Papers by Xingxing Zhang

14 papers
Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations (2026.acl-long)

Copied to clipboard

Challenge: Previous work shows that large language models generate hallucinations, yet the origins and mechanisms of these signals remain unclear.
Approach: They propose to validate and disentangle two different pathways for truthfulness cues . they also propose to use the same mechanism to derive self-contained evidence from the generated answer .
Outcome: The proposed applications improve hallucination detection performance by integrating two different inputs.
Attention Temperature Matters in Abstractive Summarization Distillation (2022.acl-long)

Copied to clipboard

Challenge: Recent progress of abstractive text summarization relies on large pre-trained sequence-to-sequence Transformer models, which are computationally expensive.
Approach: They propose to distill large Transformer summarization models into smaller ones with minimal performance loss by manipulating attention temperatures in Transformers.
Outcome: The proposed method outperforms vanilla pseudo-labeling based methods on three summarization datasets and is shorter and more abstractive.
Pre-training for Abstractive Document Summarization by Reinstating Source Text (2020.emnlp-main)

Copied to clipboard

Challenge: Abstractive document summarization models are often trained on limited supervised data . authors present three objectives for pretraining abstractive summarizing models .
Approach: They propose to pre-train a SEQ2SEQ based abstractive summarization model on unlabeled text.
Outcome: The proposed method improves on two benchmark summarization datasets with 19GB of text . the goal is sentence reordering, next sentence generation and masked document generation .
Tuna: Instruction Tuning using Feedback from Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: LLms like LLaMA have shown to be cost-effective for generating better responses . however, the instruction-tuned model has only seen one response per instruction .
Approach: They propose to fine tune an instruction-tuned LLM using probabilistic ranking and contextual ranking approaches to increase the likelihood of generating better responses.
Outcome: The proposed model improves on Super Natural Instructions, LMentry and Vicuna QA.
Improving the Efficiency of Grammatical Error Correction with Erroneous Span Detection and Correction (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods to improve the efficiency of GEC are not efficient enough for GEC.
Approach: They propose a language-independent approach to improve the efficiency of GEC by dividing the task into two subtasks: ESD and ESC.
Outcome: The proposed approach performs comparably to conventional seq2seq approaches in English and Chinese GEC benchmarks with less than 50% time cost for inference.
Neural Latent Extractive Document Summarization (D18-1)

Copied to clipboard

Challenge: Existing summarization paradigms focus on extractive summarizing based on sentence level labels .
Approach: They propose a latent variable extractive model where sentences are viewed as latent variables and sentences with activated variables are used to infer gold summaries.
Outcome: The proposed model outperforms a strong extractive baseline trained on rule-based labels and performs competitively with several recent models.
HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization (P19-1)

Copied to clipboard

Challenge: Neural extractive summarization models employ hierarchical encoders with inaccurate sentence-level labels.
Approach: They propose a method to pre-train a hierarchical encoder with unlabeled data.
Outcome: The proposed model outperforms its initialized counterpart by 1.25 ROUGE on CNN and 2.0 ROUGEE on a version of New York Times dataset.
Neural Label Search for Zero-Shot Multi-Lingual Extractive Summarization (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to translate sentences to other languages using heuristics are challenging.
Approach: They propose a model that learns hierarchical weights for different sets of labels and applies them to other languages to translate them.
Outcome: The proposed model can translate English datasets to other languages and obtain different sets of labels again using heuristics.
Unsupervised Extractive Summarization by Pre-training Hierarchical Transformers (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for document summarization use graphs and unlabeled documents . Existing models require labeled data, and it is expensive to create summarized documents.
Approach: They propose to rank sentences using transformer attentions and pre-training objectives by unlabeled documents.
Outcome: The proposed model achieves state-of-the-art on unsupervised summarization and is less dependent on sentence positions.
Unsupervised Fine-tuning for Text Clustering (2020.coling-main)

Copied to clipboard

Challenge: Existing approaches to text clustering fine-tune pre-trained models have been limited.
Approach: They propose a method to fine-tune pre-trained models unsupervisedly for text clustering by learning text representations and cluster assignments using a clustering oriented loss.
Outcome: The proposed model outperforms baseline methods and achieves state-of-the-art results on three text clustering datasets.
Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study (P19-1)

Copied to clipboard

Challenge: Sequence-to-sequence (seq2sequ) models have a weakness: they cannot always generate sentences without grammatical errors.
Approach: They propose to use automatic grammatical error correction to improve seq2seq models . they conduct experiments on machine translation, formality style transfer, sentence compression and simplification .
Outcome: The proposed system can improve grammaticality of generated text and improve formal style tasks.
Chain-of-Reasoning: Towards Unified Mathematical Reasoning in Large Language Models via a Multi-Paradigm Perspective (2025.acl-long)

Copied to clipboard

Challenge: Existing work shows that LLMs rely on single-paradigm reasoning that limits their effectiveness across diverse tasks.
Approach: They propose a new framework that integrates multiple reasoning paradigms to enable synergistic collaboration.
Outcome: The proposed model outperforms current SOTA models in theorem proving tasks and the MATH benchmark in arithmetic tasks.
Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to exploit black-box jailbreaks fail to capture key attack patterns . a novel framework decomposes jailbreak strategies into essential components .
Approach: They propose a framework that decomposes jailbreak strategies into essential components and develops genetic-based optimization with intention evaluation mechanisms.
Outcome: The proposed framework achieves 90% success rate on Claude-3.5, where prior methods completely fail . it also surpasses specialized safeguard models in evaluation accuracy .
Unsupervised Multi-Granularity Summarization (2022.findings-emnlp)

Copied to clipboard

Challenge: Experimental results confirm the substantial superiority of GranuSum on multi-granularity summarization over strong baselines.
Approach: They propose to rank events by their salience and annotate a benchmark for GranuSum that contains multiple summaries at different granularities for each document cluster.
Outcome: The proposed framework is capable of producing multi-granular summaries in unsupervised manner over strong baselines.

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