Papers by Jiaming Wang

33 papers
ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction (2026.findings-acl)

Copied to clipboard

Challenge: ProUIE improves universal information extraction (UIE) without external information . many LLM-based methods rely on extra schema cues, external resources or complex alignment and verification pipelines .
Approach: They propose a Macro-to-Micro progressive learning approach that improves UIE without external information.
Outcome: ProUIE outperforms instruction-tuned baselines on average for NER and RE while using a smaller backbone.
RealTalk-CN: A Realistic Chinese Speech Task-Oriented Dialogue Benchmark with Cross-Modal Analysis (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in speech large language models have enabled end-to-end spoken interactions, but their robustness in real-world applications remains unclear.
Approach: They propose a multi-turn, multi-domain speech–text TOD dataset for Chinese users . it contains 5.4k dialogues with annotations for dialogue states, disfluency types, speaker characteristics .
Outcome: The proposed model can be used to evaluate speech large language models in real-world scenarios . the proposed model is based on 5.4k real human-to-human dialogues with annotations .
A Survey of LLM-based Agents in Medicine: How far are we from Baymax? (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are transforming healthcare through their ability to understand and assist with medical tasks.
Approach: They analyze system profiles, clinical planning, medical reasoning frameworks, and external capacity enhancement.
Outcome: The findings highlight the future directions in medical reasoning, physical system integration, and training simulations.
DentalGPT: Incentivizing Multimodal Reasoning in Dentistry (2026.findings-acl)

Copied to clipboard

Challenge: Current multimodal large language models (MLLMs) show limited understanding of dental images.
Approach: They propose a dental-specialized multimodal large language model trained via staged multimodal alignment and reinforcement learning.
Outcome: The proposed model outperforms state-of-the-art models on disease classification and dental VQA tasks.
AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks evaluate agents in simplified, idealized settings, relying on pre-packaged tool interfaces, overlooking critical steps, and assume inputs are clean and fully specified.
Approach: They propose a framework that evaluates language agents in simplified, idealized settings . they show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
Outcome: Experiments on 15 proprietary and open-source models show that even SOTA systems like Gemini and GPT-5 struggle on AgentGym2 .
I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing (2026.acl-long)

Copied to clipboard

Challenge: Existing text-guided image editing methods rely on end-to-end pixel-level inpainting paradigm . existing models lack such intermediate representations and Reasoning-then-action process .
Approach: They propose a "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment.
Outcome: The proposed paradigm outperforms existing methods in compositional editing tasks.
QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to program repair are based on correctness alone.
Approach: They propose a framework that mitigates over-editing and improves repair accuracy by generating buggy programs and re-edits.
Outcome: The proposed framework improves repair precision by 31.4% under fix1@1, a metric that considers repair correctness and extent, and significantly increases decoding throughput when combined with speculative editing.
PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for hallucination evaluation rely on mixed queries and posterior evaluation, which quantifies hallucinosity severity but offers limited insight into where and why they occur.
Approach: They propose a controlled benchmark that disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors.
Outcome: The proposed model disentangles hallucinations into four dimensions: knowledge missing, knowledge errors, reasoning errors, and instruction-following errors.
ChildMandarin: A Comprehensive Mandarin Speech Dataset for Young Children Aged 3-5 (2025.acl-long)

Copied to clipboard

Challenge: Automatic speech recognition systems have advanced significantly with models like Whisper, Conformer, and self-supervised frameworks such as Wav2vec 2.0.
Approach: They propose to use Mandarin speech datasets to analyze pronunciation and tone of children aged 3 to 5 and evaluate their models on speaker verification (SV) They find that the datasets are more robust than those used by adult speech recognition systems and are open-source and available for all academic purposes.
Outcome: The proposed dataset includes 41.25 hours of speech with carefully crafted manual transcriptions, collected from 397 speakers across various provinces in China, with balanced gender representation.
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters (2023.acl-long)

Copied to clipboard

Challenge: Chain-of-Thought (CoT) prompting can dramatically improve the multi-step reasoning abilities of large language models (LLMs).
Approach: They propose to use Chain-of-Thought (CoT) prompting to encourage the LLM to generate intermediate rationales for solving a problem by providing a series of reasoning steps in the demonstrations.
Outcome: The proposed model can generate coherent lines of reasoning even with invalid demonstrations while still generating coherent lines during inference.
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Large Language Model (LLM) agents are expanding their action spaces to operate in complex environments.
Approach: They propose a server-side defense plugin that constrains tool acquisition via predictive reasoning regarding future safety risks.
Outcome: Experiments on PowerSeeking Bench, ToolEmu, and AgentHarm show that SafeMCP achieves a safe equilibrium, effectively mitigating risks while preserving agent utility.
AudioPrivacy: Parallel Audio Dataset for Speaker Profiling with Diverse Audio Types and Rich Attributes (2026.findings-acl)

Copied to clipboard

Challenge: Speech signals convey abundant speaker-related metadata, yet current privacy research focuses on identity-centric voiceprint protection, leaving sensitive Speaker Attribute Privacy (SAP) underexplored.
Approach: They propose a large-scale Chinese dataset to evaluate speaker-related privacy leakage . the dataset includes 227.3 hours of audio from 1,000 speakers .
Outcome: The proposed model systematically evaluates speaker-related privacy leakage in everyday scenarios.
Towards IP Intelligence: Benchmarking Large Language Models on Intellectual Property Knowledge and Practice (2026.findings-acl)

Copied to clipboard

Challenge: Existing datasets and benchmarks focus only on patents or cover limited aspects of the IP field, lacking alignment with real-world scenarios.
Approach: They propose a bilingual IP task taxonomy and a large-scale bilingual benchmark to evaluate LLMs in real-world IP practice.
Outcome: The proposed model achieves only 75.8% accuracy, indicating room for improvement . open-source IP and law-oriented models lag behind closed-source general-purpose models .
Probing Audio-Visual Reasoning in Multimodal Language Models through the Lens of Audio (2026.acl-long)

Copied to clipboard

Challenge: Recent multimodal large language models lack robust audio-visual integration ability and performance on DeafTest is highly correlated with AV-Odyssey accuracy.
Approach: They propose a benchmarking tool that integrates audio-visual reasoning with audio-video cues to infer solutions.
Outcome: The proposed model performs well on DeafTest, but lacks audio perception in simple audio tasks.
ChildTalk: A Multi-Dialect Chinese Child Speech Corpus with Full-Length Child–Caregiver Conversations for Speech Recognition (2026.findings-acl)

Copied to clipboard

Challenge: Automatic speech recognition (ASR) for children remains challenging due to developmental variability and the scarcity of high-quality corpora.
Approach: They propose a large-scale Chinese child speech corpus that contains 112.5 hours of speech from 498 children and 500 caregivers.
Outcome: The proposed model improves in-domain and cross-domain performance on children's speech.
TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting (2026.acl-long)

Copied to clipboard

Challenge: Existing models lack generalization capabilities and lack structured spatiotemporal data.
Approach: They propose a unified multi-task framework that synergizes spatiotemporal encoding with LLM reasoning through learnable prompt composition.
Outcome: The proposed framework outperforms baseline models on seven datasets and three tasks on supervised and zero-shot settings with excellent generalization and robustness.
LiPO: Listwise Preference Optimization through Learning-to-Rank (2025.naacl-long)

Copied to clipboard

Challenge: Recent work on language models with curated feedback provides promising alternatives to RLHF . multiple responses can be ranked by reward models or AI feedback, but there is no study on directly fitting upon a list of responses.
Approach: They propose a method that aligns language models with curated human feedback . they propose SLiC and DPO as promising alternatives to traditional RLHF .
Outcome: The proposed method outperforms DPO and SLiC on several preference alignment tasks with curated and real rankwise preference data.
DEGAP: Dual Event-Guided Adaptive Prefixes for Templated-Based Event Argument Extraction with Slot Querying (2025.coling-main)

Copied to clipboard

Challenge: Recent advances in event argument extraction (EAE) involve incorporating useful auxiliary information into models during training and inference.
Approach: They propose a method that uses two prefixes to learn from different events and templates.
Outcome: The proposed method achieves state-of-the-art performance on four datasets . it can leverage possible connections between different events and capture relevant information from the prefix .
PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs (2024.findings-acl)

Copied to clipboard

Challenge: Knowledge distillation (KD) is a technique for transferring expertise from large teacher models to compact student models with reduced memory footprints and inference costs.
Approach: They propose to transfer knowledge from large teacher models to compact student models by exploiting teacher-student capacity discrepancies to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.
Outcome: The proposed framework exploits teacher-student capacity discrepancy to generate pseudo-preference pairs where teacher outputs are preferred over student outputs.
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) excel at various tasks but are vulnerable to jailbreak attacks that induce harmful content generation.
Approach: They propose a reinforcement learning framework that leverages the model’s own discrimination capabilities as a reward signal to enhance generation safety through iterative self-improvement.
Outcome: The proposed framework improves model safety by iterative self-improvement without additional annotated data or external models during training phase.
Meeseeks: A Feedback-Driven, Iterative Self-Correction Benchmark evaluating LLMs’ Instruction Following Capability (2026.findings-acl)

Copied to clipboard

Challenge: Existing models lack the ability to adhere to instructions, resulting in suboptimal performance.
Approach: They propose an automated iterative instruction-following benchmark with integrated feedback mechanism.
Outcome: The proposed benchmark identifies erroneous components in model responses and provides feedback accurately.
EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations (2026.findings-acl)

Copied to clipboard

Challenge: Existing datasets face issues such as low quality, limited scale, and incomplete modalities, hindering model performance.
Approach: They propose to use Chinese multimodal datasets to capture authentic emotional interplay from 19 professional actors.
Outcome: The EmotionTalk dataset spans 23.6 hours of dyadic conversations across diverse scenarios.
SOP-Maze: Evaluating Large Language Models on Complicated Business Standard Operating Procedures (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are widely deployed as domain-specific agents, but evaluation of their capabilities in such contexts has not been fully explored.
Approach: They propose a benchmark to evaluate LLMs' ability to follow instructions and make decisions in real-world scenarios.
Outcome: The proposed benchmark is constructed from real-world business data and adapted into 23 complex SOP scenarios.
Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting (2024.findings-naacl)

Copied to clipboard

Challenge: Existing methods to rank documents using large language models do not understand these challenging ranking formulations.
Approach: They propose to use Pairwise Ranking Prompting to improve ranking performance . they propose to outperform fine-tuned baseline rankers on benchmark datasets .
Outcome: The proposed technique outperforms supervised baselines on benchmark datasets and outperformed other LLM-based solutions by over 10% on average.
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach: They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome: The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference (2025.acl-long)

Copied to clipboard

Challenge: Using large-scale annotation data, large language models can generate noise, errors and biases, leading to unexpected behaviours.
Approach: They propose a dataset to promote safety alignment in large language models . they separate helpfulness and harmlessness annotations for question-answering pairs .
Outcome: The proposed dataset provides 44.6k prompts and 265k question-answer pairs with safety meta-labels for 19 harm categories and three severity levels, with answers generated by Llama-family models.
Cascaded Mutual Modulation for Visual Reasoning (D18-1)

Copied to clipboard

Challenge: Visual reasoning is a multi-step and compositional problem that requires intensive text-vision interactions.
Approach: They propose a visual reasoning model that uses a feature-wise linear modulation technique to enable textual/visual pipelines to mutually control each other.
Outcome: The proposed model outperforms existing models on visual reasoning benchmarks CLEVR and NLVR . it can generate a textual answer to a visual question answering problem with images .
When Slower Isn’t Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: a study of slow reasoning models for multimodal reasoning finds that they are more prone to fabricating plausible yet false details when confronted with incomplete or misleading visual inputs.
Approach: They conduct the first systematic study of the inverse scaling law in slow-thinking paradigms for multimodal reasoning.
Outcome: The findings suggest that slower reasoning models are more prone to fabricating false details . the study analyzed 5,000-sample hierarchical prompt dataset by 50 participants .
Language Models Resist Alignment: Evidence From Data Compression (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) may exhibit undesirable behaviors due to the inevitable biases and harmful content present in training.
Approach: They propose to investigate the elasticity of large language models by examining their performance.
Outcome: The proposed model performance declines rapidly before reverting to the pre-training distribution, the authors show . the proposed model weight and code are available at pku-lm-res ist-alignment.github.io.
Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Recent years have witnessed significant advancements in large language models (LLMs) but still struggle with integrating vision and audio.
Approach: They propose a self-knowledge distillation method to improve vision-audio capabilities of OLLMs by learning from the vision-text components.
Outcome: The proposed method improves vision-audio capabilities of OLLMs by learning from vision-text components, which improves interaction between audio and images and results in improved performance on multimodal tasks.
LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domains (2025.findings-emnlp)

Copied to clipboard

Challenge: Evaluating 52 LLMs reveals that only the strongest models maintain robust performance under increasing context lengths and format diversity.
Approach: They propose a benchmark for evaluating long-context reasoning over semi-structured tables across diverse formats, tasks, and domains.
Outcome: The proposed model outperforms compression-based approaches on tasks requiring semantic integration.
Reward Generalization in RLHF: A Topological Perspective (2025.findings-acl)

Copied to clipboard

Challenge: Existing alignment methods share a common topology of information flow, but their alternatives have not been thoroughly explored.
Approach: They propose a theory of reward generalization in reinforcement learning from human feedback . they propose induced Bayesian networks to model the impact of dataset topologies on reward generalisation .
Outcome: The proposed method achieves an average win rate of 65% on three NLP tasks.
SpeechLLM-as-Judges: Towards General and Interpretable Speech Quality Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for evaluating the perceptual quality of synthetic speech are limited due to the complexity of perceptual quality factors and the diversity of speech generation tasks.
Approach: They propose a new paradigm for enabling large language models to conduct structured speech quality evaluation using a large-scale dataset.
Outcome: The proposed model performs well across tasks and languages.

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