Papers by Tianqi Wang

15 papers
Attn-GS: Attention-Guided Context Compression for Efficient Personalized LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to personalize large language models (LLMs) rely on heuristic methods to compress user profiles but they ignore how LLMs process and prioritize different profile components.
Approach: They propose an attention-guided context compression framework that leverages attention feedback from a marking model to mark important personalization sentences and guides a compression model to generate task-relevant compressed user contexts.
Outcome: The proposed framework outperforms baselines across tasks, token limits, and settings while reducing token usage by 50 times.
DetectRL-X: Towards Reliable Multilingual and Real-World LLM-Generated Text Detection (2026.acl-long)

Copied to clipboard

Challenge: Existing detectors are limited in their ability to detect large language models generated content in multilingual environments.
Approach: They propose a multilingual benchmark to evaluate advanced detectors across 8 dimensions to better align with real-world applications.
Outcome: The proposed benchmark encompasses 8 languages commonly used in commercial contexts and collects human-written texts from 6 domains highly susceptible to LLM misuse.
SOLAR: Serendipity Optimized Language Model Aligned for Recommendation (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models have shown strong potential in recommendation tasks . however, their application to serendipity-oriented recommendations remains challenging .
Approach: They propose a domain-adaptive instruction tuning method that aligns Large Language Models with recommendation tasks.
Outcome: The proposed framework bridges the domain gap between LLMs and recommendation tasks.
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large Language (2025.acl-long)

Copied to clipboard

Challenge: Existing datasets for instruction-following are monolingual and centered on English . existing data are unable to capture linguistic and cultural subtle differences .
Approach: They propose an extension of IFEval to a localized multilingual version called Marco-Bench-MIF . their benchmark addresses linguistic constraints and cultural references via translation and verification .
Outcome: The proposed extension of IFEval to a localized multilingual version covers 30 languages with varying levels of localization.
RQT: Hierarchical Residual Quantization for Multi-Model Compression (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods for decomposing fine-tuned LLMs are sensitive to the magnitude of delta values.
Approach: They propose a hierarchical quantization framework that shares low-bit integer weights across similar models.
Outcome: The proposed framework achieves an average accuracy degradation of approximately 3% on fine-tuned models across mathematics, coding, chatbot, and Chinese LLMs.
pFedGPT: Hierarchically Optimizing LoRA Aggregation Weights for Personalized Federated GPT Models (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for fine-tuning Large Language Models (LLMs) struggle with data heterogeneity and adapt shared global knowledge to individual client needs.
Approach: They propose a framework that leverages Hierarchical Bayesian Optimization (HBO) for fine-grained, personalized LoRA aggregation.
Outcome: The proposed framework achieves state-of-the-art (SOTA) performance on personalized FL benchmarks while introducing only minimal (approx. 4%) additional optimization overhead.
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.
Q-Mamba: Towards more efficient Mamba models via post-training quantization (2025.findings-acl)

Copied to clipboard

Challenge: Existing studies show that Mamba architectures have room for further optimization in linear projections and state caches.
Approach: They propose a decoupled scale quantization scheme to mitigate outliers in states and channels by applying separate quantization scales.
Outcome: The proposed method reduces memory consumption by 50% across various quantization settings, model sizes, and generation and zero-shot tasks.
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.
Weighted Contrastive Learning With False Negative Control to Help Long-tailed Product Classification (2023.acl-industry)

Copied to clipboard

Challenge: Item categorization (IC) aims to classify a product into leaf nodes in a categorical taxonomy due to scarce supervision.
Approach: They propose to use K-positive contrastive loss (KCL) to address IC task’s long-tail issue by re-weighting positive pairs in the KCL loss with a regularization that the sum of weights should be constrained to K+1 as close as possible.
Outcome: The proposed method improves on the long-tail issue in the image classification task and when using text-based contrastive learning, it can be applied on the IC task.
Benchmarking and Improving Compositional Generalization of Multi-aspect Controllable Text Generation (2024.acl-long)

Copied to clipboard

Challenge: Existing MCTG methods face a noticeable performance drop in compositional testing.
Approach: They propose a benchmark to evaluate compositional generalization of MCTG methods by combining multi-aspect labeled datasets and a crafted three-dimensional evaluation protocol.
Outcome: The proposed framework improves compositional generalization performance by 3.64% and 94.4% in compositional testing.
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.
Air-Decoding: Attribute Distribution Reconstruction for Decoding-Time Controllable Text Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Controllable text generation (CTG) aims to generate text with desired attributes, but current methods lack high levels of controllability.
Approach: They propose a lightweight decoding framework that reconstructs attribute distributions to balance the weights between attribute words and non-attribute words to generate more fluent text.
Outcome: The proposed framework achieves state-of-the-art control performance on multiple CTG tasks.
Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models (2025.acl-long)

Copied to clipboard

Challenge: Recent efforts to distill large reasoning models into smaller lightweight models have shown competitive performances.
Approach: They propose to distill long Chain-of-Thought data to improve SFT and RL methods by constructing data from scratch using Monte Carlo Tree Search.
Outcome: The proposed method significantly improves reasoning performance on various benchmarks such as math (GSM8K, MATH, AIME).
Inject Rubrics into Short Answer Grading System (D19-61)

Copied to clipboard

Challenge: Short Answer Grading (SAG) is a task of scoring students’ answers in examinations. Existing SAG systems only predict scores based on the answers, but they ignore important evaluation criteria such as rubrics.
Approach: They propose to inject rubrics into SAG models by introducing word-level attention mechanism into the model to locate information in each answer that are highly related to the score.
Outcome: The proposed model outperforms the state-of-the-art model on the widely used ASAP-SAS dataset under low-resource settings.

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