an adversarial attack to test whether morphological tags contribute to error propagation or correct parsing mistakes.
Outcome:	The proposed attack on 14 treebanks shows that if morphological tags were utopically robust against lexical perturbations, they would be able to correct parsing mistakes.

Copied to clipboard

Zhaohui Yan, Songlin Yang, Wei Liu, Kewei Tu

Referring Image Segmentation via Joint Mask Contextual Embedding Learning and Progressive Alignment Network (2023.emnlp-main)

Challenge:	Entity and Relation Extraction (ERE) is an important task in information extraction.
Approach:	They propose a hypergraph neural network for ERE built upon the PL-marker . they use a pruner mechanism to transfer the burden of entity identification to the joint module .
Outcome:	The proposed model improves on three widely used benchmarks on ERE task . it uses a pruner mechanism to transfer the burden of entity identification to the joint module .

Copied to clipboard

Ziling Huang, Shin’ichi Satoh

An End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization (2021.acl-long)

Challenge:	Existing methods for referring image segmentation may encounter limitations in maintaining focus on relevant information during specific stages and rectifying errors propagated from early stages.
Approach:	They propose a network that integrates a Learnable Contextual Embedding module and a Progressive Alignment Network to enhance the cascade framework.
Outcome:	The proposed network achieves state-of-the-art results on three commonly used benchmarks.

Copied to clipboard

Baohang Zhou, Xiangrui Cai, Ying Zhang, Xiaojie Yuan

Re-Cent: A Relation-Centric Framework for Joint Zero-Shot Relation Triplet Extraction (2025.coling-main)

Challenge:	Existing models for medical named entity recognition and named entity normalization suffer from error propagation between the two tasks.
Approach:	They propose an end-to-end progressive multi-task learning model for jointly modeling medical named entity recognition and normalization in an effective way.
Outcome:	The proposed model reduces error propagation by exploiting the learnable features for both tasks to improve performance.

Copied to clipboard

Zehan Li, Fu Zhang, Kailun Lyu, Jingwei Cheng, Tianyue Peng

RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Models (2025.emnlp-main)

Challenge:	Existing methods to extract triplets from context often decompose into named entity recognition and relation classification, which may introduce error propagation.
Approach:	They propose a Relation-centric joint ZSRTE method which leverages unseen relation labels to extract triplets in one go.
Outcome:	The proposed method achieves state-of-the-art performance with fewer parameters and does not rely on synthetic data or manual labor.

Copied to clipboard

Zhaoyan Gong, Juan Li, Zhiqiang Liu, Lei Liang, Huajun Chen, Wen Zhang

AgentPro: Enhancing LLM Agents with Automated Process Supervision (2025.emnlp-main)

Challenge:	Current temporal knowledge graph question answering methods focus on implicit temporal constraints and lack the capability to handle complex temporal queries.
Approach:	They propose a temporal knowledge graph question answering framework that recursively decomposes questions into sub-problems and employs multi-path answer aggregation to improve fault tolerance.
Outcome:	The proposed framework outperforms existing methods on multiTQ and TimelineKGQA benchmarks.

Copied to clipboard

Yuchen Deng, Shichen Fan, Naibo Wang, Xinkui Zhao, See-Kiong Ng

Leveraging Large Pre-trained Multilingual Models for High-Quality Speech-to-Text Translation on Industry Scenarios (2025.coling-main)

Challenge:	Existing frameworks lack explicit supervision during the reasoning process, which may lead to error propagation across reasoning chains.
Approach:	They propose a framework which automates process supervision for large language model agents by automatically generating step-level annotations and developing a process reward model based on these annotations.
Outcome:	The proposed framework outperforms existing agent-based methods on four datasets and achieves a 6.32% increase in accuracy.

Copied to clipboard

Marko Avila, Josep Crego

Query-based Instance Discrimination Network for Relational Triple Extraction (2022.emnlp-main)

Challenge:	Speech-to-Text Translation systems rely on a sequential pipeline that combines ASR and MT models.
Approach:	They propose a parameter-efficient framework that integrates one LPSM with a multilingual MT engine.
Outcome:	The proposed framework integrates one LPSM with a multilingual MT engine.

Copied to clipboard

Zeqi Tan, Yongliang Shen, Xuming Hu, Wenqi Zhang, Xiaoxia Cheng, Weiming Lu, Yueting Zhuang

Semantic Role Labeling from Chinese Speech via End-to-End Learning (2024.findings-acl)

Challenge:	Recent approaches to extract relational triples from open domain texts suffer from error propagation, relation redundancy and lack of high-level connections.
Approach:	They propose a query-based approach to construct instance-level representations for relational triples . they use query embeddings and token embeddables to extract all types of triples in one step .
Outcome:	The proposed method achieves state-of-the-art on five widely used benchmarks.

Copied to clipboard

Huiyao Chen, Xinxin Li, Meishan Zhang, Min Zhang

Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions (D19-1)

Challenge:	Semantic role labeling (SRL) has traditionally focused on text input.
Approach:	They propose an end-to-end approach for SRL from speech integrating ASR and SRL in a joint-learning framework, focusing on the Chinese language.
Outcome:	The proposed model improves on the Chinese Proposition Bank 1.0 dataset and the existing model with improved performance.

Copied to clipboard

Rui Zhang, Tao Yu, Heyang Er, Sungrok Shim, Eric Xue, Xi Victoria Lin, Tianze Shi, Caiming Xiong, Richard Socher, Dragomir Radev

FRVA: Fact-Retrieval and Verification Augmented Entailment Tree Generation for Explainable Question Answering (2024.findings-acl)

Challenge:	Generating SQL queries from user utterances is an important task to help end users acquire information from databases.
Approach:	They propose a context-dependent text-to-SQL generation task that edits previous queries . they use an utterance-table encoder and a table-aware decoder to incorporate context .
Outcome:	The proposed model is flexible to change individual tokens and robust to error propagation.

Copied to clipboard

Yue Fan, Hu Zhang, Ru Li, YuJie Wang, Hongye Tan, Jiye Liang

Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization (2023.acl-long)

Challenge:	Existing methods for generating a entailment tree exhibit the reasoning chains from knowledge facts to predicted answers, but they have large fact search spaces and error accumulation problems resulting in the generation of invalid steps.
Approach:	They propose a Fact-Retrieval and Verification Augmented bidirectional entailment tree generation method that contains two systems.
Outcome:	The proposed method outperforms existing models and achieves state-of-the-art performance in fact selection and structural correctness.

Copied to clipboard

Xinyu Wang, Lin Gui, Yulan He

SLURP: A Spoken Language Understanding Resource Package (2020.emnlp-main)

Challenge:	Document-level multi-event extraction aims to extract the structural information from a given document automatically.
Approach:	They propose an alternative approach for document-level multi-event extraction with event proxy nodes and Hausdorff distance minimization.
Outcome:	The proposed method outperforms state-of-the-art methods on two datasets with only a fraction of training time.

Copied to clipboard

Emanuele Bastianelli, Andrea Vanzo, Pawel Swietojanski, Verena Rieser

Challenge:	Publicly available datasets for Spoken Language Understanding (SLU) are limited.
Approach:	They propose a publicly available SLU resource package that includes a multi-domain dataset in English spanning 18 domains.
Outcome:	The proposed dataset is bigger and more diverse than existing datasets.

Evaluating Large Language Models for Cross-Lingual Retrieval (2025.findings-emnlp)

Copied to clipboard

Longfei Zuo, Pingjun Hong, Oliver Kraus, Barbara Plank, Robert Litschko

JumpCoder: Go Beyond Autoregressive Coder via Online Modification (2024.acl-long)

Challenge:	Large Language Models (LLMs) have been evaluated as second-stage reranking models for monolingual IR, but a systematic comparison is lacking for cross-lingual reranked IR.
Approach:	They propose to use machine translation to evaluate rerankers in cross-lingual IR . they find that LLMs perform better than LLM-based reranked models .
Outcome:	The proposed model improves cross-lingual IR but relies on machine translation for the first stage.

Copied to clipboard

Mouxiang Chen, Hao Tian, Zhongxin Liu, Xiaoxue Ren, Jianling Sun

Challenge:	Existing code large language models lack reversibility and autoregressive sequential generation is incapable of correcting previous missing statements as humans do.
Approach:	They propose a model-agnostic framework that enables human-like online modification and non-sequential generation to augment code large language models.
Outcome:	The proposed framework enables human-like modification and non-sequential generation to augment code large language models.

Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems (2025.emnlp-main)

Copied to clipboard

Xu Shen, Yixin Liu, Yiwei Dai, Yili Wang, Rui Miao, Yue Tan, Shirui Pan, Xin Wang

Meta-Reasoner: Dynamic Guidance for Optimized Inference-time Reasoning in Large Language Models (2026.findings-acl)

Challenge:	Empirical studies for communication topology design often overlook why and when sparse and dense topologies help or hinder collaboration.
Approach:	They propose a topology design approach that balances error suppression and beneficial information propagation by fusing connectivity patterns from dense and sparse graphs.
Outcome:	The proposed topology design achieves superior performance across tasks with sparse and dense graphs.

Copied to clipboard

Yuan Sui, Yufei He, Tri Cao, Sophia Simeng Han, Yulin Chen, Bryan Hooi

Training LLMs for Optimization Modeling via Iterative Data Synthesis and Structured Validation (2025.findings-emnlp)

Challenge:	Recent advances on prompting and post-training have enabled LLMs to perform step-wise reasoning tasks, but they tend to explore unproductive solution paths without effective backtracking or strategy adjustment.
Approach:	They propose a framework that empowers LLMs to “think about how to think” and dynamically adapts reasoning strategies in real-time.
Outcome:	The proposed framework outperforms previous SOTA methods by 9-12% in accuracy while reducing inference time by 28-35% under the same compute budget.

Copied to clipboard

Yang Wu, Yifan Zhang, Yurong Wu, Yuran Wang, Junkai Zhang, Jian Cheng

Towards relation extraction from speech (2022.emnlp-main)

Challenge:	Large Language Models (LLMs) are a promising tool for OR, but they face challenges when dealing with complex problems.
Approach:	They propose a framework that augments existing datasets and generates high-quality fine-tuning data tailored to OR.
Outcome:	The proposed framework augments existing datasets and generates high-quality fine-tuning data . it prevents error propagation and ensures the quality of the generated dataset .

Copied to clipboard

Tongtong Wu, Guitao Wang, Jinming Zhao, Zhaoran Liu, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari

CTC-based Non-autoregressive Speech Translation (2023.acl-long)

Challenge:	Existing methods for extracting relations from speech have been neglected due to the nature of speech.
Approach:	They propose a listening information extraction task that uses speech to extract relation extraction from speech . they use a text-to-speech system and crowd-sourced native English speakers to test the task .
Outcome:	The proposed task extracts semantic relationships from speech data using a new model . the proposed task is more challenging than the existing method due to the characteristics of speech .

Copied to clipboard

Chen Xu, Xiaoqian Liu, Xiaowen Liu, Qingxuan Sun, Yuhao Zhang, Murun Yang, Qianqian Dong, Tom Ko, Mingxuan Wang, Tong Xiao, Anxiang Ma, Jingbo Zhu

Machine Translation

Challenge:	End-to-end speech translation (E2E ST) and non-autoregressive (NAR) generation are promising in language and speech processing for their advantages of less error propagation and low latency.
Approach:	They develop a model that uses connectionist temporal classification to predict the source and target texts.
Outcome:	The proposed model achieves an average BLEU score of 29.5 with a speed-up of 5.67.

Maximal Clique Based Non-Autoregressive Open Information Extraction (2021.emnlp-main)

Copied to clipboard

Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, Bin Wang

UniCOQE: Unified Comparative Opinion Quintuple Extraction As A Set (2023.findings-acl)

Challenge:	Open Information Extraction (OpenIE) aims to discover textual facts from a given sentence.
Approach:	They propose a non-autoregressive framework that generates a fact graph and a graph with an edge linking two nodes that belong to the same fact.
Outcome:	The proposed framework outperforms current state-of-the-art methods on two benchmark datasets and significantly outperformed the existing ones.

Copied to clipboard

Zinong Yang, Feng Xu, Jianfei Yu, Rui Xia

A Unified One-Step Solution for Aspect Sentiment Quad Prediction (2023.findings-acl)

Challenge:	Existing methods decompose the COQE task into multiple subtasks and solve them in a pipeline manner, but ignore the intrinsic connection between subtask and the error propagation among stages.
Approach:	They propose a unified generative model that solves COQE in one shot by concatenating all the comparative tuples into a target output sequence.
Outcome:	The proposed model significantly outperforms the SOTA method on multiple benchmarks and ablation experiments.

Copied to clipboard

Junxian Zhou, Haiqin Yang, Yuxuan He, Hao Mou, JunBo Yang

Balancing Fidelity and Plasticity: Aligning Mixed-Precision Fine-Tuning with Linguistic Hierarchies (2026.findings-acl)

Challenge:	Existing ASQP datasets are small and low-density, hindering technical advancement . et al. (2017): aspect sentiment quad prediction provides a complete aspect-level sentiment structure.
Approach:	They propose a one-step solution for Aspect sentiment quad prediction that can detect aspect categories and identify aspectopinion-sentiment triplets simultaneously.
Outcome:	The proposed solution can detect aspect categories and identify aspectopinion-sentiment triplets simultaneously.

Copied to clipboard

Changhai Zhou, Shiyang Zhang, Yuhua Zhou, Jun Gao, Qian Qiao, Shichao Weng, Weizhong Zhang, Cheng Jin

Tree-Notebook: A Context-Aware Agent with Tree Search and Entropy-Aware Data Shadow for Interactive Data Science (2026.findings-acl)

Challenge:	Existing quantization-aware fine-tuning methods decouple weight precision and adapter capacity, overlooking that a layer’s ability to adapt is constrained by the information preserved in its frozen weights.
Approach:	They propose a framework that jointly optimizes per-layer quantization bit-width and LoRA rank.
Outcome:	Experiments on LLaMA and Qwen models show that the proposed framework matches or approaches 16-bit baselines while using substantially less memory.

Copied to clipboard

Junkun Qiu, Min Huang, Qinghai Miao

Indic-TEDST: Datasets and Baselines for Low-Resource Speech to Text Translation (2024.lrec-main)

Challenge:	Experimental results show that Tree-Notebook achieves state-of-the-art (SOTA) performance on InfiAgent-DABench and DSBench.
Approach:	They propose an agentic framework that mimics the iterative cognitive process of human data scientists.
Outcome:	The proposed framework achieves state-of-the-art (SOTA) performance on InfiAgent-DABench and DSBench.

Copied to clipboard

Nivedita Sethiya, Saanvi Nair, Chandresh Maurya

Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning (2026.findings-acl)

Challenge:	Speech-to-text Translation (ST) tasks are performed by human translators with proficiency in both the source and target languages.
Approach:	a new study compares the performance of SOTA ST models on low-resource languages . the authors propose to use a dataset to compare the models on high-resourced languages based on the results of their research .
Outcome:	a new study shows that only a few models have performed well on low-resource languages . the results indicate the need for specialized models for low- and high-resourced languages based on the dataset .

Copied to clipboard

Xudong Li, Yuhang Tian, Dandan Song, Zhijing Wu, Shuhao Zhang, Jun Yang, Yongyu Huo, Changzhi Zhou, Xinyu Zhang, Chenhao Li, Huipeng Ma, Luan Zhang, Yan Xu, Qian Liu

Towards Zero-shot Learning for End-to-end Cross-modal Translation Models (2023.findings-emnlp)

Challenge:	Existing knowledge editing methods rely on unidirectional, feed-forward pipelines . a minor retrieval error or logical mismatch at an early hop can become a silent failure .
Approach:	They propose a framework for closed-loop post-edit reasoning that uses a Critic agent to verify coherence and step-wise correctness.
Outcome:	Experiments on MQuAKE-2002 and MQuADE-hard show that CARE effectively mitigates error propagation . a minor retrieval error or logical mismatch at an early hop can become a silent failure .

Copied to clipboard

Jichen Yang, Kai Fan, Minpeng Liao, Boxing Chen, Zhongqiang Huang

InstructEd: Soft-Instruction Tuning for Model Editing with Hops (2024.findings-acl)

Challenge:	End-to-end zero-shot speech translation model is based on a zero-shot approach, but it is less competitive because of the limited amount of data available for multiple modalities.
Approach:	They propose an end-to-end zero-shot speech translation model that connects two pre-trained uni-modality modules via word rotator’s distance.
Outcome:	The proposed model performs better than or as well as those of the CTC-based models and can be trained in an end-to-end style to avoid error propagation.

Copied to clipboard

XiaoQi Han, Ru Li, Xiaoli Li, Jiye Liang, Zifang Zhang, Jeff Pan

Task-Aware Self-Supervised Framework for Dialogue Discourse Parsing (2023.findings-emnlp)

Challenge:	Existing methods for model editing are limited due to excessive memorization and knowledge conflict issues.
Approach:	They propose to insert soft instructions into the attention module to facilitate interactions between instructions and questions and to understand and utilize new facts.
Outcome:	The proposed method achieves 10% improvement in one-hop (multi-hop) model editing on three datasets with LLaMAs and GPT2 .

Copied to clipboard

Wei Li, Luyao Zhu, Wei Shao, Zonglin Yang, Erik Cambria

In-Image Neural Machine Translation with Segmented Pixel Sequence-to-Sequence Model (2023.findings-emnlp)

Challenge:	Existing discourse parsing approaches are constrained by predefined relation types, which can impede the adaptability of the parser for downstream tasks.
Approach:	They propose to introduce a task-aware paradigm to improve the versatility of the parser.
Outcome:	Empirical studies on dialogue discourse parsing datasets and a downstream task demonstrate the proposed framework.

Copied to clipboard

Yanzhi Tian, Xiang Li, Zeming Liu, Yuhang Guo, Bin Wang

MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation (2025.acl-long)

Challenge:	In-Image Machine Translation (IIMT) aims to convert images containing texts from one language to another.
Approach:	They propose an end-to-end model instead of the traditional cascade methods which use optical character recognition followed by neural machine translation and text rendering.
Outcome:	The proposed model outperforms both cascade methods and current model in translation quality and robustness across various dimensions.

Copied to clipboard

Haochen Xue, Feilong Tang, Ming Hu, Yexin Liu, Qidong Huang, Yulong Li, Chengzhi Liu, Zhongxing Xu, Chong Zhang, Chun-Mei Feng, Yutong Xie, Imran Razzak, Zongyuan Ge, Jionglong Su, Junjun He, Yu Qiao

Natural Language Interfaces

Challenge:	Existing multimodal large language models lack the ability to memorize, recall, and reason in sustained interactions.
Approach:	They propose a multimodal real-world conversation benchmark for evaluating open-ended abilities of multimodal large language models.
Outcome:	The proposed benchmarks show that the models perform better in open-ended conversations.

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction (2026.findings-acl)

Copied to clipboard

Xu Shen, Qi Zhang, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen

ApiQ: Finetuning of 2-Bit Quantized Large Language Model (2024.emnlp-main)

Challenge:	Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors.
Approach:	They propose a metacognitive framework that enables step-level error detection and self-correction in Large Language Model based multi-agent systems (MAS) .
Outcome:	The proposed framework outperforms baselines on the Who When benchmark and delivers consistent gains on AgentErrorBench.

Copied to clipboard

Baohao Liao, Christian Herold, Shahram Khadivi, Christof Monz

AgentAsk: Multi-Agent Systems Need to Ask (2026.acl-long)

Challenge:	Memory-efficient finetuning of large language models (LLMs) has attracted huge attention with the increasing size of LLMs due to the constraints posed by GPU memory limitations and the effectiveness of these methods compared to full finetune.
Approach:	They propose a memory-efficient finetuning framework called ApiQ to restore lost information from quantization by initializing LoRA components and quantizing weights of LLMs.
Outcome:	The proposed framework maintains the original LLM’s activation precision while mitigating error propagation from shallower into deeper layers.

Copied to clipboard

Bohan Lin, Kuo Yang, Zelin Tan, Yingchuan Lai, Chen Zhang, Guibin Zhang, Xinlei Yu, Miao Yu, Xu Wang, Yudong Zhang, Yang Wang

Step Feasibility-Aware and Error-Correctable Entailment Tree Generation (2024.lrec-main)

Challenge:	Multi-agent systems fail to consistently outperform strong single-a agent baselines due to error propagation at inter-aggent message handoffs.
Approach:	They propose an edge-level error taxonomy that identifies four main errors in multi-agent interactions as data gaps, signal corruption, referential drift and capacity gaps as primary sources of failure.
Outcome:	The proposed module outperforms existing systems on five benchmarks and is architecture-agnostic.

Copied to clipboard

Junyue Song, Xin Wu, Yi Cai

LaCo: Layer-wise Compensation for Pruned Large Language Models (2026.acl-long)

Challenge:	Existing methods for generating entailment trees suffer from false feasible steps, resulting in error propagation.
Approach:	They propose an iterative entailment tree generation framework with step feasibility perception and state error handling mechanisms to enhance the interpretability of QA systems.
Outcome:	The proposed framework improves the interpretation of QA systems by demonstrating that it is feasible to choose steps that are false feasible and error propagating.

Copied to clipboard

Yingen Liu, Fan Wu, null Panxuyan, Ruihui Li, Zhuo Tang, Kenli Li

Uncertainty-Aware Contrastive Decoding (2025.findings-acl)

Challenge:	Existing methods for predicting performance degradations of Large Language Models (LLMs) neglect the structural distortions caused by sparsity.
Approach:	They propose a framework that reorients the recovery paradigm from global adaptation to hierarchical representation alignment by sequentially optimizing each layer to reconstruct the model's hidden states.
Outcome:	The proposed framework surpasses parameter-efficient baselines in perplexity reduction and zero-shot reasoning.

Copied to clipboard

Hakyung Lee, Subeen Park, Joowang Kim, Sungjun Lim, Kyungwoo Song

Challenge:	Large language models excel in a wide range of tasks, but generating factually accurate outputs remains a challenge.
Approach:	They propose a method that dynamically adjusts model contributions at each decoding step based on uncertainty.
Outcome:	The proposed method significantly improves factual accuracy and reliability over existing methods.

Temporal Evidence Chain for Temporal Knowledge Graph Question Answering with Large Language Models (2026.acl-long)

Copied to clipboard

Shihao Liu, Xiaofei Zhou, Bo Wang, Geyuan Zhang

TECA: A Two-stage Approach with Controllable Attention Soft Prompt for Few-shot Nested Named Entity Recognition (2024.lrec-main)

Challenge:	Temporal Knowledge Graph Question Answering (TKGQA) aims to answer temporal questions using knowledge from Temporal knowledge graphs.
Approach:	They propose a framework to construct temporal evidence chains for LLM reasoning using Temporal Knowledge Graphs.
Outcome:	TECQA outperforms existing methods on MultiTQ and CronQuestions.

Copied to clipboard

Yuanyuan Xu, Linhai Zhang, Deyu Zhou

STA-CoT: Structured Target-Centric Agentic Chain-of-Thought for Consistent Multi-Image Geological Reasoning (2025.findings-emnlp)

Challenge:	Existing methods for few-shot nested named entity recognition (NER) ignore relationship between inner and outer entities, which is crucial for fewshot ner.
Approach:	They propose a span-based method with a controllable attention soft prompt for few-shot nested named entity recognition (TECA) the span part identification provides possible entity mentions without an extra filtering module.
Outcome:	The proposed method outperforms baseline models on four benchmark datasets and outperformed competing models on F1-score by 5.62% on ACE04, 5.11% on ace05, 3.41% on KBP2017 and 0.7% on GENIA on the 10-shot setting.

Copied to clipboard

Beibei Yu, Tao Shen, Ling Chen

ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs (2026.findings-acl)

Challenge:	Reliable multi-image geological reasoning is essential for automating expert tasks in remote-sensing mineral exploration.
Approach:	They propose a framework that orchestrates planning, execution, and verification agents to decompose, ground, and iteratively refine reasoning steps over geological and hyperspectral image sets.
Outcome:	The proposed framework decomposes, ground, and iteratively refines reasoning steps over geological and hyperspectral image sets.

Copied to clipboard

Jian Cui, Zhiyuan Ren, Desheng Weng, Yongqi Zhao, Gong Wenbin, Yu Lei, Zhenning Dong

Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language Models (2025.acl-long)

Challenge:	Existing methods rely on text retrieval and geographic knowledge bases to generate coordinates, and they are prone to error propagation and dependency on structured knowledge bases.
Approach:	They propose to use large language models to convert geographic coordinates into geohash sequences and introduce a Chain-of-Thought mechanism to enhance the model’s reasoning over spatial relationships.
Outcome:	The proposed framework can handle explicit address queries in single-point predictions and effectively resolve vague relative location queries.

Copied to clipboard

Fei Wang, Xingchen Wan, Ruoxi Sun, Jiefeng Chen, Sercan O Arik

Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity (2026.findings-acl)

Challenge:	Existing studies have not linked the behavior of retrieval augmented generation (RAG) with imperfect retrieval, including irrelevant, misleading, or even malicious information.
Approach:	They propose an approach that integrates external knowledge with source-awareness to overcome imperfect retrieval errors in RAG.
Outcome:	The proposed approach is superior to previous robustness-enhanced approaches under the worst-case scenario.

Copied to clipboard

Yucheng Zhou, Jianbing Shen

Representation Learning

Challenge:	Existing autoregressive models have shown superior performance and efficiency in image generation, but are constrained by high computational costs and prolonged training times in video generation.
Approach:	They propose a Local Optimization method which optimizes tokens within localized windows while leveraging contextual information to reduce error propagation.
Outcome:	The proposed method achieves superior performance to the baseline while halving the training cost without sacrificing quality.

Free-MAD: Consensus-Free Multi-Agent Debate (2026.findings-acl)

Copied to clipboard

Yu Cui, Hang Fu, Haibin Zhang, Licheng Wang, Cong Zuo

SR-RAG: Verifiable Multi-Hop Reasoning via On-the-fly Symbolic Graph Construction (2026.findings-acl)

Challenge:	Existing multi-agent debate methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is decided by majority voting in the last round.
Approach:	They propose a multi-agent debate framework that eliminates the need for consensus among agents and reconstructs the debate phase by introducing anti-conformity.
Outcome:	Experiments on eight benchmark datasets show that Free-MAD significantly improves reasoning performance while requiring only a single-round debate and thus reducing token costs.

Copied to clipboard

Zehua Wang, Zhaojin Zhang, Boyu Qiu, Xiaolong Weng, Ying Xiong, Buzhou Tang, Min Zhang

HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy (2026.findings-acl)

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.

Copied to clipboard

Guoqi Ma, Liang Zhang, Hongyao Tu, Hao Fu, Hui Li, Yujie Lin, Longyue Wang, Weihua Luo, Jinsong Su