Papers by Jiayi Ji

12 papers
CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to search for images using single-modality are limited by representation space fragmentation.
Approach: They propose a unified representation framework that achieves efficient query-target alignment . they introduce a multi-level Chain-of-Thought prompting strategy that guides MLMs to generate discriminative, semantically compatible captions for target images .
Outcome: The proposed framework achieves efficient query-target alignment through synergistic components.
“I See What You Did There”: Can Large Vision-Language Models Understand Multimodal Puns? (2026.acl-long)

Copied to clipboard

Challenge: Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor.
Approach: They propose a multimodal pun generation pipeline and a model to evaluate their understanding of puns.
Outcome: The proposed benchmark improves the understanding of multimodal puns by 16.5% in the F1 test.
Incorporating Causal Analysis into Diversified and Logical Response Generation (2022.coling-1)

Copied to clipboard

Challenge: Existing generation-based models generate generic and safe responses such as "So am I" or "I don't know"
Approach: They propose to predict the mediators to preserve relevant information and auto-regressively incorporate the mediator into generating process.
Outcome: The proposed model generates relevant and informative responses and outperforms the state-of-the-art in terms of automatic metrics and human evaluations.
SAME: Safety-Aware Model Editing Guided by Safety Transformation (2026.acl-long)

Copied to clipboard

Challenge: Existing models that update or insert new knowledge require sequential parameter updates while maintaining model capability.
Approach: They propose a model editing approach that estimates safety transforms and identifies corresponding safety direction in the neural activation space and aligns neural activations and network parameter updates under the safety constraints.
Outcome: The proposed approach reduces unsafe responses to malicious queries while preserving the effectiveness of model editing.
Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasks (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable abilities, but they invariably generate flawed responses.
Approach: They propose a self-correction approach that instructs VLMs to refine their outputs by allowing them to learn from their self-generated self-reference data without external feedback.
Outcome: The proposed approach enables VLMs to learn from their self-generated self-correction data without relying on external feedback, facilitating self-improvement.
DHP Benchmark: Are LLMs Good NLG Evaluators? (2025.findings-naacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly serving as evaluators in Natural Language Generation (NLG) tasks.
Approach: They propose a framework that measures the discernment of Large Language Models (LLMs) across diverse NLG tasks.
Outcome: The proposed framework provides quantitative discernment scores for LLMs across four NLG tasks.
Speculative Decoding for Multi-Sample Inference (2025.findings-emnlp)

Copied to clipboard

Challenge: Speculative decoding method exploits consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Approach: They propose a speculative decoding method that exploits the consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or external databases.
Outcome: The proposed method exploits the intrinsic consensus of parallel reasoning paths to synthesize high-quality draft tokens without auxiliary models or databases.
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.
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies on self-consistency show that it improves reasoning abilities by aggregating diverse stochastic samples.
Approach: They propose a confidence-driven mechanism that dynamically calibrates temperature to align with high probability modes.
Outcome: The proposed method outperforms fixed-diversity baselines on reasoning tasks and improves both average and best-case performance.
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.
MMAPS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization (2024.lrec-main)

Copied to clipboard

Challenge: Existing product summarization methods lack end-to-end product summaries and multi-grained multi-modal modeling.
Approach: They propose an end-to-end multi-grained multi-modal attribute-aware product summarization method that jointly models product attributes and generates product summaries.
Outcome: The proposed method outperforms state-of-the-art product summarization methods on a large-scale Chinese e-commence dataset.
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.

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