Papers with in-depth
Unsupervised Term Extraction for Highly Technical Domains (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Term extraction is an important task for knowledge discovery platforms because domain specific terms are the linguistic representation of domainspecific concepts. |
| Approach: | They propose a term extraction subsystem that uses an unsupervised annotator to generate training data to fine-tune transformer models. |
| Outcome: | The proposed system can generalize across domains while reducing latency and inference time while preserving the high performance of the existing system. |
WikiVideo: Article Generation from Multiple Videos (2026.findings-acl)
Copied to clipboard
Alexander Martin, Reno Kriz, William Gantt Walden, Kate Sanders, Hannah Recknor, Eugene Yang, Francis Ferraro, Benjamin Van Durme
| Challenge: | Existing methods for retrieval-augmented generation focus on text rather than video. |
| Approach: | They propose a benchmark to generate Wikipedia-style articles from multiple videos . they propose 'collaborative article generation' that leverages an r1-style reasoning model and a VideoLLM to draw higher-level inferences about the target event than is possible with VideoLLms alone. |
| Outcome: | The proposed method outperforms existing methods in oracle retrieval and RAG settings while suggesting promising avenues for future work. |
Writing habits and telltale neighbors: analyzing clinical concept usage patterns with sublanguage embeddings (D19-62)
Copied to clipboard
| Challenge: | Existing biomedical concepts may have multiple, often non-compositional surface forms, making them difficult to analyze using lexical occurrence alone. |
| Approach: | They propose a method for characterizing usage patterns of clinical concepts among different document types by embedding concepts on clinical documents of different types and measuring their nearest neighborhood structures. |
| Outcome: | Experiments on the MIMIC-III corpus show that the proposed method captures clinically relevant differences in concept usage while correcting for noise in embedding learning. |
Approaches and Challenges for Resolving Different Representations of Fictional Characters for Chinese Novels (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing automatic text analysis tools and models are often developed for generic, open-domain tasks, restricting in-depth literary studies. |
| Approach: | They adapt a state-of-the-art anaphora resolution model to resolve character representations in Chinese novels by making some modifications and train a widely used BERT fine-tuned model for speaker extraction as assistance. |
| Outcome: | The proposed model is modified to resolve character representations in Chinese novels and train a BERT fine-tuned model for speaker extraction as assistance. |
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection (2022.findings-emnlp)
Copied to clipboard
Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao, Zhifang Sui
| Challenge: | DialogUSR is a plug-in and domain-agnostic module that empowers multi-intent detection for chatbots . a single user query triggers inquiries on highspeed train ticket price and weather of destination. |
| Approach: | They propose a dialog utterance splitting and reformulation task that splits multi-intent user query into multiple single-intention sub-queries and recovers all coreferred and omitted information in the sub-questions. |
| Outcome: | The proposed model can be used to split multi-intent user queries into multiple sub-queries . it can be trained in two stages and perform in-depth analyses on the proposed models . |
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalyst (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have demonstrated that inference-time scaling increases performance of Large Language Models (LLMs) in various reasoning tasks such as mathematics and complex question answering by increasing the length of Chain-of-Thought (CoT). |
| Approach: | They propose a model which synthesizes longer CoT data and iteratively improves performance through self-training by incorporating a few demonstration examples. |
| Outcome: | The proposed model achieves an average improvement of more than +2.5 points across five reasoning tasks: MMLU, GSM8K, ARC-C, HellaSwag, and BBH on two backbone models. |
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade (2024.naacl-long)
Copied to clipboard
Zefan Cai, Xin Zheng, Tianyu Liu, Haoran Meng, Jiaqi Han, Gang Yuan, Binghuai Lin, Baobao Chang, Yunbo Cao
| Challenge: | Existing models for natural language understanding are based on a well-defined intent 1 ontology. |
| Approach: | They propose to retrain the natural language understanding model as new data from real users are merged into existing data. |
| Outcome: | The proposed model shows that the semantically entangled intents can be recognized with an automatic workflow. |
Controllable Chest X-Ray Report Generation from Longitudinal Representations (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Radiology reports are detailed text descriptions of the content of medical scans. |
| Approach: | They propose a method to align, concatenate and fuse the current and prior visual information into a joint longitudinal representation which can be provided to a multimodal report generation model. |
| Outcome: | The proposed method achieves state-of-the-art results while enabling anatomy-wise controllable report generation. |
Retrieval-Augmented Few-shot Text Classification (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for retrieval-augmented text classification are successful in the few-shot scenario with limited retrieval space. |
| Approach: | They propose to use EM-L and R-L to provide task-specific guidance to retrieval metric . they also propose to incorporate retrieved memory alongside parameters for better generalization . |
| Outcome: | The proposed methods perform better on the few-shot scenario with limited retrieval space. |
Late Fusion with Triplet Margin Objective for Multimodal Ideology Prediction and Analysis (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior work on ideology prediction has focused on single modalities, i.e., text or images. |
| Approach: | They propose a task where a model predicts binary or five-point scale ideological leanings given a text-image pair with political content. |
| Outcome: | The proposed model outperforms the state-of-the-art model by almost 4% and a strong multimodal baseline with no pretraining by over 3%. |
Harnessing Large Language Models for Disaster Management: A Survey (2025.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, including their emerging role in mitigating threats to human life, infrastructure, and the environment during natural disasters. |
| Approach: | They propose a taxonomy that categorizes existing LLMs based on disaster phases and application scenarios to provide valuable insights for the research community and practitioners . |
| Outcome: | The proposed taxonomy categorizes existing LLMs based on disaster phases and application scenarios. |
CEASR: A Corpus for Evaluating Automatic Speech Recognition (2020.lrec-1)
Copied to clipboard
Malgorzata Anna Ulasik, Manuela Hürlimann, Fabian Germann, Esin Gedik, Fernando Benites, Mark Cieliebak
| Challenge: | Automatic Speech Recognition (ASR) systems are increasingly needed for research and practical applications. |
| Approach: | They propose to use public speech corpora to evaluate the quality of automatic speech recognition (ASR) they calculate an average Word Error Rate (WER) per corpus, per system and per corpor-system pair . |
| Outcome: | The proposed corpus evaluates the quality of automatic speech recognition systems using public speech corpora and transcripts generated by state-of-the-art systems. |
Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization (2025.findings-acl)
Copied to clipboard
| Challenge: | Multimodal Large Language Models (MLLMs) are known to hallucinate, which limits their practical applications. |
| Approach: | They propose a method that uses three types of preference pairs to target hallucinations from their diverse forms and causes. |
| Outcome: | The proposed method surpasses most state-of-the-art methods and shows potential for further improvements. |
CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors (2023.acl-long)
Copied to clipboard
| Challenge: | Large language models pre-trained on massive corpora have shown impressive few-shot learning ability on many NLP tasks. |
| Approach: | They propose to recast structured output in the form of code instead of natural language and use generative LLMs of code to perform IE tasks. |
| Outcome: | The proposed method outperforms fine-tuning moderate-size pre-trained models and prompting NL-LLMs under few-shot settings. |
MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing evaluation approaches focus on mLLMs’ detection accuracy for binary classification tasks, which often fail to reflect the in-depth interpretive nuance of harmfulness across diverse contexts. |
| Approach: | They propose an agent-based arena-style evaluation framework that provides context-aware and unbiased assessment for mLLMs’ understanding of multimodal harmfulness. |
| Outcome: | The proposed framework reduces evaluation biases of judge agents and provides unbiased comparisons of mLLMs’ abilities to interpret multimodal harmfulness. |
Vision-Flan: Scaling Human-Labeled Tasks in Visual Instruction Tuning (2024.findings-acl)
Copied to clipboard
Zhiyang Xu, Chao Feng, Rulin Shao, Trevor Ashby, Ying Shen, Di Jin, Yu Cheng, Qifan Wang, Lifu Huang
| Challenge: | Recent vision-language models (VLMs) have shown impressive capabilities as general visual assistants, but there are two challenges to their performance: (1) lacking task diversity in pretraining and visual instruction tuning; (2) annotation error and bias in GPT-4 synthesized instruction tuning data. |
| Approach: | They propose a two-stage instruction tuning framework that fine tunes VLMs firstly and further tuned on GPT-4 synthesized data. |
| Outcome: | The proposed framework outperforms the traditional single-stage visual instruction tuning framework and achieves state-of-the-art performance across a wide range of multi-modal evaluation benchmarks. |