Papers by Feiteng Mu
Enhancing Event Causality Identification with Counterfactual Reasoning (2023.acl-short)
Copied to clipboard
| Challenge: | Existing methods for event causality identification (ECI) focus on mining potential causal signals, but causal signals are ambiguous, which may lead to the context-keywords bias and the event-pairs bias. |
| Approach: | They propose a method that explicitly estimates the influence of context keywords and event pairs in training to eliminate biases in inference. |
| Outcome: | The proposed method eliminates biases in inference on two datasets. |
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Models (2025.findings-emnlp)
Copied to clipboard
Zhen Zhang, Xinyu Wang, Yong Jiang, Zile Qiao, Zhuo Chen, Guangyu Li, Feiteng Mu, Mengting Hu, Pengjun Xie, Fei Huang
| Challenge: | Retrieval-augmented generation (RAG) is employed to tackle these challenges . a Knowledge Boundary Model (KBM) is used to express the known/unknown of a given question . |
| Approach: | They propose a Knowledge Boundary Model to express the known/unknown of a given question . they find that not all questions need to trigger RAG to improve performance . |
| Outcome: | The proposed model reduces time and computational costs by retrieving parts of unknown knowledge . the proposed model can express the known/unknown of a given question and determine whether a RAG needs to be triggered . |
Effect Generation Based on Causal Reasoning (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for reasoning causalities on word level are limited . a word-level causal reasoning method may only predict the unintelligible effect of "quarrel" |
| Approach: | They propose a novel event-level causal reasoning method that structuralizes event-effect event pairs into an event causality network and shows its use in the task of effect generation. |
| Outcome: | The proposed method generates more reasonable effect sentences than well-designed competitors. |
Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenario (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing tool learning methods focus on selecting the most effective tool from a wide array of options, often overlooking cost-effectiveness. |
| Approach: | They propose to predict query performance and cost required to accomplish a given task . they then assign queries to the optimal tools in a cost-effective manner . |
| Outcome: | The proposed method achieves higher performance at lower cost compared to baseline approaches. |
A Causal Approach for Counterfactual Reasoning in Narratives (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for counterfactual reasoning in narratives are based on dataset-specific heuristics, but they are abusing unique patterns, i.e., the feature of minimum editing, in the dataset, which limits the generality of their methods. |
| Approach: | They propose a basic VAE module for counterfactual reasoning in narratives and introduce a pre-trained classifier and external event commonsense to mitigate the posterior collapse problem. |
| Outcome: | The proposed method improves the causality between the counterfactual condition and the generated counterf actual outcome on two public benchmarks. |
Generating Contrastive Narratives Using the Brownian Bridge Process for Narrative Coherence Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for learning narrative coherence are coarse-grained and superficial . existing methods are inadequate for learning negative samples, which are irrelevant or repetitive . |
| Approach: | They propose two strategies for mining hard negatives using the Brownian Bridge process . they evaluate the method on several tasks and show it is applicable to many applications . |
| Outcome: | The proposed method proves that it is applicable to many applications. |