Papers by Jing Xiang
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models with stacked layers do not explicitly model hierarchical structure of language understanding. |
| Approach: | They propose a recursive Transformer model based on differentiable CKY style binary trees to emulate hierarchical composition process. |
| Outcome: | The proposed model can predict words given their left and right abstraction nodes. |
Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text Matching (2025.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable capabilities in acquiring diverse knowledge, making them highly effective across a wide range of tasks. |
| Approach: | They propose a flipped knowledge distillation paradigm where LLM learns from SLM . they propose to reinterpret LLMs as encoder-decoder models using LoRA . |
| Outcome: | The proposed model has been deployed in an online application environment and validated on financial and healthcare benchmarks and real-world applications. |
Reasoning-Enhanced Domain-Adaptive Pretraining of Multimodal Large Language Models for Short Video Content Governance (2025.emnlp-industry)
Copied to clipboard
Zixuan Wang, Yu Sun, Hongwei Wang, Baoyu Jing, Xiang Shen, Xin Dong, Zhuolin Hao, Hongyu Xiong, Yang Song
| Challenge: | Existing approaches to identifying inappropriate content require extensive human-labeled data and lack cross-issue generalization. |
| Approach: | They propose a reasoning-enhanced multimodal large language model (MLLM) pretraining paradigm for unified inappropriate content detection. |
| Outcome: | The proposed model improves the MLLM's performance in both zero-shot and supervised fine-tuning settings and shows strong generalization capabilities to emergent, previously unseen issues. |
Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity (2026.acl-long)
Copied to clipboard
Feiteng Fang, Dingwei Chen, Xiang Huang, Ting-En Lin, Yuchuan Wu, Xiong Liu, Jing Ye, Ziqiang Liu, Haonan Zhang, Liang Zhu, Hamid Alinejad-Rokny, Min Yang, Yongbin Li
| Challenge: | Existing approaches to reward modeling in reinforcement learning tasks are limited when dealing with ambiguous preferences. |
| Approach: | They propose to use AAM to dynamically calibrate preference margins using the Bradley-Terry model's internal parameter knowledge to improve reward modeling in subjective tasks. |
| Outcome: | The proposed approach improves reward modeling by dynamically calibrating preference margins using the model’s internal parameter knowledge. |
EmoHarbor: Evaluating Personalized Emotional Support by Simulating the User’s Internal World (2026.acl-long)
Copied to clipboard
| Challenge: | EmoHarbor is an evaluation framework that rewards generic empathetic responses but fails to assess whether the support is genuinely personalized to users’ unique psychological profiles and contextual needs. |
| Approach: | They propose an automated evaluation framework that adopts a User-as-a-Judge paradigm by simulating the user's inner world. |
| Outcome: | The proposed framework decomposes users' internal processes into three specialized roles and defines 10 evaluation dimensions of personalized support quality. |
PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent methods for detecting LLM-generated text have shown impressive performance, but in real-world scenarios, users often introduce perturbations to the text. |
| Approach: | They propose a method that detects syntactic trees that are minimally affected by perturbations and exhibit distinct differences between human-written and LLM-generated text. |
| Outcome: | The proposed method shows that it is significantly better against perturbations on the HC3 and GPT-3.5-mixed datasets and also has the shortest time expenditure. |
From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignment (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) show great potential for expressing empathy, but often deliver generic responses that fail to address users’ specific needs. |
| Approach: | They propose a self-evolution framework to help LLMs improve their responses to better align with users’ implicit preferences concerning personality, emotional state, and specific context. |
| Outcome: | The proposed model significantly improves the model's performance in emotional support, reducing unhelpful responses and minimizing discrepancies between user preferences and model outputs. |
UICOMPASS: UI Map Guided Mobile Task Automation via Adaptive Action Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Mobile task automation is an emerging technology that leverages AI to automatically execute routine tasks by users’ commands on mobile devices like Android. |
| Approach: | They propose a UI Map-guided LLM-based approach to automate mobile tasks using static analysis and LLMs. |
| Outcome: | The proposed approach achieves a 15.87% higher task execution success rate than SOTA approaches even when only APK is available. |
SweetieChat: A Strategy-Enhanced Role-playing Framework for Diverse Scenarios Handling Emotional Support Agent (2025.coling-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated promising potential in providing empathetic support during interactions, but their responses are often verbose or overly formulaic, failing to adequately address the diverse emotional support needs of real-world scenarios. |
| Approach: | They propose a strategy-enhanced role-playing framework that emulates real-world interactions and a dataset that is used to develop an emotional support agent. |
| Outcome: | The proposed framework emulates real-world interactions and promotes a broader range of dialogues and Emotional Support Agent training. |
Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalization (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for detoxification of text often rely on manually annotated data . xiangli: "detoxification of texts is a powerful way to remove toxic content" |
| Approach: | They propose a reinforcement learning framework that optimizes detoxification and semantic preservation without annotating large amounts of data. |
| Outcome: | The proposed method overcomes major limitations and surpasses humanannotated references across multiple benchmarks. |
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation (2026.acl-long)
Copied to clipboard
Jiawei Zhou, Chi Zhang, Xiang Feng, Qiming Zhang, Haibo Qiu, Lihuo He, Dengpan Ye, Xinbo Gao, Jing Zhang
| Challenge: | a benchmark is designed to evaluate the capability of Large Multimodal Models (LMMs) in converting complex, structured digital graphics into executable code. |
| Approach: | They propose a benchmark to evaluate the capability of Large Multimodal Models to convert digital graphics into executable code. |
| Outcome: | The proposed benchmark exposes the performance gap among leading LMMs . the benchmark features 1130 meticulously curated samples . |
ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing benchmarks lack the ability to automatically evaluate from users’ perspective and lack the explainability of the results of LLM agents’ code generation capabilities. |
| Approach: | They propose a new benchmark for LLM agents' automated evaluation by simulating user interaction. |
| Outcome: | The proposed benchmark can evaluate the generated projects by user interaction simulation and by code similarity through existing objective indicators. |
LLM Inductive Reasoning Through Multi-Agent Enhanced Monte Carlo Tree Search (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for enhancing inductive reasoning of large language models often lack explicit optimization guidance and effective error correction. |
| Approach: | They propose a plug-and-play test-time framework that integrates multi-agent coordination with Monte Carlo Tree Search to improve inductive reasoning. |
| Outcome: | The proposed framework outperforms existing methods on four benchmarks and shows consistent improvements on QWQ-32B and Deepseek-V3 . |
When Cantonese NLP Meets Pre-training: Progress and Challenges (2022.aacl-tutorials)
Copied to clipboard
| Challenge: | Cantonese is an influential Chinese variant with a large population of speakers worldwide. |
| Approach: | This tutorial will review Cantonese's progress in linguistics and NLP . it will introduce transformer-based pre-training methods for a wide range of downstream tasks . |
| Outcome: | This tutorial will present the main challenges for Cantonese NLP in relation to Cantonesian language idiosyncrasies of colloquialism and multilingualism. |
Impromptu Cybercrime Euphemism Detection (2025.coling-main)
Copied to clipboard
| Challenge: | Existing methods for detecting euphemisms are ineffective in impromptu euphorism detection . Existing approaches for e-mail detection are limited to word-level ephemismals . |
| Approach: | They propose a framework for impromptu euphemism detection that integrates context augmentation and multi-round iterative training to better predict the actual meaning of a masked token. |
| Outcome: | The proposed framework improves 76-fold over the previous state-of-the-art euphemism detector. |