Papers with realistic scenarios
End-to-End Evaluation for Low-Latency Simultaneous Speech Translation (2023.emnlp-demo)
Copied to clipboard
Christian Huber, Tu Anh Dinh, Carlos Mullov, Ngoc-Quan Pham, Thai Binh Nguyen, Fabian Retkowski, Stefan Constantin, Enes Ugan, Danni Liu, Zhaolin Li, Sai Koneru, Jan Niehues, Alexander Waibel
| Challenge: | a framework to evaluate low-latency speech translations is currently only limited to specific aspects and is not able to compare different approaches. |
| Approach: | They propose a framework to perform and evaluate low-latency speech translation in realistic conditions. |
| Outcome: | The proposed framework evaluates various aspects of low-latency speech translation under realistic conditions. |
Unknown Intent Detection Using Gaussian Mixture Model with an Application to Zero-shot Intent Classification (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for unknown intent detection are limited by prior knowledge of class labels. |
| Approach: | They propose to use a Gaussian mixture model to model utterance embeddings with a distribution and inject dynamic class semantic information into Gausssian means. |
| Outcome: | The proposed model performs well on three real task-oriented dialogue datasets in two languages. |
Cross-media User Profiling with Joint Textual and Social User Embedding (C18-1)
Copied to clipboard
| Challenge: | Empirical studies demonstrate the effectiveness of the proposed approach to cross-media user profiling tasks. |
| Approach: | They propose a uniform user embedding learning approach to address cross-media user profiling by bridging the knowledge between the source and target media. |
| Outcome: | Empirical results show that the proposed approach performs well on two cross-media user profiling tasks. |
Cross-lingual Continual Learning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing multi-lingual representations such as the one-hop transfer learning pipeline are difficult to adapt to new languages. |
| Approach: | They propose a cross-lingual continuum learning paradigm that evaluates continuous learning approaches that adapt to emerging data from different languages. |
| Outcome: | The proposed model can be used to adapt to new languages in a sequential manner. |
Joint Multilingual Supervision for Cross-lingual Entity Linking (D18-1)
Copied to clipboard
| Challenge: | Entity Linking (XEL) systems ground entity mentions written in any language to Wikipedia . XEL is challenging for most languages due to limited availability of resources as supervision . |
| Approach: | They develop a cross-lingual XEL approach that combines supervision from multiple languages jointly. |
| Outcome: | The proposed approach significantly improves on the current state-of-the-art in 8 languages. |
GenIE: Generative Information Extraction (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing approaches to open information extraction only work with unrealistically small numbers of entities and relations. |
| Approach: | They propose to use a transformer encoder-decoder model to extract triplets from unstructured text . they use 'generative information extraction' to generate triplet representations of information . |
| Outcome: | The proposed model is state-of-the-art on closed information extraction and generalizes from fewer training data points than baselines. |
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that visual encoders can induce harmful behavior in multimodal large language models. |
| Approach: | They propose a vision-centric jailbreak attack that uses visual information to create a jailbreak context. |
| Outcome: | The proposed attack outperforms baseline attacks on MM-SafetyBench and GPT-4o. |
Towards Better Hierarchical Text Classification with Data Generation (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to improve hierarchical text classification are expensive and lack high-quality labeled data. |
| Approach: | They propose a hierarchical text classification framework that can achieve both label controllability and text diversity by extracting high-quality hierarchic label information. |
| Outcome: | The proposed method can achieve label controllability and text diversity by extracting high-quality hierarchical label information. |
From Values to Opinions: Predicting Human Behaviors and Stances Using Value-Injected Large Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing large-scale surveys soliciting opinions on issues can be costly and laborious. |
| Approach: | They propose to use value-injected large language models to inject a target value distribution into large language model (LLM) and have them predict opinions and behaviors of people with similar values. |
| Outcome: | The proposed method significantly outperforms baseline methods on four tasks and the results suggest opinions and behaviors can be better predicted using value-injected LLMs. |
InteracSPARQL : An Interactive System for SPARQL Query Refinement Using Natural Language Explanations (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches for SPARQL generation rely on one-turn models. |
| Approach: | They propose a training-free interactive refinement pipeline that acts as a plug-and-play enhancement for existing SPARQL systems. |
| Outcome: | The proposed approach improves the accuracy of base models without fine-tuning . it transforms potentially flawed queries from any source into verifiable code . |
The Pitfalls of KV Cache Compression (2026.acl-long)
Copied to clipboard
| Challenge: | Recent literature has shown minimal degradation of KV cache in multi-instruction prompts . authors show that certain instructions degrade much more rapidly with compression . |
| Approach: | They propose to change KV cache eviction policies to reduce the impact of KV evict bias . they propose to use a 'simple' evviction policy to reduce ejection bias if the LLM is a multi-instruction model . |
| Outcome: | The proposed methods show that certain instructions degrade much faster with compression, causing them to be ignored by the LLM. |