Papers by Kai Tian

15 papers
Rethinking Data Selection at Scale: Random Selection is Almost All You Need (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing data selection techniques are designed for small data pools, a study finds . filtering data by token length is an efficient method for improving results .
Approach: They use self-scoring methods that do not rely on external help to perform fine-tuning . they also find that filtering data by token length offers a stable and efficient method .
Outcome: The proposed methods outperform random selection on large datasets on large data pools.
AGD: Adversarial Game Defense Against Jailbreak Attacks in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Existing defenses, including post-training alignment and prompt engineering, struggle with adaptability to out-of-distribution (OOD) attacks.
Approach: They propose an adversarial game-based defense method that dynamically adjusts LLMs’ internal representations to achieve a balanced trade-off between helpfulness and harmlessness.
Outcome: The proposed method improves LLMs’ safety over all baselines.
ReviewRL: Towards Automated Scientific Review with RL (2025.emnlp-main)

Copied to clipboard

Challenge: Existing automated review systems struggle with factual accuracy, rating consistency, and analytical depth.
Approach: They propose a framework for generating comprehensive and factually grounded scientific paper reviews using supervised fine-tuning and reinforcement learning.
Outcome: The proposed framework outperforms existing methods on ICLR 2025 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.
A Fast and High-quality Text-to-Speech Method with Compressed Auxiliary Corpus and Limited Target Speaker Corpus (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to generate high-quality speech with limited target speaker corpus require extensive training data.
Approach: They propose an auxiliary corpus compression algorithm that reduces the training cost while the naturalness of synthesized speech is not significantly degraded.
Outcome: The proposed method significantly reduces training costs while maintaining the naturalness of synthesized speech.
Self-Improvement in Multimodal Large Language Models: A Survey (2025.findings-emnlp)

Copied to clipboard

Challenge: Using data and data, self-improvement for Large Language Models has improved model capabilities without significantly increasing costs.
Approach: This survey provides a comprehensive overview of self-improvement for Large Language Models . it includes commonly used evaluations and downstream applications .
Outcome: The authors provide a comprehensive overview of self-improvement in Multimodal LLMs.
CLUE: A Chinese Language Understanding Evaluation Benchmark (2020.coling-main)

Copied to clipboard

Challenge: Existing language evaluation benchmarks for English are limited to English . lack of such benchmarks makes it difficult to replicate success in other languages .
Approach: They introduce a large-scale Chinese language understanding evaluation benchmark . the benchmark uses a set of current state-of-the-art pre-trained Chinese models .
Outcome: The first large-scale Chinese Language Understanding Evaluation (CLUE) benchmark is released . the benchmark evaluates models across a wide range of tasks on original Chinese text . existing language evaluation benchmarks are mostly limited to English .
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process (2025.acl-long)

Copied to clipboard

Challenge: Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models with human preferences post pre-training.
Approach: They propose to combine Supervised Fine-Tuning and Preference Optimization (PO) with two sub-processes defined at token level within the Markov Decision Process (MDP)
Outcome: The proposed process performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities.
SDAR: A Synergistic Diffusion-AutoRegression Paradigm for Scalable Sequence Generation (2026.findings-acl)

Copied to clipboard

Challenge: Autoregressive (AR) language models are a dominant paradigm in the field of parallelism and non-causal modeling.
Approach: They propose a blockwise discrete diffusion model that preserves AR-compatible serving while enabling parallel intra-block generation.
Outcome: The proposed model achieves theoretical speedups over 5 and wall-clock speedup of 2.3 on H200 GPUs in latency-critical regimes.
BSCodec: A Band-Split Neural Codec for High-Quality Universal Audio Reconstruction (2026.findings-eacl)

Copied to clipboard

Challenge: Neural audio codecs have enabled high-fidelity reconstruction of speech, music and sound . however, speech-optimized codec systems suffer degradation on music or sound if they ignore spectral differences .
Approach: They propose a neural audio codec that splits the spectral dimension into separate bands and compresses each band independently.
Outcome: Experimental results show that BSCodec achieves better reconstruction quality on music and sound compared to existing codecs.
Training Language Models to Critique With Multi-agent Feedback (2025.findings-emnlp)

Copied to clipboard

Challenge: utilizing human annotations can enhance critique ability, but model-generated critiques suffer from inherent flaws due to complexity of critique . a new framework that leverages multi-agent feedback improves critique ability .
Approach: They propose a framework that leverages multi-agent feedback to improve critique ability . they propose to use supervised fine-tuning and reinforcement learning to improve this capability .
Outcome: The proposed framework improves critique ability in both supervised fine-tuning and reinforcement learning stages.
Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations treat visual understanding and generation in isolation or overlook tasks that inherently couple them.
Approach: They propose a benchmark that examines the bidirectional synergy between generation and understanding across eight reasoning-centric domains.
Outcome: The proposed model systematically unfolds the bidirectional synergy between generation and understanding across eight reasoning-centric domains.
League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, but reliable evaluation remains a challenge due to data contamination, opaque operation, and subjective preferences.
Approach: They propose a benchmark-free evaluation paradigm that organizes multiple LLMs into a self-governed league for multi-round mutual evaluation.
Outcome: Experiments on eight mainstream LLMs in mathematics and programming show that the proposed model can distinguish capabilities while maintaining high internal ranking stability.
DPGA-TextSyn: Differentially Private Genetic Algorithm for Synthetic Text Generation (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to fine-tune large language models pose privacy risks . researchers have synthesized data with strong generation capabilities closed-source LLMs to alleviate this problem .
Approach: They propose to combine general LLMs with genetic algorithm to produce relevant and diverse synthetic text under differential privacy constraints.
Outcome: The proposed method significantly improves the performance of the model in downstream tasks while ensuring privacy.
Multi-Domain Dialogue Acts and Response Co-Generation (2020.acl-main)

Copied to clipboard

Challenge: Existing pipeline approaches for task-oriented dialogue systems tend to predict multiple dialogue acts first and use them to assist response generation.
Approach: They propose a neural co-generation model that generates dialogue acts and responses concurrently and preserves semantic structures of multi-domain dialogue acts.
Outcome: The proposed model improves over state-of-the-art models in automatic and human evaluations on a large-scale dataset.

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