Papers by Xin Sheng

10 papers
Enhancing Chain-of-Thought Reasoning via Neuron Activation Differential Analysis (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on optimizing external components of CoT, but lack internal explanations for the quality of the model's outputs.
Approach: They propose an efficient method to identify reasoning-critical neurons by analyzing their activation patterns under reasoning chains of varying quality.
Outcome: The proposed method shows that neurons in the feed-forward layers are critical in the generation of high-quality reasoning chains.
Can Language Models Capture Human Writing Preferences for Domain-Specific Text Summarization? (2025.findings-acl)

Copied to clipboard

Challenge: Recent studies employ large language models as auxiliary tools for humancentered NLP.
Approach: They construct a model to capture human writing preferences by fine-tuning pre-trained models with data and designing prompts to optimize the output of large language models.
Outcome: The proposed model captures human writing preferences through the dimensions of length, content depth, tone & style, and summary format.
Event Causality Extraction with Event Argument Correlations (2022.coling-1)

Copied to clipboard

Challenge: Event Causality Identification (ECI) ignores crucial event structure and cause-effect component information, making it struggle for downstream applications.
Approach: They propose a task to extract event causality pairs with their structured event information from plain text.
Outcome: The proposed method captures the intra- and inter-event argument correlations for ECE and provides several future directions.
Semantic-Preserving Abstractive Text Summarization with Siamese Generative Adversarial Net (2022.findings-naacl)

Copied to clipboard

Challenge: Existing methods focus on attention mechanism, but they are not suitable for abstractive text summarization.
Approach: They propose a siamese generative adversarial net for abstractive text summarization which preserves the main semantics of the source text and the target summary.
Outcome: The proposed model can preserve the main semantics of the source text and target summary.
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning (2022.findings-naacl)

Copied to clipboard

Challenge: Pre-trained language models (PLMs) are a good starting point for downstream applications, but it is difficult to generalize them to new tasks given a few labeled samples.
Approach: They propose to use Relation Graph augmented learning to improve the performance of few-shot natural language understanding tasks by rewriting the input sequence into a cloze question with masks.
Outcome: Extensive experiments show that Relation Graph augmented learning (RGL) improves performance of prompt-based tuning strategies.
MMAD:Multi-modal Movie Audio Description (2024.lrec-main)

Copied to clipboard

Challenge: Current methods of creating accessible movies rely on manual work, resulting in high costs and limited scalability.
Approach: They propose a multi-modal movie audio description pipeline that generates narrations of information that is not accessible through unimodal hearing in movies.
Outcome: The proposed pipeline surpasses existing baselines in performance on widely used datasets.
RecMem: Recurrence-based Memory Consolidation for Efficient and Effective Long-Running LLM Agents (2026.findings-acl)

Copied to clipboard

Challenge: Existing memory systems invoke LLMs to extract episodic and semantic memory, and this leads to substantial token consumption.
Approach: They propose a method that stores incoming interactions in a subconscious memory layer and encodes them using lightweight embedding models for retrieval.
Outcome: Experiments show that RecMem reduces the memory construction token cost of three SOTA memory systems by up to 87% while exceeding their accuracy.
Retrieved Sequence Augmentation for Protein Representation Learning (2024.emnlp-main)

Copied to clipboard

Challenge: Using multiple sequence alignments (MSA) to extract evolutionary knowledge is limited.
Approach: They propose to use multiple sequence alignments to augment protein representations . they propose to employ Retrieved Sequence Augmentation to enhance protein representation learning .
Outcome: The proposed method surpasses MSA Transformer by 5% in structural and property prediction tasks while being 373 times faster.
Sociolectal Analysis of Pretrained Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Using data from English cloze tests, we demonstrate wide performance gaps across demographic groups and show that pretrained language models disfavor young non-white male speakers.
Approach: They use data from English cloze tests to examine performance differences of pretrained language models across demographic groups.
Outcome: The models disfavor young non-white male speakers, but larger models reduce performance gaps between majority and minority groups.
CoCGAN: Contrastive Learning for Adversarial Category Text Generation (2022.coling-1)

Copied to clipboard

Challenge: Experimental results on synthetic and real category text generation datasets demonstrate that CoCGAN can achieve significant improvements over the baseline category text generators.
Approach: They propose to incorporate contrastive learning into adversarial category text generation by using a discriminator to optimize a contrastive learn objective to capture more flexible data-to-class relations and data- to-data relations among training samples.
Outcome: The proposed model improves on synthetic and real category text generation datasets.

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