Papers by Jing Feng

30 papers
CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for social media bot detection neglect community structure and poor model generalization due to the relatively small scale of the dataset.
Approach: They propose a framework that constructs social networks as heterogeneous graphs and uses community-aware modules to mine hard positive and hard negative samples for supervised graph contrastive learning.
Outcome: The proposed framework outperforms baselines on three social media bot benchmarks.
CORD: Bridging the Audio–Text Reasoning Gap via Weighted On-policy Cross-modal Distillation (2026.findings-acl)

Copied to clipboard

Challenge: Large Audio Language Models (LALMs) exhibit a degradation in knowledge and reasoning capabilities . empirical results show that CORD significantly bridges the audio–text performance gap .
Approach: They propose a framework that performs online cross-modal self-distillation to bridge the acoustic-semantic gap between LALMs and text-based models.
Outcome: The proposed framework bridges the acoustic-semantic gap between LALMs and text-based models . it employs on-policy reverse KL divergence with importance-aware weighting .
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: a novel post-training pruning method relies on the Hessian matrix to perform pruning . current pruning methods are computationally intensive and lack performance due to second-order derivative calculations.
Approach: They propose a Hessian-free weight pruning method that reduces computational burden . they use an Exponentially Weighted Moving Average technique to bypass weight sorting .
Outcome: The proposed method achieves hardware-efficient model compression by eliminating computational intensive calculations.
ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Currently, tool-augmented large language models (LLMs) only achieve total scores of 45.3 and 37.0, respectively, on a scale of 100.
Approach: They propose a multi-level diagnostic process to assess the LLM's hallucinations through two perspectives: depth and breadth.
Outcome: The proposed diagnostic process assesses the hallucinations of large language models through two perspectives: depth and breadth.
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.
PsyChain: A Collaborative Chain-of-Agents Framework for Generating Personalized and Professional Counseling Dialogues (2026.findings-acl)

Copied to clipboard

Challenge: Existing psychological counseling datasets suffer from monolithic client personas, insufficient therapeutic depth, and a lack of process controllability.
Approach: They propose a framework that evolves static counseling corpora into high-fidelity dialogues . they use a Client Profiler that pairs life scenarios with psychological personality archetypes based on client personality and stage progression .
Outcome: The proposed framework achieves 61-91% win rates against domain-specific baselines in pairwise evaluation and the highest average score in human evaluation, indicating potential for real-world counseling.
Mitigating Over-Generation for Unsupervised Keyphrase Extraction with Heterogeneous Centrality Detection (2023.emnlp-main)

Copied to clipboard

Challenge: Existing keyphrase extraction models incorrectly determine a keyphrase as a phrase but output other candidates as keyphrases because they contain the same word.
Approach: They propose a new approach that detects both implicit and explicit centrality within a heterogeneous graph as the importance score of each candidate keyphrase.
Outcome: The proposed approach outperforms state-of-the-art keyphrase extraction models on three benchmark datasets.
LA-UCL: LLM-Augmented Unsupervised Contrastive Learning Framework for Few-Shot Text Classification (2024.lrec-main)

Copied to clipboard

Challenge: Experimental results show that our model exceeds the baseline models due to the lack of cognitive ability.
Approach: They propose a LLM-Augmented Unsupervised Contrastive Learning Framework which introduces a cognition-enabled Large Language Model (LLM) for efficient data augmentation and presents corresponding contrastive learning strategies.
Outcome: The proposed model exceeds baseline models on six datasets.
SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks.
Approach: They propose a tool-memory based self-evolving agentic framework that integrates planning with execution.
Outcome: The proposed framework is able to extract explicit knowledge from historical data and leverage inter-trajectory correlations to densify reward signals.
Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to mental health support lack realism and capture therapeutic progression over time.
Approach: They propose a framework that simulates expert narrative therapists by planning therapeutic stages, guiding reflection levels, and generating contextually appropriate responses through retrieval-augmentation.
Outcome: The proposed framework outperforms standard methods in quality and depth on 260 simulated clients and 230 human participants.
AlignBench: Benchmarking Chinese Alignment of Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Effective evaluation of alignment for emerging Chinese LLMs is still significantly lacking, calling for real-scenario grounded, open-ended, challenging and automatic evaluations tailored for alignment.
Approach: They propose a multi-dimensional benchmark for evaluating LLMs’ alignment in Chinese with 8 main categories, 683 real-scenario rooted queries and corresponding human verified references.
Outcome: The benchmark uses a human-in-the-loop data curation pipeline, 683 real-scenario rooted queries and human verified references.
SPD-Faith Bench: Diagnosing and Improving Faithfulness in Chain-of-Thought for Multimodal Large Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Existing studies on multimodal faithfulness have focused on perceptual hallucinations, raising concerns about the validity of reasoning traces.
Approach: They propose a diagnostic benchmark that enforces explicit visual comparison to assess faithfulness of reasoning traces.
Outcome: The proposed framework improves visual routing and aligns reasoning with perception.
Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing Diffusion Language Models rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions.
Approach: They propose a diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions.
Outcome: The proposed approach outperforms existing DLMs on multiple benchmarks.
Exploring and Adapting Chinese GPT to Pinyin Input Method (2022.acl-long)

Copied to clipboard

Challenge: a frozen GPT can generate state-of-the-art performance on perfect pinyin, but performance drops when input includes abbreviated pinyan, which links to even larger number of Chinese characters.
Approach: They propose to use Chinese GPT to generate fluent sentences using abbreviated pinyin.
Outcome: The proposed approach improves on abbreviated pinyin across all domains.
CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language Models (2025.findings-naacl)

Copied to clipboard

Challenge: Current music information retrieval systems struggle to meet linguistic diversity challenges . current systems struggle with text queries in non-English languages .
Approach: They propose a music information retrieval system that supports both ABC notation and MIDI . CLaMP 2 includes a multilingual text encoder and a multiple-modal music encoder .
Outcome: The proposed system achieves state-of-the-art results in multilingual semantic search and music classification across modalities.
Match More, Extract Better! Hybrid Matching Model for Open Domain Web Keyphrase Extraction (2024.findings-acl)

Copied to clipboard

Challenge: Existing models for keyphrase extraction use noisy information to filter the salient phrases from the document.
Approach: They propose a hybrid matching model that combines representation-focused and interaction-based matching modules into a unified framework for improving keyphrase extraction.
Outcome: The proposed model outperforms state-of-the-art keyphrase extraction models on the OpenKP dataset.
AlignedCoT: Prompting Large Language Models via Native-Speaking Demonstrations (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing LLMs are delicate and elusive in prompt words and styles.
Approach: They propose an LLM-acquainted prompting technique that includes proficient "native-speaking" they propose to use in-context learning to prompt LLMs to perform high-performance reasoning .
Outcome: The proposed technique achieves step-wise prompts in zero-shot scenarios while maintaining the prompt quality.
Omni-I2C: A Holistic Benchmark for High-Fidelity Image-to-Code Generation (2026.acl-long)

Copied to clipboard

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 .
MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free (2026.findings-acl)

Copied to clipboard

Challenge: Existing research on Large Language Models (LLMs) limited to textual input modality . acoustic information is intrinsically heterogeneous, entangling attributes such as speech, music, and environmental context.
Approach: They propose a sparse Mixture-of-Experts architecture to decouple acoustic information by routing audio tokens to specialized experts.
Outcome: The proposed architecture outperforms existing models on audio semantic and paralinguistic tasks while retaining shared experts for global context.
StereoRel: Relational Triple Extraction from a Stereoscopic Perspective (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for relational triple extraction still face challenges, including information loss and error propagation.
Approach: They propose a model which maps relational triples to a three-dimensional space and leverages three decoders to extract them.
Outcome: The proposed model outperforms the baselines on five public datasets.
Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Existing work on large reasoning models (LRMs) focuses on using reinforcement learning (RL) to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Approach: They propose to use reinforcement learning to train hybrid reasoning models that automatically decide whether to engage in thinking or not based on the complexity of the query.
Outcome: The proposed model reduces token usage by around 50%$ compared to DeepSeek-R1-Distill-Qwen-1.5B/7B and DeepScaleR-1.5b, while significantly improving accuracy.
FrontCoder: Scaling Visual Fidelity in Front-End Code Generation (2026.findings-acl)

Copied to clipboard

Challenge: Existing work on front-end code generation fails to provide visual fidelity and rendering quality for front- end developers.
Approach: They propose a three-stage pipeline to enhance front-end code generation capabilities in LLMs . they use synthetic data, quality-controlled supervised fine-tuning, and reinforcement learning .
Outcome: The proposed model achieves competitive performance with frontier models while maintaining generation efficiency.
Cultural Bias Matters: A Cross-Cultural Benchmark Dataset and Sentiment-Enriched Model for Understanding Multimodal Metaphors (2025.acl-long)

Copied to clipboard

Challenge: Metaphors are pervasive in communication, making them crucial for natural language processing.
Approach: They propose a multicultural multimodal metaphor dataset designed for cross-cultural studies of metaphor in Chinese and English.
Outcome: The proposed model improves metaphor comprehension across cultural backgrounds and cultural domains.
Hyperbolic Relevance Matching for Neural Keyphrase Extraction (2022.naacl-main)

Copied to clipboard

Challenge: Keyphrase extraction is a fundamental task in natural language processing that aims to extract a set of phrases with important information from a source document.
Approach: They propose a hyperbolic matching model to explore keyphrase extraction in hyperbolical space using word embeddings from RoBERTa to capture hierarchical syntactic and semantic structures.
Outcome: The proposed model outperforms the state-of-the-art models on six benchmark datasets and outperformed previous models.
A Survey on Recent Advances in Keyphrase Extraction from Pre-trained Language Models (2023.findings-eacl)

Copied to clipboard

Challenge: Keyphrase extraction is a key component in Natural Language Processing (NLP) systems for selecting a set of phrases from the document that could summarize the important information discussed in the source document.
Approach: They propose to use supervised and unsupervised keyphrase extraction techniques to investigate the state-of-the-art models for keyphrase extracting.
Outcome: The proposed keyphrase extraction system can significantly accelerate the speed of retrieval and help people get first-hand information from a long document quickly and accurately.
Improving Embedding-based Unsupervised Keyphrase Extraction by Incorporating Structural Information (2023.findings-acl)

Copied to clipboard

Challenge: Existing unsupervised keyphrase extraction models ignore the indicative role of the highlights in certain locations, leading to wrong keyphrases extraction.
Approach: They propose a Highlight-Guided Unsupervised Keyphrase Extraction model that models phrase-document relevance via the highlights of documents and calculates cross-phrase relevance between all candidate phrases.
Outcome: The proposed model outperforms the state-of-the-art unsupervised keyphrase extraction models on three benchmarks.
Debiasing Large Language Models via Adaptive Causal Prompting with Sketch-of-Thought (2026.findings-eacl)

Copied to clipboard

Challenge: Existing prompting methods for Large Language Models (LLMs) suffer from excessive token usage and limited generalisability across diverse reasoning tasks.
Approach: They propose an Adaptive Causal Prompting with Sketch-of-Thought framework that leverages structural causal models to infer the causal effect of a query on its answer.
Outcome: The proposed framework outperforms existing prompting baselines in terms of accuracy, robustness, and computational efficiency.
A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing knowledge bases (KBs) can explicitly facilitate the QA process.
Approach: They propose a numerical reasoning model pretraining NumGNN and NumTransformer, guided by explicit self-supervision signals, to enhance numerical reasoning ability for IR-based KBQA models.
Outcome: Extensive experiments on two KBQA benchmarks confirm the effectiveness of the proposed model.
HoLLMwood: Unleashing the Creativity of Large Language Models in Screenwriting via Role Playing (2024.findings-emnlp)

Copied to clipboard

Challenge: Generative AI has demonstrated unprecedented creativity in the field of computer vision, yet such phenomena have not been observed in the realm of literary creation.
Approach: They propose a framework for unleashing the creativity of large language models (LLMs) they assign LLMs to different roles involved in real-world scenario, they write .
Outcome: The proposed framework outperforms baselines in terms of coherence, relevance, interestingness and overall quality on automatically generated screenplays.
Flow-Based Page Unique Semantic Mapping Architecture for Document Visual Question Answering (2026.acl-long)

Copied to clipboard

Challenge: Document Visual Question Answering (DocVQA) aims to generate answers by understanding textual, layout, and visual elements within document images.
Approach: They propose a Flow-Based Page Unique Semantic Mapping Architecture to solve the distinguishability problem among semantically similar pages.
Outcome: The proposed model outperforms existing methods in evidence localization and answer generation.

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