Papers by Tianyu Zhu

15 papers
Large Language Models are not Fair Evaluators (2024.acl-long)

Copied to clipboard

Challenge: Existing evaluation frameworks that use large language models as referees are insufficient for accurately assessing their alignment with human intent.
Approach: They propose a calibration framework to address positional bias in large language models as evaluators by manually annotating the “win/tie/lose” outcomes of responses from ChatGPT and Vicuna-13B in the Vicun A Benchmark’s question prompt.
Outcome: The proposed framework alleviates evaluation bias, resulting in closer alignment with human judgments.
Robust Utility-Preserving Text Anonymization Based on Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing techniques face challenges of re-identification ability of large language models . anonymizing text that contains sensitive information is crucial for a wide range of applications .
Approach: They propose a framework that integrates three key LLM components to perform anonymization.
Outcome: The proposed model outperforms baselines while maintaining greater data utility in downstream tasks.
LaMP-Val: Large Language Models Empower Personalized Valuation in Auction (2025.findings-emnlp)

Copied to clipboard

Challenge: Currently, most research focuses on the bidding algorithms used within auction mechanisms.
Approach: They propose a personalized valuation framework that integrates Large Language Models to incorporate personalized semantic preference into users valuation process.
Outcome: The proposed framework incorporates Large Language Models to incorporate personalized semantic preference into users valuation process.
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation (2021.tacl-1)

Copied to clipboard

Challenge: Existing language representation models (PLMs) cannot capture factual knowledge from text.
Approach: They propose a unified model for Knowledge Embedding and Pre-trained LanguagERepresentation which integrates factual knowledge into PLMs and produces effective text-enhanced KE with the strong PLM.
Outcome: The proposed model improves on existing pre-trained language representation models and improves their performance on various NLP tasks.
Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning (2024.acl-long)

Copied to clipboard

Challenge: Experimental results show that fine-tuning of large language models for specific tasks can be challenging . distribution shift during fine-timing can lead to performance degradation in general task capabilities .
Approach: They propose a new approach that bridges the distribution gap between task datasets and LLMs by guiding fine-tuning with a distilled dataset generated by the model itself.
Outcome: The proposed approach achieves comparable or superior performance on downstream tasks compared to the vanilla approach.
InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have identified the severe performance decrease on analogous classes as a key factor for catastrophic forgetting.
Approach: They propose a replay-based continual text classification method that uses fast-slow and current-past contrastive learning to perform mutual information maximization and better recover previously learned representations.
Outcome: The proposed method achieves state-of-the-art on three text classification tasks.
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale (2025.acl-long)

Copied to clipboard

Challenge: Current instruction-tuning datasets focus on simplistic visual question answering tasks, and provide phrase-level answers without any intermediate rationales.
Approach: They propose to use open-source multimodal large language models to train MLLMs on a dataset with 12M instruction-response pairs to elicit CoT reasoning.
Outcome: The proposed model achieves state-of-the-art performance on benchmarks such as MathVerse, MMMU-Pro, and MuirBench, and gains improvements of up to 4% on non-reasoning-based benchmarks.
FewRel 2.0: Towards More Challenging Few-Shot Relation Classification (D19-1)

Copied to clipboard

Challenge: Few-shot domain adaptation and NOTA detection are two real-world challenges for few-shot relation classification models.
Approach: They propose a task to investigate two aspects of few-shot relation classification models . they build upon the FewRel dataset by adding a new test set in a different domain .
Outcome: The proposed task can evaluate few-shot domain adaptation and few- shot none-of-the-above detection on a new domain and NOTA relation choice.
Training Verifier to Assessing Complex Real-World Tool-Use Trajectories (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for training effective AI agents often resort to synthetic data generation.
Approach: They propose a plug-and-play framework for data quality control in tool-use scenarios . they construct a tool-verify dataset and release a benchmark to assess its performance .
Outcome: The proposed framework surpasses Qwen2.5-72B-Instruct on Tool-V-Bench and the previous APIGen-MT dataset.
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters (2026.acl-industry)

Copied to clipboard

Challenge: Existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck.
Approach: They propose a conversation starter generation system that generates personalized starters to guide users into conversation without explicit user intent.
Outcome: The proposed system improves user active days by +1.84 and click-through rate by +94.25 and has been deployed in production.
Faster and Better LLMs via Latency-Aware Test-Time Scaling (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing research has overlooked the efficiency of TTS from a latency-sensitive perspective.
Approach: They propose two approaches to achieve latency-optimal TTS by branch-wise parallelism and sequence-wise parallelism.
Outcome: The proposed approach achieves latency-optimal TTS for large models . branch-wise parallelism and sequence-wise parallelism are key approaches .
SARA: Unlocking Multilingual Knowledge in Mixture-of-Experts via Semantically Anchored Routing Alignment (2026.findings-acl)

Copied to clipboard

Challenge: Low-resource language tokens are often routed to different experts than those activated by high-resourced inputs, which hinders their efficacy in multilingual contexts.
Approach: They propose a framework to transfer specialized capabilities from high-resource languages as anchors to low-resourced languages by using a symmetric Jensen-Shannon constraint.
Outcome: The proposed framework outperforms standard instruction tuning on 5 low-resource languages and 3 benchmarks.
LIME: Less Is More for MLLM Evaluation (2025.findings-acl)

Copied to clipboard

Challenge: Existing MLLM benchmarks and unified evaluation frameworks cannot accurately and efficiently reflect the ability of MLMLs.
Approach: They propose a semi-automated benchmark curated using a pipeline that filters out uninformative samples and eliminates answer leakage by focusing on tasks that require image-based understanding.
Outcome: The proposed benchmark reduces the number of samples by 76% and evaluation time by 77% while it can more effectively distinguish different models’ abilities.
History-Aware Conversational Dense Retrieval (2024.findings-acl)

Copied to clipboard

Challenge: Current approaches for conversational dense retrieval rely on fine-tuning a pre-trained ad-hoc retriever, which can be lengthy and noisy.
Approach: They propose a context-denoised query reformulation and automatic mining of supervision signals based on historical turns.
Outcome: The proposed system improves on two public conversational search datasets.
MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine Translation (2025.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have demonstrated strong performance even with limited parallel data.
Approach: They propose a multiple language-aware LoRA knowledge transfer framework that selectively adapts LLMs to MT by transferring knowledge from a large teacher to a small student model.
Outcome: The proposed framework outperforms baseline models on multilingual language pairs by +1.7 BLEU on average.

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