Papers by Fan Xing

25 papers
Maximizing the Effectiveness of Larger BERT Models for Compression (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for capturing large BERT models as teachers do not fully exploit the potential advantages of larger teachers.
Approach: They propose a method that leverages a pretrained teacher model to guide the training of a lightweight student model to enhance knowledge transfer.
Outcome: The proposed method enhances knowledge transfer by leveraging a pretrained teacher model to guide the training of a lightweight student model.
Unified Contextual Query Rewriting (2023.acl-industry)

Copied to clipboard

Challenge: Large-scale conversational AI agents such as Alexa, Siri, and Google Assistant are becoming increasingly popular in real-world applications to assist users in daily life.
Approach: They propose a unified contextual query rewriting model that unifies QR for friction reduction and contextual carryover . they leverage the text-to-text unified framework which uses independent tasks with weighted loss to account for task importance .
Outcome: The proposed model reduces friction and contextual carryover by using multiple auxiliary tasks.
Towards Human-aligned Evaluation for Linear Programming Word Problems (2024.lrec-main)

Copied to clipboard

Challenge: Existing evaluation methodologies for MWPs diverge from human judgment and face challenges in recognizing mathematically equivalent answers.
Approach: They propose an evaluation metric rooted in graph edit distance that features benefits such as permutation invariance and more accurate program equivalence identification.
Outcome: The proposed evaluation metric features benefits such as permutation invariance and more accurate program equivalence identification.
Learning to Selectively Learn for Weakly-supervised Paraphrase Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate paraphrases with weak supervision are limited in real-world scenarios due to the lack of coherent and controllable generated paraphrase.
Approach: They propose a method to generate high-quality paraphrases with weak supervision . they obtain abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion .
Outcome: The proposed approach achieves significant improvements over existing methods and is even comparable in performance with supervised state-of-the-arts.
FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks emphasize final numerical answers while neglecting intermediate reasoning steps.
Approach: They propose a symbolic benchmark for verifiable Chain-of-Thought evaluation in finance . FINCHAIN spans 58 topics across 12 financial domains and three difficulty levels .
Outcome: The proposed benchmark aims to bridge symbolic reasoning and factual verification.
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach: They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome: The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .
ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code (2026.findings-acl)

Copied to clipboard

Challenge: Large Reasoning Models suffer from the "over-thinking" problem, causing performance degradation.
Approach: They propose a unified model that balances reasoning performance and efficiency across multiple formats through a reinforcement learning framework augmented with length-aware optimization.
Outcome: The proposed model reduces token costs while preserving performance compared to traditional models.
PENTATRON: PErsonalized coNText-Aware Transformer for Retrieval-based cOnversational uNderstanding (2022.emnlp-industry)

Copied to clipboard

Challenge: In a large fraction of the global traffic from smart digital assistants, frictions in dialogues may be attributed to incorrect understanding of the entities in a user's query due to factors including ambiguous mentions, mispronunciation, background noise and faulty on-device signal processing.
Approach: They propose a parametric transformer-based language model to learn patterns from in-session customer-device interactions coupled with a non-parametric personalized entity index to compute the correct query.
Outcome: The proposed system improves on the existing system and shows that it can learn the correct query from in-session customer-device interactions.
Learning to Ask Denotative and Connotative Questions for Knowledge-based VQA (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models have attracted increasing attention due to their prominent performance on various tasks.
Approach: They propose to let LLMs learn to ask informative questions to collect visual information . they introduce concepts of denotation and connotation to promote image and question understanding .
Outcome: The proposed model can generate high-quality questions and efficiently collect required information without expensive training or annotations.
Contextual Rephrase Detection for Reducing Friction in Dialogue Systems (2021.emnlp-main)

Copied to clipboard

Challenge: Large-scale conversational AI based dialogue systems like Alexa, Siri, and Google Assistant, are getting more and more prevalent in real-world applications to help users across the globe.
Approach: They propose a contextual rephrase detection model ContReph to automatically identify rephrasings from multi-turn dialogues using contextual information and user-agent interaction signals.
Outcome: The proposed model outperforms the pairwise rephrase detection models by leveraging the context and user-agent interaction signals.
CL-QR: Cross-Lingual Enhanced Query Reformulation for Multi-lingual Conversational AI Agents (2023.emnlp-industry)

Copied to clipboard

Challenge: Existing QR systems that reformulate defective user queries are limited in English due to the scarcity of non-English QR labels.
Approach: They propose a query reformulation method which reformulates defective user queries to improve non-English QR performance.
Outcome: The proposed framework improves non-English QR performance by leveraging abundant reformulation resources in English.
Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiency (2025.findings-acl)

Copied to clipboard

Challenge: Recent dynamic computation methods show that not all components are required for inference, enabling a training-free pipeline.
Approach: They propose a token-position aware layer skipping framework to save 1.5x times operations efficiently while maintaining performance.
Outcome: The proposed algorithm achieves 1.5x speedup on large language models with no retraining and with comparable performance on the GSM8K and BBH benchmarks.
CGF: Constrained Generation Framework for Query Rewriting in Conversational AI (2022.emnlp-industry)

Copied to clipboard

Challenge: Large-scale conversational AI agents such as Alexa, Siri and Google Assistant help millions of users to perform a lot of tasks.
Approach: They propose a Constrained Generation Framework for query rewriting at global and personalized levels.
Outcome: The proposed framework significantly boosts the query rewriting performance.
SedarEval: Automated Evaluation using Self-Adaptive Rubrics (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing evaluation paradigms rely on generic scoring rubrics that fail to consider the specificities of each question and its problem-solving process.
Approach: They propose a new evaluation paradigm based on self-adaptive rubrics that mimic a human evaluator's analytical process.
Outcome: The proposed evaluation paradigm achieves higher concordance rate with human graders than existing paradigms, including GPT-4.
Overcoming Catastrophic Forgetting During Domain Adaptation of Seq2seq Language Generation (2022.naacl-main)

Copied to clipboard

Challenge: Existing work on lifelong learning requires incremental memory space to learn a model . existing work on experience replay or elastic weighted consolidation requires incremental space .
Approach: They propose a framework that leverages a recall optimization mechanism to memorize parameters of previous tasks via regularization and a domain drift estimation algorithm to compensate the drift between different domains in the embedding space.
Outcome: The proposed framework outperforms SOTA models on paraphrase and dialog response generation tasks.
RecMind: Large Language Model Powered Agent For Recommendation (2024.findings-naacl)

Copied to clipboard

Challenge: Existing recommendations systems are limited in generalizing to new tasks due to model scale and data size constraints.
Approach: They propose an LLM-powered autonomous recommender agent, RecMind, which is capable of leveraging external knowledge to provide zero-shot personalized recommendations.
Outcome: The proposed model outperforms existing zero/few-shot LLM-based recommendation baseline methods in various tasks and achieves comparable performance to a fully trained recommendation model P5.
Analyzing and Internalizing Complex Policy Documents for LLM Agents (2026.acl-long)

Copied to clipboard

Challenge: Large language model agents rely on in-context policy documents to act as effective user assistants.
Approach: They propose an agentic benchmark generator with Controllable Complexity in agent policy across four levels to evaluate agents under increasing complexity.
Outcome: The proposed method outperforms the baseline in data-sparse and high-complexity settings.
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing large language model evaluation benchmarks focus on English, while current multilingual tasks lack parallel questions that specifically assess cross-lingual reasoning abilities.
Approach: They propose a comprehensive benchmark covering 29 languages, built on an English benchmark.
Outcome: The MMLU-ProX is a comprehensive benchmark covering 29 languages, built on an English benchmark.
A Survey on Multi-modal Intent Recognition: Recent Advances and New Frontiers (2025.findings-emnlp)

Copied to clipboard

Challenge: Multi-modal intent recognition (MIR) requires integrating non-verbal cues from real-world contexts to enhance human intention understanding.
Approach: They present a comprehensive review of multi-modal intent recognition . they provide a survey of the field covering textual, visual, and acoustic signals .
Outcome: The present survey summarises the current state of multi-modal intent recognition . it includes a comprehensive taxonomy and advanced methods .
Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding (2023.emnlp-industry)

Copied to clipboard

Challenge: Defective queries impact the robustness of conversational AI systems such as Alexa, Siri or Google Assistant.
Approach: They propose a Personalized Query Rewriting system that takes into account individual preferences or unique error patterns identified from a user's historical interactions with the conversational AI.
Outcome: The proposed approach has been proven on a large-scale real-world dataset and online A/B experiments.
Multi-Granularity Fusion Text Semantic Matching Based on WoBERT (2024.lrec-main)

Copied to clipboard

Challenge: Existing text-matching methods struggle with semantic nuances in short texts . a novel approach to improve text semantic matching is being developed .
Approach: They propose a multi-granularity fusion model that harnesses a pre-trained language model to capture text semantic nuances.
Outcome: The proposed model improves on Chinese short text matching datasets compared to traditional methods . the proposed model captures individual text semantic nuances and improves accuracy .
Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study (2020.acl-main)

Copied to clipboard

Challenge: Existing studies on automatic generation of citation texts in scholarly papers have not investigated this problem.
Approach: They propose to train an implicit citation extraction model based on BERT and a multi-source pointer-generator network with cross attention mechanism for citation text generation.
Outcome: The proposed model can generate short texts to describe cited papers in scholarly papers with training data.
Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning (2023.emnlp-industry)

Copied to clipboard

Challenge: Contextual query rewriting (CQR) is a crucial component in Conversational AI agents, leveraging contextual information from previous user-agent conversations to improve comprehension of current user intent.
Approach: They propose a framework to enhance the CQR model's capability in generating user preference-aligned rewrites.
Outcome: The proposed framework improves the CQR model's ability to generate user preference-aligned rewrites.
PAIGE: Personalized Adaptive Interactions Graph Encoder for Query Rewriting in Dialogue Systems (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing methods to fix faulty queries are limited in their ability to fix them.
Approach: They propose a Personalized Adaptive Interactions Graph Encoder that integrates user's affinities and query semantics to refine utterance embeddings.
Outcome: The proposed Query Rewriting (QR) techniques improve the rewrite accuracy of state-of-the-art baselines by 12.5–17.5% while having nearly ten times fewer parameters.
Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging (2024.emnlp-main)

Copied to clipboard

Challenge: Existing studies suggest that the order of training samples can affect model performance, but this is not the case.
Approach: They propose to merge supervised fine-tuning models with different data orders to mitigate this imbalance by parameter merging.
Outcome: The proposed method outperforms the weighted-average method on five 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