Papers by Feiteng Mu

6 papers
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

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.

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