END-TO-END

Entity Resolution in Open-domain Conversations (2021.naacl-industry)

Challenge:	tutorial aims to familiarise research community with recent advances in statistical dialogue systems . focus of tutorial is on learning end-to-end from data and their relation to more common modular systems.
Approach:	This tutorial aims to familiarise the research community with the latest advances in statistical dialogue systems . the focus of the tutorial is on recently introduced end-to-end learning for dialogue systems and their relation to more common modular systems.
Outcome:	This tutorial aims to familiarise the research community with the recent advances in statistical dialogue systems for open-domain and task-based dialogue paradigms.

Copied to clipboard

Mingyue Shang, Tong Wang, Mihail Eric, Jiangning Chen, Jiyang Wang, Matthew Welch, Tiantong Deng, Akshay Grewal, Han Wang, Yue Liu, Yang Liu, Dilek Hakkani-Tur

Towards Codec-LM Co-design for Neural Codec Language Models (2025.naacl-srw)

Challenge:	Recent work on incorporating external knowledge into the response generation models has attracted great interest.
Approach:	They propose a neural entity linking approach to incorporate external knowledge into the response generation models to improve the relevancy of retrieved knowledge.
Outcome:	The proposed approach outperforms the baseline model by 62.8% relative to the baseline.

Copied to clipboard

Shih-Lun Wu, Aakash Lahoti, Arjun D Desai, Karan Goel, Chris Donahue, Albert Gu

Which Side Are You On? A Multi-task Dataset for End-to-End Argument Summarisation and Evaluation (2024.findings-acl)

Challenge:	Neural codec language models (or codec LMs) are emerging as a powerful framework for text-to-speech (TTS) despite the close interdependence of codecs and LM, research on codec and lms has largely remained siloed.
Approach:	They propose a frame-wise codec encoder that improves both LM log-likelihood and TTS metrics . they also propose LM codebook level dropout to efficiently navigate a portion of codec-LM design space .
Outcome:	The proposed codec-LM co-design improves intelligibility, audio quality and speaker control compared to a siloed baseline.

Copied to clipboard

Hao Li, Yuping Wu, Viktor Schlegel, Riza Batista-Navarro, Tharindu Madusanka, Iqra Zahid, Jiayan Zeng, Xiaochi Wang, Xinran He, Yizhi Li, Goran Nenadic

PDDLEGO: Iterative Planning in Textual Environments (2024.starsem-1)

Challenge:	Recent advances in large language models (LLMs) have made it difficult to build an automated debate system that helps people to synthesise persuasive arguments.
Approach:	They propose to use an argument mining dataset to capture the end-to-end process of preparing an argumentative essay for a debate.
Outcome:	The proposed dataset shows that it performs better on individual tasks than on human-centred evaluations.

Copied to clipboard

Li Zhang, Peter Jansen, Tianyi Zhang, Peter Clark, Chris Callison-Burch, Niket Tandon

Challenge:	Existing methods to plan in textual environments rely on a fully-observed environment where all entity states are known, but are not interpretable.
Approach:	They propose to use LLMs to generate a formal representation of the environment that can be solved by a symbolic planner.
Outcome:	The proposed model outperforms existing methods in the Coin Collector simulation and Cooking World simulations.

BotSIM: An End-to-End Bot Simulation Framework for Commercial Task-Oriented Dialog Systems (2022.emnlp-demos)

Copied to clipboard

Guangsen Wang, Samson Tan, Shafiq Joty, Gang Wu, Jimmy Au, Steven C.h. Hoi

Automatic Spelling Correction for Resource-Scarce Languages using Deep Learning (P18-3)

Challenge:	evaluating and troubleshooting production TOD systems is still a largely manual process requiring large amount of human conversations with the systems.
Approach:	They propose a data-efficient end-to-end Bot SIMulation framework for commercial task-oriented dialog systems that can generate user queries and generate semantic-level dialog acts and entities from bot definitions.
Outcome:	The proposed framework is able to infer semantic-level dialog acts and entities from bot definitions and generate user queries via model-based paraphrasing.

Copied to clipboard

Pravallika Etoori, Manoj Chinnakotla, Radhika Mamidi

DATE: Detecting Anomalies in Text via Self-Supervision of Transformers (2021.naacl-main)

Challenge:	Indic languages are resource-scarce and do not have such parallel data due to low volume of queries.
Approach:	They propose a sequence-to-sequence deep learning model which trains end-to end for Indic languages, Hindi and Telugu.
Outcome:	The proposed model is competitive with existing spell checking and correction techniques for Indic languages.

Copied to clipboard

Andrei Manolache, Florin Brad, Elena Burceanu

Graph-Induced Syntactic-Semantic Spaces in Transformer-Based Variational AutoEncoders (2024.findings-naacl)

Challenge:	Recent deep learning methods for anomalies in images learn better features of normality in an end-to-end self-supervised setting.
Approach:	They propose to use a novel pretext task to learn a deep learning model for Anomaly Detection in text to train a model to discriminate between different transformations applied to visual data.
Outcome:	The proposed method outperforms state-of-the-art methods on 20Newsgroups and AG News datasets in the semi-supervised setting and in the unsupervised setting.

Copied to clipboard

Yingji Zhang, Marco Valentino, Danilo Carvalho, Ian Pratt-Hartmann, Andre Freitas

AMuSE-WSD: An All-in-one Multilingual System for Easy Word Sense Disambiguation (2021.emnlp-demo)

Challenge:	Existing studies on syntactic injection in Variational AutoEncoders (VAEs) are limited to LSTM-based VAEs.
Approach:	They propose to use latent space separation techniques to inject syntactic information into Variational AutoEncoders (VAEs) using graph-based models.
Outcome:	The proposed end-to-end VAE architecture can improve the organisation of the latent space, alleviating the information loss occurring in standard VAE setups, and resulting in enhanced performances on language modelling and downstream generation tasks.

Copied to clipboard

Riccardo Orlando, Simone Conia, Fabrizio Brignone, Francesco Cecconi, Roberto Navigli

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

Challenge:	Word Sense Disambiguation (WSD) is a task of associating a word in context with its most appropriate sense from a predefined sense inventory.
Approach:	They propose to use a state-of-the-art neural model to integrate WSD into real-world applications.
Outcome:	The proposed system offers high-quality sense information in 40 languages through a state-of-the-art neural model for WSD.

Copied to clipboard

Rujun Han, Qiang Ning, Nanyun Peng

On the Use of External Data for Spoken Named Entity Recognition (2022.naacl-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

Ankita Pasad, Felix Wu, Suwon Shon, Karen Livescu, Kyu Han

Speech & Audio in NLP

Challenge:	Named entity recognition (NER) tasks require large labeled datasets to perform . compared to prior work, relative improvements in F1 of up to 16% are found .
Approach:	They propose to use self-training, knowledge distillation, and transfer learning to learn SLU models . they compare pipeline and pipeline approaches to find out how to use external data .
Outcome:	The proposed models improve performance beyond pre-trained models in resource-constrained settings . the best baseline model is a pipeline approach, while the best performance is achieved by an E2E model.

Sentence-Level Content Planning and Style Specification for Neural Text Generation (D19-1)

Copied to clipboard

Xinyu Hua, Lu Wang

GraSAME: Injecting Token-Level Structural Information to Pretrained Language Models via Graph-guided Self-Attention Mechanism (2024.findings-naacl)

Challenge:	Recent advances in text generation systems often produce incoherent and unfaithful outputs . a novel automated text generation system takes into account content selection, text planning, and surface realization.
Approach:	They propose an end-to-end trained two-step text generation model that considers sentence-level content planners and language styles.
Outcome:	The proposed model outperforms competing models in three domains with diverse topics and varying language styles.

Copied to clipboard

Shuzhou Yuan, Michael Färber

End-to-End Speech to Intent Prediction to improve E-commerce Customer Support Voicebot in Hindi and English (2022.emnlp-industry)

Challenge:	Pretrained Language Models (PLMs) benefit from external knowledge stored in graph structures for various downstream tasks.
Approach:	They propose a graph-guided self-attention mechanism that integrates token-level structural information into PLMs without additional alignment or concatenation efforts.
Outcome:	The proposed model outperforms baseline models and achieves comparable results to state-of-the-art models on WebNLG datasets.

Copied to clipboard

Abhinav Goyal, Anupam Singh, Nikesh Garera

GRAM: Fast Fine-tuning of Pre-trained Language Models for Content-based Collaborative Filtering (2022.naacl-main)

Challenge:	Experimental results show that an E2E S2I model outperforms a conventional pipeline by 27% on the F1 score . multi-component pipelines require large annotated datasets, have higher latency, and have complex deployment.
Approach:	They propose an end-to-end (E2E) S2I model that uses pre-trained automatic speech recognition with slight modification and fine-tuning on small annotated datasets.
Outcome:	The proposed model outperforms a conventional pipeline on an annotated dataset by 27% on the F1 score.

Copied to clipboard

Yoonseok Yang, Kyu Seok Kim, Minsam Kim, Juneyoung Park

DIRECT: Directional Relevance in Conversational Trajectories (2026.eacl-industry)

Challenge:	Content-based collaborative filtering (CF) predicts user-item interactions based on both items’ interaction history and item content information.
Approach:	They propose to combine item encodings with a multi-modality approach to improve training efficiency by 146x .
Outcome:	The proposed model improves training efficiency (up to 146x) on five datasets from two task domains of Knowledge Tracing and News Recommendation.

Copied to clipboard

Anshuman Mourya, Rajdeep Mukherjee, Prerna Jolly, Vinayak S Puranik, Sivaramakrishnan R Kaveri

Unifying Streaming and Non-streaming Zipformer-based ASR (2025.acl-industry)

Challenge:	Conversational Agents (Agents) often fail to understand how to start a conversation or what to ask next . a novel approach to recommending highly relevant follow-up question suggestions is proposed .
Approach:	They propose a method to recommend highly relevant follow-up question suggestions . they use offline QBs to fetch the most-relevant candidate questions .
Outcome:	The proposed system produces a ranked list of highly relevant follow-up question recommendations within 1 sec.

Copied to clipboard

Bidisha Sharma, Karthik Pandia D S, Shankar Venkatesan, Jeena J Prakash, Shashi Kumar, Malolan Chetlur, Andreas Stolcke

Semi-Supervised Semantic Role Labeling with Cross-View Training (D19-1)

Challenge:	Existing frameworks for streaming and non-streaming ASR models have been used to reduce development, training and deployment costs.
Approach:	They propose to use dynamic right-context through chunked attention masking to train zipformer-based ASR models.
Outcome:	The proposed framework reduces word error by relative 7.9% with a small degradation in user-perceived latency.

Copied to clipboard

Rui Cai, Mirella Lapata

Responsible & Trustworthy NLP

Challenge:	Recent approaches rely on expensive annotations and are unavailable in low resource scenarios (e.g., rare languages or domains).
Approach:	They propose an end-to-end SRL model which leverages unlabeled data and propose to reduce the annotation effort involved via semi-supervised learning.
Outcome:	The proposed model outperforms the state-of-the-art in English and consistently improves performance in other languages, including Chinese, German, and Spanish.

Leveraging End-to-End ASR for Endangered Language Documentation: An Empirical Study on Yolóxochitl Mixtec (2021.eacl-main)

Copied to clipboard

Jiatong Shi, Jonathan D. Amith, Rey Castillo García, Esteban Guadalupe Sierra, Kevin Duh, Shinji Watanabe

Robust Question Answering Through Sub-part Alignment (2021.naacl-main)

Challenge:	End-to-end ASR systems that eschew linguistic resources but are more dependent on large-data settings are suggested as a solution to EL documentation bottlenecks.
Approach:	They propose to build an end-to-end ASR system that is reproducible by the ASR community and propose a novice transcription correction task.
Outcome:	The proposed method would mitigate bottlenecks and shortages in transcribers . it is based on a Yoloxóchitl Mixtec corpus and is reproducible by the ASR community.

Copied to clipboard

Jifan Chen, Greg Durrett

Robustness in NLP

Challenge:	Current textual question answering models fail to generalize to out-of-domain settings.
Approach:	They propose to decompose question and context into smaller units and align them to find the answer.
Outcome:	The proposed model is more robust than the standard BERT QA model on adversarial and out-of-domain datasets.

Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning (2025.emnlp-industry)

Copied to clipboard

Zhiwei Li, Yong Hu, Wenqing Wang

Challenge:	Currently, the dominant end-to-end reinforcement learning paradigm for agents in Large Language Models (LLMs) employs multi-objective optimization that jointly trains both planning and answer summarization capabilities.
Approach:	They propose a framework that decouples the training process to enable a focused, single-objective optimization of the planning module.
Outcome:	The proposed framework achieves an 8%–12% improvement in planning performance compared to end-to-end baselines.

Improving Formality Style Transfer with Context-Aware Rule Injection (2021.acl-long)

Copied to clipboard

Zonghai Yao, Hong Yu

Text Classification

Challenge:	Existing language models pre-trained on large-scale corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text.
Approach:	They propose a method for formality style transfer by injecting multiple rules into an end-to-end BERT-based encoder and decoder model.
Outcome:	The proposed method outperforms existing rule-based FST approaches on tweet sentiment analysis tasks.

Exploring the Potential of Large Language Models in Computational Argumentation (2024.acl-long)

Copied to clipboard

Guizhen Chen, Liying Cheng, Anh Tuan Luu, Lidong Bing

EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition (2022.findings-acl)

Challenge:	Argumentation is an essential tool in various domains, including law, public policy, and artificial intelligence.
Approach:	They propose to evaluate LLMs on various computational argumentation tasks . they organize existing tasks into six main categories and standardize the format of 14 datasets .
Outcome:	The proposed model performs well on argument mining and argument generation tasks.

Copied to clipboard

Zaijing Li, Fengxiao Tang, Ming Zhao, Yusen Zhu

Dialogue Systems & Conversational Agents

Challenge:	Existing studies on ERC focus on context modeling but ignore representation of contextual emotional tendency.
Approach:	They propose to use Emoformer to extract multi-modal emotion vectors from different modalities and fuse them with sentence vector to be an emotion capsule.
Outcome:	The proposed model outperforms the state-of-the-art models on two benchmark datasets.

RAPIDS: Resume Attack Prompt Injection Detection at Scale (2026.acl-industry)

Copied to clipboard

Yohann Augey, Joshua H. Levy, Arda Akdemir

Responsible & Trustworthy NLP

Challenge:	Existing generic prompt injection detectors lack domain specificity needed for nuanced resume attacks.
Approach:	They propose a scalable detection framework that uses a synthetically generated dataset to address data scarcity in this domain.
Outcome:	The proposed framework outperforms the best off-the-shelf detector by over 50% in relative F1 and approaches frontier LLM accuracy.

An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking (P18-1)

Copied to clipboard

Puyang Xu, Qi Hu

Dialogue Systems & Conversational Agents

Challenge:	a dialogue state tracker is a core component in most of today's spoken dialogue systems . slot-filling dialogues are composed of a predefined set of slots that need to be filled through the conversation .
Approach:	They propose an E2E architecture that extracts unknown slot values while still achieving state-of-the-art accuracy on the standard DSTC2 benchmark.
Outcome:	The proposed architecture achieves state-of-the-art accuracy on the DSTC2 benchmark while retaining predefined slot values.

A Unified Span-Based Approach for Opinion Mining with Syntactic Constituents (2021.naacl-main)

Copied to clipboard

Qingrong Xia, Bo Zhang, Rui Wang, Zhenghua Li, Yue Zhang, Fei Huang, Luo Si, Min Zhang

Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer (2022.emnlp-main)

Challenge:	Existing methods for fine-grained opinion mining (OM) are based on span-based annotations, but they are not effective.
Approach:	They propose a unified span-based approach for the end-to-end OM setting using syntactic constituents and multi-task learning to integrate them into the proposed model.
Outcome:	The proposed approach achieves significant improvements over previous work on the MPQA 2.0 dataset and reduces the number of wrongly-predicted opinion expressions and roles.

Copied to clipboard

Zhengbao Jiang, Luyu Gao, Zhiruo Wang, Jun Araki, Haibo Ding, Jamie Callan, Graham Neubig

Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment (2021.naacl-main)

Challenge:	eschewing separate architecture and training for knowledge-intensive tasks is cumbersome . end-to-end training only based on supervision from the end task is awkward .
Approach:	They propose a single Transformer that performs retrieval as attention and end-to-end training solely based on supervision from the end QA task.
Outcome:	The proposed model outperforms state-of-the-art retrievers and readers on in-domain datasets.

Copied to clipboard

Ethan A. Chi, Julian Salazar, Katrin Kirchhoff

Analyzing Modular Approaches for Visual Question Decomposition (2023.emnlp-main)

Challenge:	Non-autoregressive encoder-decoder models improve decoding speed, but generation quality suffers . editing at the level of output sequences limits model flexibility.
Approach:	They propose iterative realignment which iteratively realigns connectionist temporal alignments.
Outcome:	The proposed model matches an autoregressive baseline with a 14x speedup on the WSJ dataset; on LibriSpeech, it achieves an LM-free test-other WER of 9.0% (19% relative improvement on comparable work).

Copied to clipboard

Apoorv Khandelwal, Ellie Pavlick, Chen Sun

BIOPSY - Biomarkers In Oncology: Pipeline for Structured Yielding (2025.emnlp-industry)

Challenge:	Modular neural networks without additional training have been shown to surpass end-to-end neural networks on challenging vision–language tasks.
Approach:	They propose to use BLIP-2-based modular neural networks without additional training to build programs and a number of skill-specific, task-oriented modules to execute them.
Outcome:	The proposed methods outperform end-to-end neural networks on vision language tasks and retain performance when they use task-agnostic selections.

Copied to clipboard

Sanya A. Chetwani, Jaseem Mahmmdla

Controllable Sentence Simplification via Operation Classification (2022.findings-naacl)

Challenge:	Biomarkers are crucial indicators for early cancer detection and prognosis, but extracting biomarkers from clinical texts remains a challenge.
Approach:	They propose a pipeline that integrates a domain-adapted biomarker entity recognition model and a relation extraction model to link biomarkers to their respective mutations.
Outcome:	The proposed pipeline achieves an F1 score of 0.86 for oncology and 0.87 for neuroscience domains on 5,000 clinical texts.

Copied to clipboard

Liam Cripwell, Joël Legrand, Claire Gardent

<SYNTACT>: Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates (2025.emnlp-industry)

Challenge:	Sentence simplification involves a sentence being transformed into a simpler version of itself while preserving its core meaning.
Approach:	They propose a controllable-simplification model that tailors simplifications to four global operations . they propose to use a dataset to train highly accurate classification systems for these operations based on syntactic or discourse structure .
Outcome:	The proposed model outperforms both end-to-end and controllable approaches in sentence simplification tasks.

Copied to clipboard

Sachin Kumar Giroh, Pushpendu Ghosh, Aryan Jain, Harshal Giridhari Paunikar, Aditi Rastogi, Promod Yenigalla, Anish Nediyanchath

Challenge:	Unstructured and ambiguous Standard Operating Procedures suffer from ambiguity, missing information, and inconsistency, all of which hinder automation.
Approach:	They propose a three-stage LLM framework that transforms unstructured SOPs into a structured plan and an executable code template.
Outcome:	The proposed framework shows an 88.4% accuracy and significant reduction in inconsistency on real-world SOPs and synthetic variants.

End-to-End Construction of NLP Knowledge Graph (2021.findings-acl)

Copied to clipboard

Ishani Mondal, Yufang Hou, Charles Jochim

Knowledge Representation

Challenge:	a new schema for NLP knowledge about tasks, datasets and metrics is proposed.
Approach:	They propose a new schema that represents knowledge about tasks, datasets and metrics in the NLP domain.
Outcome:	The proposed framework can be automatically built into scientific leaderboards . the proposed system achieves reasonable results for all relation types on this small-scale graph .

Benchmarking the Simplification of Dutch Municipal Text (2024.lrec-main)

Copied to clipboard

Daniel Vlantis, Iva Gornishka, Shuai Wang

Beyond Sentence-Level End-to-End Speech Translation: Context Helps (2021.acl-long)

Challenge:	Text simplification (TS) is a technique that makes written information more accessible to all people, especially those with cognitive or language impairments.
Approach:	They propose to use English as a pivot language for simplification of Dutch medical and municipal texts.
Outcome:	The proposed approach improves on Dutch medical text, while the existing pipeline performs better on all metrics.

Copied to clipboard

Biao Zhang, Ivan Titov, Barry Haddow, Rico Sennrich

Machine Translation

Challenge:	Document-level contextual information has shown benefits to text-based machine translation, but whether and how it helps end-to-end speech translation is still under-studied.
Approach:	They propose a concatenation-based ST model with adaptive feature selection for computational efficiency.
Outcome:	The proposed model improves translation quality and robustness to (artificial) audio segmentation errors.

Language Model-Driven Data Pruning Enables Efficient Active Learning (2026.findings-eacl)

Copied to clipboard

Abdul Hameed Azeemi, Ihsan Ayyub Qazi, Agha Ali Raza

Responsible & Trustworthy NLP

Challenge:	Existing data pruning methods for active learning are expensive and time-consuming.
Approach:	They propose a plug-and-play data pruning strategy that leverages language models to prune the unlabeled pool.
Outcome:	The proposed pruning strategy outperforms existing pruning methods on translation, sentiment analysis, topic classification, and summarization tasks on diverse datasets.

Syntax-guided Neural Module Distillation to Probe Compositionality in Sentence Embeddings (2023.eacl-main)

Copied to clipboard

Rohan Pandey

Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation (2026.acl-long)

Challenge:	Past work on sentence embedding models faces issues determining the causal impact of implicit syntax representations.
Approach:	They construct a neural module net based on a transformer model and train it end-to-end to approximate the sentence’s embedding.
Outcome:	The proposed model captures whether syntax is a strong model of its compositional ability.

Copied to clipboard

Yihang Li, Chenhui Chu

Challenge:	Current methods for evaluating meeting effectiveness rely on post-hoc surveys that yield a single coarse-grained score for an entire meeting.
Approach:	They propose a new paradigm for evaluating meeting effectiveness centered on novel criteria and temporal fine-grained approach . they introduce a meta-evaluation dataset containing 2,459 human-annotated segments from 130 AMI Corpus meetings.
Outcome:	The proposed framework can be used to evaluate meeting effectiveness across different meeting types and from business scenarios to unstructured discussions.

Adaptive Feature Selection for End-to-End Speech Translation (2020.findings-emnlp)

Copied to clipboard

Biao Zhang, Ivan Titov, Barry Haddow, Rico Sennrich

Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation (2025.findings-emnlp)

Challenge:	End-to-end speech translation (E2E) models that directly maps audio to a foreign text are not efficient.
Approach:	They propose adaptive feature selection (AFS) for encoder-decoder based E2E ST.
Outcome:	The proposed model outperforms the existing model on LibriSpeech En-Fr and MuST-C with a BLEU score of 18.56.

Copied to clipboard

Pengchao Feng, Ziyang Ma, Wenxi Chen, Yao Li, Sheng Wang, Kai Yu, Xie Chen

Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs (2024.acl-long)

Challenge:	End-to-end speech-to speech (S2S) dialogue systems face key challenges in incorporating external knowledge into their models.
Approach:	They propose a framework that directly retrieves relevant textual knowledge from speech queries.
Outcome:	The proposed framework improves the performance of end-to-end speech-tospeech dialogue systems while achieving higher retrieval efficiency.

Copied to clipboard

Jiejun Tan, Zhicheng Dou, Yutao Zhu, Peidong Guo, Kun Fang, Ji-Rong Wen

A Purely End-to-End System for Multi-speaker Speech Recognition (P18-1)

Challenge:	Existing methods to determine the knowledge an LLM already possesses and the knowledge that requires the help of a search engine are expensive and require excessive computational costs.
Approach:	They propose a slim proxy model that detects missing knowledge in LLMs with a proxy model and use it to perform retrieval for the missing knowledge.
Outcome:	The proposed approach detects missing knowledge in LLMs with a slim proxy model and takes its answers as heuristic answers.

Copied to clipboard

Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey

Logical Neural Networks for Knowledge Base Completion with Embeddings & Rules (2022.emnlp-main)

Challenge:	Existing methods for multi-speaker speech recognition require isolated source signals or senone alignments for effective learning.
Approach:	They propose a sequence-to-sequence framework to decode multiple label sequences from a single speech sequence by unifying source separation and speech recognition functions in an end-to end manner.
Outcome:	The proposed model improves on existing models by 83.1% relative to previous models with explicit separation and recognition modules.

Copied to clipboard

Prithviraj Sen, Breno William Carvalho, Ibrahim Abdelaziz, Pavan Kapanipathi, Salim Roukos, Alexander Gray

Knowledge-Driven Slot Constraints for Goal-Oriented Dialogue Systems (2021.naacl-main)

Challenge:	Knowledge base completion (KBC) is a human-interpretable dialect . rule-based KBC has a high quality but low accuracy .
Approach:	They propose to use logical neural networks to learn both kinds of rules in a common framework using gradient-based optimization.
Outcome:	The proposed method improves by 10% relative to SotA rule-based methods and by combining it with knowledge graph embeddings it achieves an additional 7.5% relative improvement.

Copied to clipboard

Piyawat Lertvittayakumjorn, Daniele Bonadiman, Saab Mansour

Zuchao Li, Jiaxun Cai, Shexia He, Hai Zhao

Challenge:	Traditional goal-oriented dialogue systems allow execution of validation rules as a post-processing step after slots have been filled which can lead to error accumulation.
Approach:	They propose a task of constraint violation detection based on knowledge-driven slot constraints . they propose methods to integrate external knowledge into the system and compare it to traditional rule-based pipeline approach .
Outcome:	The proposed task compares to the existing system and a rule-based pipeline.

Seq2seq Dependency Parsing (C18-1)

Copied to clipboard

The Interpreter Understands Your Meaning: End-to-end Spoken Language Understanding Aided by Speech Translation (2023.findings-emnlp)

Challenge:	Recent trend for dependency parsing is adopting neural networks due to their significant success in a wide range of applications.
Approach:	They propose a sequence to sequence (seq2seque) dependency parser that predicts the relative position of head for each word.
Outcome:	The proposed parser achieves 94.11% UAS on PTB and 88.78% UAS .

Copied to clipboard

Mutian He, Philip Garner

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

Challenge:	Modern artificial intelligence is characterized by large pretrained language models with strong language capabilities to be adapted to various downstream tasks.
Approach:	They propose to use the task of speech translation (ST) to pretrain speech models for end-to-end SLU on intra- and cross-lingual scenarios.
Outcome:	The proposed model achieves higher performance over baselines on monolingual and multilingual intent classification as well as spoken question answering using SLURP, MINDS-14, and NMSQA benchmarks.

Copied to clipboard

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

BERT-based Lexical Substitution (P19-1)

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

Wangchunshu Zhou, Tao Ge, Ke Xu, Furu Wei, Ming Zhou

CCIM: Cross-modal Cross-lingual Interactive Image Translation (2023.findings-emnlp)

Challenge:	Existing approaches to lexical substitution tend to overlook good substitute candidates that are not the synonyms of the target words in the lexicals and fail to take into account the substitution’s influence on the global context of the sentence.
Approach:	They propose an end-to-end BERT-based lexical substitution approach which proposes and validates substitute candidates without using annotated data or manually curated resources.
Outcome:	The proposed approach performs well in proposing and ranking substitute candidates, achieving the state-of-the-art results in both LS07 and LS14 benchmarks.

Copied to clipboard

Cong Ma, Yaping Zhang, Mei Tu, Yang Zhao, Yu Zhou, Chengqing Zong

How Accents Confound: Probing for Accent Information in End-to-End Speech Recognition Systems (2020.acl-main)

Challenge:	Existing research on text image machine translation (TIMT) lacks recognized source language information resulting in a decrease in translation performance.
Approach:	They propose a cross-modal cross-lingual interactive model which incorporates source language information by synchronizing source and target language results.
Outcome:	The proposed model outperforms end-to-end models and has faster decoding speed with smaller model size than cascade models.

Copied to clipboard

Archiki Prasad, Preethi Jyothi

CroCoSum: A Benchmark Dataset for Cross-Lingual Code-Switched Summarization (2024.lrec-main)

Challenge:	a new study examines how accent information is encoded and propagated in an end-to-end ASR system.
Approach:	They propose to use phone probes to analyze phonetic content of representations at each layer.
Outcome:	The proposed model is based on a large amount of US-accented English speech and is compared with other models using phone probes.

Copied to clipboard

Ruochen Zhang, Carsten Eickhoff

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

Challenge:	Cross-lingual summarization (CLS) has attracted increasing interest due to the availability of large-scale web-mined datasets and the advancements of multilingual language models.
Approach:	They propose a dataset of cross-lingual code-switched summaries in Chinese and English . they show that leveraging existing CLS resources does not improve performance .
Outcome:	The proposed method does not improve on CroCoSum, indicating the limited generalizability of existing approaches.

Copied to clipboard

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

Beyond Common Words: Enhancing ASR Cross-Lingual Proper Noun Recognition Using Large Language Models (2024.findings-emnlp)

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

Rishabh Kumar, Sabyasachi Ghosh, Ganesh Ramakrishnan

Speech & Audio in NLP

Challenge:	In this work, we address the challenge of cross-lingual proper noun recognition in automatic speech recognition systems where proper nodes in an utterance may originate from a language different from the language in which the ASR system is trained.
Approach:	They propose a dictionary-based method to correct ASR predictions in a large language model .
Outcome:	The proposed method significantly reduces word error rates across cross-lingual proper noun recognition tasks involving three secondary languages.

Document Segmentation Matters for Retrieval-Augmented Generation (2025.findings-acl)

Copied to clipboard

Zhitong Wang, Cheng Gao, Chaojun Xiao, Yufei Huang, Shuzheng Si, Kangyang Luo, Yuzhuo Bai, Wenhao Li, Tangjian Duan, Chuancheng Lv, Guoshan Lu, Gang Chen, Fanchao Qi, Maosong Sun

OIE@OIA: an Adaptable and Efficient Open Information Extraction Framework (2022.acl-long)

Challenge:	Existing rule-based chunking methods lead to suboptimal splits, where overly large chunks introduce irrelevant information and small chunks lack semantic coherence.
Approach:	They propose a method that leverages document summaries as pseudo-instructions to guide chunking by computing semantic similarity between sentences and the summary.
Outcome:	Experiments on multiple open-domain question-answering benchmarks show that PIC significantly improves retrieval accuracy (Hits@k) and end-to-end QA performance (Exact Match) without any additional training.

Copied to clipboard

Xin Wang, Minlong Peng, Mingming Sun, Ping Li

Cogito: A Cognitive Agentic Framework Driven by Dynamic Graph of Thoughts for Financial Report Generation (2026.findings-acl)

Challenge:	Different Open Information Extraction (OIE) tasks require different types of information.
Approach:	They propose to adapt an OIE Graph to different OIE tasks with simple rules . they implement an end-to-end OIA generator and make it open-accessible .
Outcome:	The proposed system achieves new SOTA performance on three popular OIE tasks.

Copied to clipboard

Chen Lifan, Wei Ding, Jingwen Yang, Xiuze Zhou, Jingan Chen, Fan Lin

Biomedical Event Extraction as Sequence Labeling (2020.emnlp-main)

Challenge:	Existing approaches to financial report generation are insufficient to handle dynamic uncertainties of real-world financial environments.
Approach:	They propose a cognitively grounded agentic framework for professional financial report generation that is driven by Dynamic Graph of Thoughts and a social collaboration mechanism to facilitate coordinated agent interaction.
Outcome:	The proposed framework is based on a dynamic reasoning model and social collaboration mechanism.

Copied to clipboard

Alan Ramponi, Rob van der Goot, Rosario Lombardo, Barbara Plank

DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog (2023.findings-emnlp)

Challenge:	Empirical results show that BeeSL’s speed and accuracy makes it a viable approach for large-scale real-world scenarios.
Approach:	They propose a joint end-to-end neural information extraction model that recasts the task as sequence labeling and jointly models intermediate tasks via multi-task learning.
Outcome:	Empirical results show that BeeSL outperforms the current best system on the Genia 2011 benchmark by 1.57% absolute F1 score reaching 60.22% F1 .

Copied to clipboard

Xin Zheng, Tianyu Liu, Haoran Meng, Xu Wang, Yufan Jiang, Mengliang Rao, Binghuai Lin, Yunbo Cao, Zhifang Sui

Bottom-Up Abstractive Summarization (D18-1)

Challenge:	Existing work on question-answer extraction fails to integrate incomplete utterances from dialog context for composite QA retrieval.
Approach:	They propose a task where questions and corresponding answers might be separated across different utterances.
Outcome:	The proposed methods perform well on 5 customer service datasets and set a benchmark for N-to-N DialogQAE with utterance and session level evaluation metrics.

Copied to clipboard

Sebastian Gehrmann, Yuntian Deng, Alexander Rush

Accented Speech Recognition With Accent-specific Codebooks (2023.emnlp-main)

Challenge:	Existing approaches to summarize text using end-to-end content selectors have had mixed success in content selection, for example copying full sentences from the source document.
Approach:	They propose to use content selectors to over-determine phrases in a source document that should be part of the summary.
Outcome:	The proposed model over-determines phrases in a source document that should be part of the summary while generating fluent summaries.

Copied to clipboard

Darshan Prabhu, Preethi Jyothi, Sriram Ganapathy, Vinit Unni

PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization (2025.naacl-long)

Challenge:	Degradation in performance across underrepresented accents is a severe deterrent to inclusive adoption of ASR.
Approach:	They propose an approach to adapt speech accents to unseen accents by using cross-attention with a trainable set of codebooks.
Outcome:	The proposed approach yields significant performance gains on the seen English accents and unseen accents on the Mozilla Common Voice dataset.

Copied to clipboard

Jiayi Wu, Hengyi Cai, Lingyong Yan, Hao Sun, Xiang Li, Shuaiqiang Wang, Dawei Yin, Ming Gao

MT3: A Synergistic Multi-Task RL Framework for Specializing MLLMs in Text Image Machine Translation (2026.acl-long)

Challenge:	Existing approaches to optimize RAG generators fail to align with RAG requirements thoroughly.
Approach:	They propose a method for optimizing the RAG generator from multiple preference perspectives to align with RAG requirements comprehensively.
Outcome:	The proposed method improves the performance of RAG generators by incorporating retrieved documents into the prompt.

Copied to clipboard

Zhaopeng Feng, Yupu Liang, Shaosheng Cao, Jiayuan Su, Jiahan Ren, Zhijie Zhou, Wenxuan Huang, Jian Wu, Zuozhu Liu

EFTNAS: Searching for Efficient Language Models in First-Order Weight-Reordered Super-Networks (2024.lrec-main)

Challenge:	Text Image Machine Translation (TIMT) is a critical subfield of machine translation . it requires accurate optical character recognition, robust visual-text reasoning, and high-quality translation a challenge .
Approach:	They propose a multi-task optimization framework to specialize MLLMs into expert TIMT models.
Outcome:	The proposed model outperforms baselines on the latest in-domain MIT-10M benchmark.

Copied to clipboard

Juan Pablo Munoz, Yi Zheng, Nilesh Jain

ClidSum: A Benchmark Dataset for Cross-Lingual Dialogue Summarization (2022.emnlp-main)

Challenge:	Depending on the size of transformer-based models, they can be restricted from deployment in resource-constrained environments.
Approach:	They propose to combine neural architecture search and network pruning techniques to generate and train weight-sharing super-networks that contain efficient transformer-based models.
Outcome:	The proposed model achieves high-performing, high-performance subnetworks on the general language understanding evaluation and the Stanford Question Answering Dataset.

Copied to clipboard

Jiaan Wang, Fandong Meng, Ziyao Lu, Duo Zheng, Zhixu Li, Jianfeng Qu, Jie Zhou

Recovering Missing Characters in Old Hawaiian Writing (D18-1)

Challenge:	Existing approaches to building cross-lingual summarization systems on dialogue documents are limited.
Approach:	They propose a benchmark dataset for building cross-lingual summarization systems on dialogue documents.
Outcome:	The proposed model outperforms pipeline models on ClidSum and mDialBART.

Copied to clipboard

Brendan Shillingford, Oiwi Parker Jones

Challenge:	Modern Hawaiian orthography includes characters for long vowels and glottal stops . manual transliteration is laborious when performed manually .
Approach:	They propose two methods to help transliterate Hawaiian between older and newer texts automatically using finite state transducers and a recurrent neural network language model.
Outcome:	The proposed method solves the transliteration problem automatically using finite state transducers and a neural network language model.

Ensembles of Hybrid and End-to-End Speech Recognition. (2024.lrec-main)

Copied to clipboard

Aditya Kamlesh Parikh, Louis ten Bosch, Henk van den Heuvel

A Graph-Based Method for Unsupervised Knowledge Discovery from Financial Texts (2022.lrec-1)

Challenge:	Existing methods to combine hybrid and end-to-end ASRs with confidence measures are limited and neither can achieve optimal performance.
Approach:	They propose to combine the hybrid Kaldi-based Automatic Speech Recognition system with the end-to-end wav2vec 2.0 XLS-R ASR using confidence measures.
Outcome:	The proposed method reduces the word error rate by 14% on the primary test set and 20% on other noisy and imbalanced data.

Copied to clipboard

Joel Oksanen, Abhilash Majumder, Kumar Saunack, Francesca Toni, Arun Dhondiyal

Structured Data in NLP

Challenge:	A financial analyst's work involves manually reviewing lengthy filings and financial news articles in order to extract relevant pieces of information.
Approach:	They propose an end-to-end, fully unsupervised method for knowledge discovery from financial texts that integrates existing resources to construct a knowledge graph of companies and related entities.
Outcome:	The proposed method calculates the environmental rating for companies in the S&P 500 based on company filings with the SEC and provides an independent assessment of its outputs with an independent MSCI source.

Analyzing and Improving Coherence of Large Language Models in Question Answering (2025.naacl-long)

Copied to clipboard

Ivano Lauriola, Stefano Campese, Alessandro Moschitti

MultiMed-ST: Large-scale Many-to-many Multilingual Medical Speech Translation (2025.emnlp-main)

Challenge:	Large language models suffer from instability or lack of coherence when receiving diverse input variations.
Approach:	They analyze the behavior of large language models when dealing with multiple lexical variations of the same info-seeking questions.
Outcome:	The proposed model generates equivalent outputs when receiving diverse input variations.

Copied to clipboard

Khai Le-Duc, Tuyen Tran, Bach Phan Tat, Nguyen Kim Hai Bui, Quan Dang Anh, Hung-Phong Tran, Thanh Thuy Nguyen, Ly Nguyen, Tuan Minh Phan, Thi Thu Phuong Tran, Chris Ngo, Khanh Xuan Nguyen, Thanh Nguyen-Tang

DePlot: One-shot visual language reasoning by plot-to-table translation (2023.findings-acl)

Challenge:	Multilingual speech translation (ST) and machine translation (MT) in the medical domain enhances patient care by enabling efficient communication across language barriers.
Approach:	They present a large-scale ST dataset for the medical domain spanning all translation directions in Vietnamese, English, German, French, and Simplified/Traditional Chinese, together with the models.
Outcome:	The multi-language speech translation (ST) and machine translation (MT) in the medical domain is the largest medical MT dataset and the largest many-to-many multilingual ST among all domains.

Copied to clipboard

Fangyu Liu, Julian Eisenschlos, Francesco Piccinno, Syrine Krichene, Chenxi Pang, Kenton Lee, Mandar Joshi, Wenhu Chen, Nigel Collier, Yasemin Altun

Discourse Structure-Aware Prefix for Generation-Based End-to-End Argumentation Mining (2024.findings-acl)

Challenge:	Existing models for visual language reasoning require tens of thousands of training examples and their reasoning capabilities are limited.
Approach:	They propose a one-shot solution to visual language reasoning by combining plot-to-text translation and reasoning over the translated text into a modality conversion module.
Outcome:	The proposed method improves on human-written queries on plots and charts compared with a fine-tuned SOTA model on human queries.

Copied to clipboard

Yang Sun, Guanrong Chen, Caihua Yang, Jianzhu Bao, Bin Liang, Xi Zeng, Min Yang, Ruifeng Xu

PRIM: Towards Practical In-Image Multilingual Machine Translation (2025.emnlp-main)

Challenge:	Recent advances in AM models overlook the integration of supplementary discourse structure information, resulting in suboptimal outcomes.
Approach:	They propose a framework which generates discourse structure-aware prefixes for each layer of the generation model.
Outcome:	The proposed framework achieves state-of-the-art performance on two AM benchmarks.

Copied to clipboard

Yanzhi Tian, Zeming Liu, Zhengyang Liu, Chong Feng, Xin Li, Heyan Huang, Yuhang Guo

A Generative Model for End-to-End Argument Mining with Reconstructed Positional Encoding and Constrained Pointer Mechanism (2022.emnlp-main)

Challenge:	Current research on in-image machine translation focuses on synthetic data with simple background, single font, fixed text position, and bilingual translation.
Approach:	They propose an end-to-end model to handle the challenge of practical conditions in PRIM . they annotate a real-world one-line text image with complex background, fonts, diverse text positions .
Outcome:	The proposed model improves translation quality and visual effect compared to other models.

Copied to clipboard

Jianzhu Bao, Yuhang He, Yang Sun, Bin Liang, Jiachen Du, Bing Qin, Min Yang, Ruifeng Xu

A Joint Neural Model for Information Extraction with Global Features (2020.acl-main)

Challenge:	Argument mining (AM) is a challenging task as it requires recognizing complex argumentation structures involving multiple subtasks.
Approach:	They propose a generative framework where expected outputs of AM are framed as a simple target sequence.
Outcome:	The proposed framework achieves state-of-the-art on two AM benchmarks.

Copied to clipboard

Ying Lin, Heng Ji, Fei Huang, Lingfei Wu

CHAMP: A Competition-level Dataset for Fine-Grained Analyses of LLMs’ Mathematical Reasoning Capabilities (2024.findings-acl)

Challenge:	Existing joint neural models for Information Extraction use local task-specific classifiers to predict labels for individual instances.
Approach:	They propose a joint neural framework that extracts the optimal IE result as a graph from an input sentence.
Outcome:	The proposed model achieves new state-of-the-art on all subtasks and does not use any language-specific feature.

Copied to clipboard

Yujun Mao, Yoon Kim, Yilun Zhou

Integrating Pre-Trained Speech and Language Models for End-to-End Speech Recognition (2024.findings-acl)

Challenge:	Recent large language models have shown indications of mathematical reasoning ability on competition-level problems.
Approach:	They propose a benchmark dataset to enable such analyses using large language models.
Outcome:	The proposed model performs better with concepts and hints than with the best model, but it is difficult to verify.

Copied to clipboard

Yukiya Hono, Koh Mitsuda, Tianyu Zhao, Kentaro Mitsui, Toshiaki Wakatsuki, Kei Sawada

To Adapt or to Annotate: Challenges and Interventions for Domain Adaptation in Open-Domain Question Answering (2023.acl-long)

Challenge:	Mainstream of automatic speech recognition (ASR) has shifted from pipeline methods to end-to-end (E2E) methods.
Approach:	They propose to integrate a pre-trained speech representation model and a large language model (LLM) for automatic speech recognition in an end-to-end manner.
Outcome:	The proposed model achieves comparable performance to modern E2E ASR models by utilizing powerful pre-training models with the proposed integrated approach.

Copied to clipboard

Dheeru Dua, Emma Strubell, Sameer Singh, Pat Verga

Low-Resource NLP

Challenge:	Recent advances in open-domain question answering have demonstrated impressive accuracy on general-purpose domains like Wikipedia.
Approach:	They propose a more realistic end-to-end domain shift evaluation setting covering five diverse domains to assess model adaption.
Outcome:	The proposed model improves by 24 points when adapted to unsupervised datasets.

ÌròyìnSpeech: A Multi-purpose Yorùbá Speech Corpus (2024.lrec-main)

Copied to clipboard

Tolulope Ogunremi, Kola Tubosun, Anuoluwapo Aremu, Iroro Orife, David Ifeoluwa Adelani

HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question Answering (2026.acl-long)

Challenge:	rynSpeech corpus is a dataset that can be used for both Text-to-Speecher (TTS) and Automatic Speech Recognition (ASR) speakers of many African languages have no access to voice-enabled applications in their native languages.
Approach:	They propose a dataset to collect Yorùbá speech data that can be used for both TTS and ASR tasks.
Outcome:	The proposed dataset can generate a good quality model with as little as 5 hours of speech . the results are consistent with previous studies on the Yorùbá language .

Copied to clipboard

Joongmin Shin, Gyuho Shim, Jeongbae Park, Jaehyung Seo, Heuiseok Lim

TextGenSHAP: Scalable Post-Hoc Explanations in Text Generation with Long Documents (2024.findings-acl)

Challenge:	Existing approaches to document-based Opendomain Question Answering (ODQA) use flat text chunks or page-level images to locate the correct document.
Approach:	They propose a hierarchical tree-based multimodal retrieval framework that elevates document hierarchy to a first-class retrieval signal.
Outcome:	The proposed framework outperforms page- and chunk-based baselines on ODQA benchmarks and improves retrieval recall by 12.9% and end-to-end QA performance by 6.8%.

Copied to clipboard

James Enouen, Hootan Nakhost, Sayna Ebrahimi, Sercan Arik, Yan Liu, Tomas Pfister

Explainability & Interpretability in NLP

Challenge:	Large language models (LLMs) are difficult to explain and understand due to long input contexts and autoregressive output generation.
Approach:	They propose a post-hoc explanation method which incorporates LLM-specific techniques.
Outcome:	The proposed method improves retrieval recall and prediction accuracy significantly on open-domain question answering benchmarks.

Less than One-shot: Named Entity Recognition via Extremely Weak Supervision (2023.findings-emnlp)

Copied to clipboard

Letian Peng, Zihan Wang, Jingbo Shang

Open Information Extraction via Chunks (2023.emnlp-main)

Challenge:	Named entity recognition (NER) problem is performed under extremely weak supervision . XWS setting is considered weaker than 1-shot since example entity is given in context-free way .
Approach:	They propose a method that uses extremely weak supervision to train named entity recognition models.
Outcome:	The proposed method outperforms the state-of-the-art few-shot methods with 1-shot supervision and ChatGPT annotations significantly.

Copied to clipboard

Kuicai Dong, Aixin Sun, Jung-jae Kim, Xiaoli Li

We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning? (2025.acl-long)

Challenge:	Existing OIE systems split a sentence into tokens and recognize token spans as tuple relations and arguments.
Approach:	They propose to split a sentence into tokens and recognize token spans as tuple relations and arguments.
Outcome:	The proposed model achieves state-of-the-art on multiple OIE datasets showing that SaC has better properties than sentence as token sequence.

Copied to clipboard

Runqi Qiao, Qiuna Tan, Guanting Dong, MinhuiWu MinhuiWu, Chong Sun, Xiaoshuai Song, Jiapeng Wang, Zhuoma GongQue, Shanglin Lei, YiFan Zhang, Zhe Wei, Miaoxuan Zhang, Runfeng Qiao, Xiao Zong, Yida Xu, Peiqing Yang, Zhimin Bao, Muxi Diao, Chen Li, Honggang Zhang

Seg2Act: Global Context-aware Action Generation for Document Logical Structuring (2024.emnlp-main)

Challenge:	Existing benchmarks focus more on end-to-end performance, but neglect the underlying principles of knowledge acquisition and generalization.
Approach:	They propose a benchmark specifically designed to explore the problem-solving principles by decomposing 6.5K visual math problems into 10.9K step-level questions for evaluation.
Outcome:	The proposed benchmark covers 6.5K visual math problems and 10.9K step-level questions spanning 5 layers of knowledge granularity and 67 hierarchical knowledge concepts.

Copied to clipboard

Zichao Li, Shaojie He, Meng Liao, Xuanang Chen, Yaojie Lu, Hongyu Lin, Yanxiong Lu, Xianpei Han, Le Sun

Challenge:	Document logical structuring is crucial for document intelligence due to the complexity of text segment dependencies in the document.
Approach:	They propose an end-to-end, generation-based method for document logical structuring that generates the action sequence via a global context-aware generative model and updates its global context and current logical structure based on the generated actions.
Outcome:	Experiments on ChCatExt and HierDoc datasets show that Seg2Act performs better than previous methods in both supervised and transfer learning settings.

AnyTOD: A Programmable Task-Oriented Dialog System (2023.emnlp-main)

Copied to clipboard

Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, Yonghui Wu

Reinforced IR: A Self-Boosting Framework For Domain-Adapted Information Retrieval (2025.acl-long)

Challenge:	a neuro-symbolic approach allows zero-shot adaptation to unseen tasks and domains . a neural LM keeps track of events that occur during a conversation and a symbolic program implements dialog policy is executed to recommend actions.
Approach:	They propose an end-to-end, zero-shot task-oriented dialog system . it is designed to adapt to unseen tasks or domains without prior training .
Outcome:	The proposed system can be programmed to adapt to unseen tasks without training . it reduces data collection and training requirements for enabling new TOD 1 16189 tasks .

Copied to clipboard

Chaofan Li, Jianlyu Chen, Yingxia Shao, Chaozhuo Li, Quanqing Xu, Defu Lian, Zheng Liu

Not All Terms Matter: Recall-Oriented Adaptive Learning for PLM-aided Query Expansion in Open-Domain Question Answering (2025.acl-long)

Challenge:	Existing retrieval methods struggle with highly specialized situations that require extensive domain expertise.
Approach:	They propose a method that integrates additional information from an LLM-based generator to enhance query performance and train the retriever to better discriminate the relevant documents identified by the generator.
Outcome:	The proposed method outperforms existing domain adaptation methods by a large margin and leads to substantial improvements in retrieval quality across a wide range of application scenarios.

Copied to clipboard

Xinran Chen, Ben He, Xuanang Chen, Le Sun

Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems (2025.findings-acl)

Challenge:	Open-domain question answering (ODQA) systems typically adopt a retriever-reader architecture, where the retriever finds relevant documents, and the reader extracts or synthesizes answers.
Approach:	They propose a method that iteratively adjusts the importance weights of QE terms based on their relevance, refining term distinction and enhancing the separation of relevant terms.
Outcome:	The proposed method improves retrieval accuracy and overall performance on four ODQA datasets and five QE methods.

Copied to clipboard

Yucheng Cai, Ke Li, Yi Huang, Junlan Feng, Zhijian Ou

KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)

Challenge:	Existing knowledge retrieval methods fail to account for interrelationship between knowledge pieces . however, current methods fail in a situation where multiple knowledge pieces are relevant .
Approach:	They propose an energy-based retriever that directly models the candidate retrieval results as a whole instead of modeling the knowledge pieces separately.
Outcome:	The proposed retriever outperforms the baseline energy-based retriever in knowledge retrieval tasks.

Copied to clipboard

Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang

AnalystBench: Benchmarking professional long-form report generation with web-mined multimodal tasks (2026.findings-acl)

Challenge:	Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question .
Approach:	They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance .
Outcome:	The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered .

Copied to clipboard

Chau Minh Pham, Zichao Wang, Puneet Mathur, Alexa Siu, Akriti Jain, Aparna Garimella, Ananya B. Sai, Nedim Lipka, Mohit Iyyer, Varun Manjunatha

SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning (2026.acl-long)

Challenge:	Existing benchmarks decompose the end-to-end professional report generation into individual components.
Approach:	They propose a benchmarking tool that evaluates 20 real-world professional report generation tasks grounded in multimodal document collections.
Outcome:	The proposed model outperforms closed-source models on executive summarization tasks but drops significantly on long-horizon synthesis tasks.

Copied to clipboard

Peidong Wang, Zhiming Ma, Xin Dai, YongKang Liu, Shi Feng, Xiaocui Yang, Wenxing Hu, Zhihao Wang, Mingjun Pan, Li Yuan, Daling Wang

LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real World (2025.findings-acl)

Challenge:	Existing methods for fraud detection rely on transcribed text, lacking acoustic cues . a proposed framework for audio-based slow-thinking fraud detection eliminates transcription errors .
Approach:	They propose a framework for audio-based slow-thinking fraud detection that eliminates transcription errors and rewards slow-thought reasoning by capturing fine-grained audio details.
Outcome:	The proposed method improves accuracy, inference efficiency, and real-time processing capabilities.

Copied to clipboard

Sina Semnani, Pingyue Zhang, Wanyue Zhai, Haozhuo Li, Ryan Beauchamp, Trey Billing, Katayoun Kishi, Manling Li, Monica Lam

It’s Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text Systems (2025.acl-long)

Challenge:	Using a partially reannotated subset of the Armed Conflict Location & Event Data, we analyze 39,786 conflict events across 20 languages and 171 countries.
Approach:	They propose a large-scale conflict event dataset with extensive coverage of region-specific entities.
Outcome:	The proposed method detects event arguments and entities through holistic document understanding and normalizes them across the multilingual dataset.

Copied to clipboard

Iuliia Zaitova, Badr M. Abdullah, Wei Xue, Dietrich Klakow, Bernd Möbius, Tania Avgustinova

Reasoning in a Combinatorial and Constrained World: Benchmarking LLMs on Natural-Language Combinatorial Optimization (2026.findings-acl)

Challenge:	idioms are defined as words with a figurative meaning not deducible from their individual components.
Approach:	They compare idiom translation as compared to conventional news translation in two languages . they compare MT and SLT systems with MT, Large Language Models and cascaded alternatives .
Outcome:	The proposed systems show better handling of idioms than standard news translation systems.

Copied to clipboard

Xia Jiang, Jing Chen, Cong Zhang, Jie Gao, Chengpeng Hu, Chenhao Zhang, Yaoxin Wu, Yingqian Zhang