Papers by Fei Teng

17 papers
Are Emotion and Rhetoric Neurons in LLM? Neuron Recognition and Adaptive Masking for Emotion-Rhetoric Prediction Steering (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on neurons focus on emotion and rhetoric, neglecting their intrinsic connections.
Approach: They propose a framework for fine-grained steering of emotion and rhetoric in large language models . they propose 'neuro-based' masking method that integrates multi-dimensional screening .
Outcome: The proposed method achieves directed induction of non-target sentences and enhancement of emotion tasks via rhetoric neurons.
Zero-Shot Conversational Stance Detection: Dataset and Approaches (2025.findings-acl)

Copied to clipboard

Challenge: Existing stance detection datasets are limited to a limited set of specific targets . current models are limited in their ability to detect large numbers of unseen targets based on a large number of unidentified targets.
Approach: They propose a speaker interaction and target-aware prototypical contrastive learning model that can detect public opinion towards specific targets using social media data.
Outcome: The proposed model achieves state-of-the-art in zero-shot conversational stance detection with only an F1-macro score of 43.81%.
Enhancing Hyperbole and Metaphor Detection with Their Bidirectional Dynamic Interaction and Emotion Knowledge (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for hyperbole and metaphor detection focus on superficial text features, ignoring the associations of hyperbola and metaphor . Existing frameworks focus on identifying superficial text, focusing on superficial features .
Approach: They propose an emotion-guided hyperbole and metaphor detection framework based on bidirectional dynamic interaction.
Outcome: The proposed framework outperforms baseline methods on four datasets.
DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning (2025.findings-acl)

Copied to clipboard

Challenge: Existing multimodal sentence representation learning methods focus on aligning images and text at a coarse level, resulting in cross-modal misalignment bias and intra-modal semantic divergence.
Approach: They propose a dual-level alignment learning framework for multimodal sentence representation learning that promotes cross-modal and intra-modal alignment.
Outcome: The proposed framework outperforms state-of-the-art methods on semantic textual similarity and transfer tasks on semantic similarity, ranking distillation and global intra-modal alignment learning.
Harvesting Events from Multiple Sources: Towards a Cross-Document Event Extraction Paradigm (2024.findings-acl)

Copied to clipboard

Challenge: Document-level event extraction aims to extract structured information from unstructured text.
Approach: They propose a cross-document event extraction pipeline that integrates event information from multiple documents and provides a comprehensive perspective on events.
Outcome: The proposed pipeline achieves about 72% F1 in end-to-end cross-document event extraction, setting up a benchmark for future research.
PEMV: Improving Spatial Distribution for Emotion Recognition in Conversations Using Proximal Emotion Mean Vectors (2025.findings-naacl)

Copied to clipboard

Challenge: Existing research focuses on the analysis of contextual structure in dialogue and the interactions between different emotions.
Approach: They propose a method that generates Proximal Emotion Mean Vectors (PEMVs) based on emotion feature queues to optimize the spatial representation of text features.
Outcome: The proposed method achieves state-of-the-art performance on three widely used benchmark datasets.
Cross-Document Cross-Lingual NLI via RST-Enhanced Graph Fusion and Interpretability Prediction (2025.emnlp-main)

Copied to clipboard

Challenge: Despite the development of many subdirections, Cross-Document Cross-Lingual NLI remains largely unexplored.
Approach: They propose a novel paradigm that extends traditional NLI capabilities to multi-document, multilingual scenarios by integrating RST-enhanced graph fusion with interpretability-aware prediction.
Outcome: The proposed method improves on existing models and document-level NLI to multi-document, multilingual scenarios.
Can LLMs Learn from Previous Mistakes? Investigating LLMs’ Errors to Boost for Reasoning (2024.acl-long)

Copied to clipboard

Challenge: Recent studies have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought rationales or using them as correct examples in few-shot prompting.
Approach: They propose a new benchmark to test the effectiveness of large language models by leveraging errors to enhance reasoning capabilities.
Outcome: The proposed methods can be used to fine-tune models in correct and incorrect domains, rather than tuning models to learn ground truth in traditional methods.
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel in natural language processing tasks but are vulnerable to harmful content and being exploited for malicious purposes.
Approach: They propose a framework to measure the risk coverage of alignment datasets across three dimensions: Lexical Diversity, Malicious Intent, and Jailbreak Tactics.
Outcome: The proposed framework measures risk coverage across Lexical Diversity, Malicious Intent, and Jailbreak Tactics.
DiscoSG: Towards Discourse-Level Text Scene Graph Parsing through Iterative Graph Refinement (2025.emnlp-main)

Copied to clipboard

Challenge: Current approaches typically merge sentence-level parsing outputs for discourse input, resulting in fragmented graphs and degraded downstream performance.
Approach: They propose a task for discourse-level text scene graph parsing that merges sentence-level outputs for discourse input and propose 'DiscoSG' a dataset of 400 expert-annotated and 8,430 synthesised multi-sentence caption-graph pairs is used to test the new task.
Outcome: The proposed task improves SPICE by 30% over the baseline while achieving 86 faster inference than existing models.
Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing (2024.acl-long)

Copied to clipboard

Challenge: Structured Sentiment Analysis (SSA) is a problem of bi-lexical dependency graph parsing due to the internal structures of spans neglected.
Approach: They propose to use latent spans as latent subtrees to model internal structures of spans and leverage TreeCRFs to extract the complete opinion tuple from a sentence.
Outcome: The proposed method performs significantly better than all previous bi-lexical methods, achieving new state-of-the-art.
Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information (2024.lrec-main)

Copied to clipboard

Challenge: Existing cross-document event coreference resolution models lack the ability to capture long-distance dependencies.
Approach: They propose to construct document-level Rhetorical Structure Theory trees and cross-document Lexical Chains to model structural and semantic information of documents.
Outcome: The proposed model outperforms baseline models on English and Chinese datasets by large margins.
Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks focus on linguistic competence or structured mathematical problem-solving, neglecting fundamental numerical reasoning required in real-world scenarios.
Approach: They propose a benchmark to evaluate numerical capabilities for large language models . they use a dataset to assess number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning.
Outcome: The proposed benchmark evaluates six fundamental numerical capabilities: number recognition, arithmetic operations, contextual retrieval, comparison, summary, and multi-step reasoning.
Uncertainty-Calibrated Elastic Alignment for Multimodal Sentiment Analysis with Missing Modalities (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for multimodal sentiment analysis are often dynamically incomplete.
Approach: They propose a new uncertainty-calibrated elastic alignment framework to address these issues by employing probabilistic imputation to capture cross-modal ambiguity and leverage the estimated uncertainty to drive elastic alignment.
Outcome: The proposed framework outperforms state-of-the-art models in multiple benchmarks and consistently outperformed existing models.
Dynamic Emotion and Personality Profiling for Multimodal Deception Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for deception detection lack sample-level dynamic annotations for emotions and personality.
Approach: They propose a multi-model multi-prompt annotation scheme and a strict label quality evaluation standard for deception, emotion, and personality annotations.
Outcome: The proposed framework outperforms state-of-the-art models on the MDPE and DDEP datasets.
Refining and Synthesis: A Simple yet Effective Data Augmentation Framework for Cross-Domain Aspect-based Sentiment Analysis (2024.findings-acl)

Copied to clipboard

Challenge: Aspect-based Sentiment Analysis (ABSA) data augmentation has attracted increasing attention in recent years due to data sparsity.
Approach: They propose a framework to augment ABSA data using pseudo labels for target domain . they refine generated labeled data using a natural language inference filter .
Outcome: The proposed framework outperforms 7 strong baselines on 4 kinds of ABSA tasks.
What Factors Influence LLMs’ Judgments? A Case Study on Question Answering (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies indicate that Large Language Models perform at a level comparable to humans with advantages of speed and cost-effectiveness in different fields.
Approach: They propose to introduce four unexplored factors and a new dimension of question difficulty to provide a more comprehensive understanding of LLMs’ judgments across varying question intricacies.
Outcome: The proposed dimensions of question difficulty and answer quantity provide valuable insights into optimizing LLMs’ performance as judges.

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