Papers by Xia Zeng

9 papers
LLM-Rec: Personalized Recommendation via Prompting Large Language Models (2024.findings-naacl)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have showcased their remarkable ability to harness commonsense knowledge and reasoning.
Approach: They propose a novel approach which incorporates four distinct prompting strategies of text enrichment for improving personalized text-based recommendations.
Outcome: The proposed approach improves recommendation quality and even basic MLP models achieve comparable or even better results than complex content-based methods.
MAPLE: Micro Analysis of Pairwise Language Evolution for Few-Shot Claim Verification (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods for verification of claims are limited by the availability of labeled data.
Approach: They propose a method that explores the alignment between a claim and its evidence using a seq2seq model and a novel semantic measure.
Outcome: The proposed method shows significant performance improvements over baselines SEED, PET and LLaMA 2 across three fact-checking datasets.
MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct (2025.findings-acl)

Copied to clipboard

Challenge: a new framework for image-text instruction data evolution improves MLLM performance . lack of high-quality instruction data remains a major bottleneck in ML modeling .
Approach: They propose a multimodal instruction data evolution framework that iteratively enhances data quality through fine-grained perception, cognitive reasoning, and interaction evolution.
Outcome: The proposed approach improves MLLM performance in nine vision-language tasks while using significantly less data.
SimpleOCR: Rendering Visual Questions to Teach MLLMs to Read (2026.findings-acl)

Copied to clipboard

Challenge: MLLMs lack visual grounding mechanism to read text embedded in images, or rely on parametric shortcuts . despite strong OCR capabilities, models suffer performance degradation of 12.7% in the VQ setting .
Approach: They propose a plug-and-play training strategy that invalidates shortcuts in text prompts . they propose 'vq' setting where text queries are rendered directly onto images .
Outcome: The proposed training strategy surpasses the base model by 5.4% and GRPO based on original images by 2.7% on four representative OOD benchmarks.
What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? (2024.naacl-long)

Copied to clipboard

Challenge: Recent advances in GPT-4V have demonstrated remarkable multi-modal capabilities in processing image inputs and following open-ended instructions.
Approach: They propose a plug-and-play technique to enhance multi-modal LLMs . they propose 'lynx' to train multi-modal LLM models .
Outcome: The proposed training strategy improves understanding accuracy and instruction-following proficiency of multi-modal models.
VisFinEval: A Scenario-Driven Chinese Multimodal Benchmark for Holistic Financial Understanding (2025.emnlp-main)

Copied to clipboard

Challenge: Existing benchmarks focus on text comprehension, but MLLMs lack the ability to integrate visual data over financial visuals.
Approach: They evaluate 21 state-of-the-art multimodal large language models in a zero-shot setting . they use an annotated question–answer pair from eight common financial image modalities .
Outcome: The new benchmark outperforms existing models but trailed financial experts by 14 percentage points.
RShield: A User-level Traceable Backdoor Watermark for LLMs in Embedding-as-a-Service (2026.findings-acl)

Copied to clipboard

Challenge: Existing backdoor watermarking techniques are limited to zero-bit detection . RShield enables reliable user-level attribution of large language models under model extraction attacks.
Approach: They propose a multi-bit backdoor watermarking technique that enables reliable user-level attribution of large language models under model extraction attacks.
Outcome: RShield achieves 100% multi-bit watermark recovery and high semantic fidelity under model extraction attacks compared to existing methods.
Active PETs: Active Data Annotation Prioritisation for Few-Shot Claim Verification with Pattern Exploiting Training (2023.findings-eacl)

Copied to clipboard

Challenge: Recent work on few-shot classification has addressed the issue of data prioritisation of unlabelled data.
Approach: They propose a weighted approach that uses a set of pattern-exploiting training models to actively select unlabelled data as candidates for annotation.
Outcome: The proposed approach shows consistent improvement over baseline methods on two technical fact-checking datasets and using six different pretrained language models.
Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards (2026.acl-industry)

Copied to clipboard

Challenge: a large language model (LLM) is used as a business development agent for persuasive price negotiation in online travel agencies.
Approach: They propose a reward-enhancing policy optimization method that integrates three complementary reward sources-a preference-trained reward model and an LLM-as-a-judge.
Outcome: The proposed method improves average dialogue rating to 4.63 (+0.33 over GRPO) and raises share of conversations with at least one excellent response to 66.67% (+23.34 pp over grepo).

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