Papers with text-based methods
Deja vu: Contrastive Historical Modeling with Prefix-tuning for Temporal Knowledge Graph Reasoning (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing text-based methods for Temporal Knowledge Graph Reasoning struggle to balance textual knowledge and temporal information with expensive purpose-built training strategies. |
| Approach: | They propose a Contrastive historical modeling framework with prefix-tuning for TEmporal Reasoning that feeds history-contextualized text into the pseudo-Siamese encoders to strike a textual-temporal balance. |
| Outcome: | The proposed framework achieves superior performance on four transductive and three few-shot inductive TKGR benchmarks. |
MatViX: Multimodal Information Extraction from Visually Rich Articles (2025.naacl-long)
Copied to clipboard
Ghazal Khalighinejad, Sharon Scott, Ollie Liu, Kelly L. Anderson, Rickard Stureborg, Aman Tyagi, Bhuwan Dhingra
| Challenge: | Existing methods for multimodal information extraction are limited due to the multimodal nature of scientific articles and complex interconnections between data points. |
| Approach: | They propose a benchmark to extract structured information from scientific articles . they use curated JSON files extracted from text, tables, and figures . |
| Outcome: | The proposed benchmark is based on 324 full-length research articles and 1,688 complex structured JSON files curated by experts in polymer nanocomposites and biodegradation. |
Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing embedding-based methods rely on triples in the KG, which is vulnerable to specious relation patterns and long-tail entities. |
| Approach: | They propose a context-enriched framework for KGC that uses a large language model to generate potential answers for each query triple. |
| Outcome: | The proposed framework improves on FB15k237 and WN18RR datasets. |
Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic Reasoning (2025.naacl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on text-based cognitive reframing, but neglected the importance of non-verbal evidence in real-life therapy. |
| Approach: | They propose a dataset that pairs each GPT-4-generated dialogue with an image that reflects the virtual client’s facial expressions to better mirror real psychotherapy, where facial expression leads to interpreting implicit emotional evidence. |
| Outcome: | The proposed approach outperforms existing methods with LLMs and vision-language models and provides more thoughtful and empathetic suggestions. |
SimKGC: Simple Contrastive Knowledge Graph Completion with Pre-trained Language Models (2022.acl-long)
Copied to clipboard
| Challenge: | Text-based methods lag behind graph embedding-based approaches for knowledge graph completion (KGC) |
| Approach: | They propose three types of negatives to improve contrastive learning to improve learning efficiency. |
| Outcome: | The proposed model outperforms embedding-based methods on several benchmark datasets. |
Development of an Annotated Multimodal Dataset for the Investigation of Classification and Summarisation of Presentations using High-Level Paralinguistic Features (L18-1)
Copied to clipboard
| Challenge: | Existing summarisation methods take no account of multimodal high-level paralinguistic features which form part of audio-visual presentations. |
| Approach: | They propose to use audiovisual recordings to extract paralinguistic features from audio recordings . they use manual annotations to help users find relevant material . |
| Outcome: | The proposed method can identify the most important or emphasised material within a presentation. |
Reasoning with Multimodal Sarcastic Tweets via Modeling Cross-Modality Contrast and Semantic Association (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for sarcasm detection rely on text data, but are insufficient to detect multimodal sarcasm. |
| Approach: | They propose a method for modeling cross-modality contrast in the associated context by constructing the Decomposition and Relation Network. |
| Outcome: | The proposed model can detect sarcasm in multimodal tweets using a dataset . |
CondenseFlow: Scalable Latent Space Collaboration via Semantic Compression for Multi-Agent Systems (2026.findings-acl)
Copied to clipboard
| Challenge: | Full-state latent communication in LLMs suffers from memory overhead scaling linearly with collaboration rounds. |
| Approach: | They propose a lightweight module that uses learnable semantic probes to compress KV caches into fixed-size representations. |
| Outcome: | The proposed module reduces KV cache memory by over 99% and inference latency by approximately 20% on seven benchmarks spanning six models . it outperforms text-based methods by 1.7 percentage points on average across all configurations while outperforming existing methods by 1.7%. |
Measuring Consistency in Text-based Financial Forecasting Models (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in natural language processing (NLP) have allowed financial forecasting to gain significant accuracy and reliability. |
| Approach: | They propose a tool that assesses logical consistency in financial text and compares it with other models to assess their performance. |
| Outcome: | The proposed evaluation tool assesses logical consistency in financial text. |
ATAP: Automatic Template-Augmented Commonsense Knowledge Graph Completion via Pre-Trained Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Commosense knowledge graphs (CKGC) are powerful representations of real-world commonsense knowledge. |
| Approach: | They propose a framework that uses automatically generated prompt templates combined with pre-trained language models to improve CKGC performance. |
| Outcome: | The proposed framework mitigates the long-tail problem and improves CKGC performance on a large dataset. |
CodeRipple: Wavelet-Based Detection of LLM-Generated Code (2026.acl-long)
Copied to clipboard
| Challenge: | Existing training-free detectors rely on global statistics of the Token Perplexity Sequence (TPS) and struggle with code. |
| Approach: | They propose a training-free detection framework that characterizes TPS morphology across scales. |
| Outcome: | The proposed framework outperforms existing training-free detectors on three challenging benchmarks spanning programming languages, multiple generating LLMs, and various evasion strategies. |