Papers with text-based methods

11 papers
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

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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations