Papers by Jinpeng Wang

25 papers
Enhancing Neural Data-To-Text Generation Models with External Background Knowledge (D19-1)

Copied to clipboard

Challenge: Recent neural models for data-to-text generation rely on parallel pairs of data and text to learn writing knowledge.
Approach: They propose to enhance neural models with external knowledge to improve fidelity of generated text.
Outcome: The proposed model improves on Wikipedia infobox-to-text datasets on 21 datasets.
Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for data-to-text generation use a large-scale training corpus to learn semantic correspondences between structured input data and associated texts.
Approach: They propose a local-to-global alignment framework that uses local and global models to learn semantic correspondences from large-scale datasets.
Outcome: The proposed framework can be generalized to restaurant and computer domains and improve alignment accuracy.
Evaluating Object Hallucination in Large Vision-Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Large vision-language models (LVLMs) suffer from object hallucinations, i.e., they tend to generate objects inconsistent with the target images in the descriptions.
Approach: They propose to integrate powerful large vision-language models (LVLMs) they propose a polling-based query method to evaluate object hallucination .
Outcome: The proposed model can evaluate object hallucination in a more stable and flexible way.
Representation Degeneration Problem in Prompt-based Models for Natural Language Understanding (2024.lrec-main)

Copied to clipboard

Challenge: Prompt-based fine-tuning (PF) models have shown improved performance on few-shot natural language understanding benchmarks.
Approach: They propose a framework to alleviate anisotropy in the embedding space by aligning with pre-trained language models' training objective.
Outcome: The proposed method outperforms mainstream methods on many NLU benchmarks.
Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for full-attention dLLMs rely on random masking strategies that overlook intrinsic token dependencies.
Approach: They propose an attention-guided denoising and optimization framework that aligns training and optimization with attention-derived dependencies.
Outcome: The proposed framework outperforms state-of-the-art methods on mathematical and coding benchmarks.
Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data (D18-1)

Copied to clipboard

Challenge: Existing work on grounded language learning does not capture the semantics of correspondences between structured world state representations and texts.
Approach: They propose to learn explicit latent semantic annotations from paired structured tables and texts . they use an adapted semi-hidden Markov model to impose a soft constraint to further improve performance .
Outcome: The proposed framework improves on a semi-hidden Markov model and extracts templates for language generation.
SEAD: Self-Evolving Agent for Multi-Turn Service Dialogue (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models have demonstrated remarkable capabilities in open-domain dialogues, but their performance in service dialogues remains suboptimal.
Approach: They propose a framework that enables agents to learn effective strategies without large-scale human annotations.
Outcome: The proposed framework decouples user modeling into two components that provide adaptive training scenarios rather than acting as an unfair adversary.
Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses (2026.acl-long)

Copied to clipboard

Challenge: Culture is a fundamental determinant of human affective processing and affective perceptions are often limited by declarative knowledge or established societal customs.
Approach: They propose a multimodal benchmark that leverages LLM-generated provisional labels to isolate cross-cultural emotional distinctions.
Outcome: The proposed benchmark captures cross-cultural emotional distinctions and derives reliable ground-truth annotations through human evaluation.
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason (2026.acl-long)

Copied to clipboard

Challenge: Reinforcement learning with verifiable rewards (RLVR) approaches face two challenges: the near-miss reward problem and exploration stagnation.
Approach: They propose an algorithm that partitions valid reasoning chains into reasoning steps using multi-level stepwise hints.
Outcome: The proposed method outperforms competing RLVR enhancement methods across six mathematical benchmarks and two out-of-domain benchmarks.
PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics (2026.findings-acl)

Copied to clipboard

Challenge: Mental disorders affect nearly one in seven people worldwide, yet the vast majority do not receive adequate care.
Approach: They propose a framework to evaluate LLMs' ethical knowledge and behavioral responses through multiple-choice and open-ended tasks with fine-grained ethicality annotations.
Outcome: Empirical results across 14 models reveal that refusal rates are poor indicators of ethical behavior, revealing a significant divergence between safety triggers and clinical appropriateness.
WebUncertainty: Dual-Level Uncertainty Driven Planning and Reasoning For Autonomous Web Agent (2026.findings-acl)

Copied to clipboard

Challenge: Existing web agents struggle with complex tasks due to rigid planning strategies and hallucination-prone reasoning.
Approach: They propose a task-uncertainty-driven Adaptive Planning Mechanism that adaptively selects planning modes to navigate unknown environments.
Outcome: The proposed framework performs better on the WebArena and WebVoyager benchmarks than existing frameworks.
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and Refinement (2025.acl-long)

Copied to clipboard

Challenge: GigaSpeech 2 is a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages.
Approach: They propose a large-scale, multi-domain, multilingual speech recognition corpus for low-resource languages and an automated pipeline for data crawling, transcription, and label refinement.
Outcome: The proposed corpus reduces the word error rate for Thai, Indonesian, and Vietnamese on a realistic YouTube test set by 25% to 40% compared to Whisper large-v3.
Operation-guided Neural Networks for High Fidelity Data-To-Text Generation (D18-1)

Copied to clipboard

Challenge: Recent neural models for data-to-text generation generate descriptions that are not consistent with structured data.
Approach: They propose a framework for data-to-text generation that uses symbolic operations to generate texts from structured data.
Outcome: The proposed framework improves the fidelity of the generated texts to the input structured data.
GenDis: Generative-Discriminative Dual-View Co-Training for Generalized Category Discovery (2026.acl-long)

Copied to clipboard

Challenge: Existing methods rely on one-hot discriminative supervision, leading to overfitting on seen classes and poor generalization to unseen ones.
Approach: They propose a Generative–Discriminative Dual-View Co-Training framework that unifies discriminative classification and semantic label generation within an LLM.
Outcome: The proposed framework outperforms existing methods on five benchmarks on the generalized category discovery (GCD) task.
Easy First Relation Extraction with Information Redundancy (D19-1)

Copied to clipboard

Challenge: Existing relation extraction models make decisions globally using integer linear programming . Existing approaches require time and memory to encode redundant information for ILP .
Approach: They propose an easy first approach for relation extraction with information redundancies embedded in local sentence extractors to resolve conflict decisions with domain and uniqueness constraints.
Outcome: The proposed approach outperforms both ILP and neural network-based methods in relation extraction (RE) studies have shown that the proposed approach improves the efficiency and accuracy of RE models.
Data2Text Studio: Automated Text Generation from Structured Data (D18-2)

Copied to clipboard

Challenge: Data2Text Studio is a platform for automated text generation from structured data.
Approach: They conduct experiments on RotoWire datasets for template extraction and text generation . they find that the Semi-HMMs model improves interactivity and interpretability .
Outcome: The proposed model improves on template extraction and text generation tasks on RotoWire datasets.
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholds (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods neglect stylistic modeling and rely on static thresholds, which greatly limits the detection performance.
Approach: They propose a framework that enables stylistics-aware uncertainty quantification through conditional threshold estimation.
Outcome: The proposed framework achieves an average improvement 11.34% in detection performance compared to baselines.
A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation (P19-1)

Copied to clipboard

Challenge: Recent neural language generation systems often hallucinate contents when trained on loosely corresponding pairs of the input structure and text.
Approach: They propose to integrate a language understanding module for data refinement with self-training iterations to induce strong equivalence between the input data and the paired text.
Outcome: Experiments on the E2E challenge dataset show that the proposed framework reduces relative unaligned noise by 50% compared with the current state-of-the-art ensemble generator.
VSTAR: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions (2023.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for video-grounded dialogues neglect the intrinsic attributes of multimodal dialogues, such as scene and topic transitions.
Approach: They propose to use a large scale video-grounded scene&topic AwaRe dialogue dataset to study video-based dialogue understanding.
Outcome: The proposed dataset shows that multimodal information and segments are important in video-grounded dialogue understanding and generation.
Disambiguated Lexically Constrained Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Challenge: Current approaches to LCNMT assume that pre-specified lexicon constraints are contextually appropriate.
Approach: They propose a framework that disambiguates constraints based on contexts at first and integrates them into LCNMT.
Outcome: The proposed approach outperforms baseline approaches on benchmark datasets and comprehensive experiments in multiple target constraints.
What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning (2025.coling-main)

Copied to clipboard

Challenge: Experimental results show that visual instruction tuning improves performance of Multi-modal Large Language Models (MLLMs) to extend the application scope of Large Language Modells, a surge of work augments LLMs with vision encoders to endow the ability of multi-modal cognition and reasoning.
Approach: They propose a systematic approach to create high-quality visual reasoning instructions using a synthesize-complicate-reformulate paradigm.
Outcome: The proposed method improves performance of MLLMs by 27.86% and 27.60% on MME-Perception and MME Cognition.
From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal large language models struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive efficiency.
Approach: They propose a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory that structures memory hierarchically into a *Sensory Buffer*, *Episodic Stream*, and *Symbolic Schema*.
Outcome: The proposed architecture achieves state-of-the-art on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization.
Modeling Uncertainty in Composed Image Retrieval via Probabilistic Embeddings (2025.acl-long)

Copied to clipboard

Challenge: Composed Image Retrieval (CIR) combines text and reference images to search for images . metric learning methods that focus on point embeddings fail to capture uncertainty in input data .
Approach: They propose a framework that captures uncertainty in images and queries by Gaussian distributions in latent space rather than fixed points.
Outcome: Experiments show that the proposed framework quantifies quality and semantic uncertainties . it can handle polysemy and ambiguity in search intentions, authors say .
Psyche-R1: Towards Reliable Psychological LLMs through Unified Empathy, Expertise, and Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Recent reasoning-augmented LLMs have demonstrated impressive capabilities across a wide range of domains owing to their exceptional text understanding capabilities.
Approach: They propose a Chinese psychological LLM that integrates empathy, psychological expertise, and reasoning.
Outcome: The proposed model produces over 75k high-quality psychological questions paired with detailed rationales, generated through and iterative prompt-rationale optimization procedure, along with 73k empathetic dialogues.
See the Forest for the Trees: Loosely Speculative Decoding via Visual-Semantic Guidance for Efficient Inference of Video LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for video understanding suffer from autoregressive generation of tokens.
Approach: They propose a training-free loosely SD framework for Video-LLMs that uses visual-relevant tokens to accurately pinpoint the latter.
Outcome: The proposed framework boosts the accepted length and speedup ratio by 136% and 35% compared to SOTA training-free SD methods for Video-LLMs.

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