Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling.

[BibT_eX]

[DOI]

Yiwen Ding

Zhiheng Xi

Wei He

Lizhuoyuan Lizhuoyuan

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Earlier Tokens Contribute More: Learning Direct Preference Optimization From Temporal Decay Perspective.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

AgentRefine: Enhancing Agent Generalization through Refinement Tuning.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

A Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuning.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

ReMamba: Equip Mamba with Effective Long-Sequence Modeling.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

FIRE: Flexible Integration of Data Quality Ratings for Effective Pretraining.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversity.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoning.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Too Consistent to Detect: A Study of Self-Consistent Errors in LLMs.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Instance-level Randomization: Toward More Stable LLM Evaluations.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

LLMs Know What They Need: Leveraging a Missing Information Guided Framework to Empower Retrieval-Augmented Generation.

[BibT_eX]

[DOI]

Proceedings of the 31st International Conference on Computational Linguistics, 2025

Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI Collaboration.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

AMoPO: Adaptive Multi-objective Preference Optimization without Reward Models and Reference Models.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and Insights.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Don't Half-listen: Capturing Key-part Information in Continual Instruction Tuning.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Multi-Programming Language Sandbox for LLMs.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations), 2025

Revisit Self-Debugging with Self-Generated Tests for Code Generation.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2025

S^3cMath: Spontaneous Step-Level Self-Correction Makes Large Language Models Better Mathematical Reasoners.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

Enhancing LLMs via High-Knowledge Data Selection.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

Ltri-LLM: Streaming Long Context Inference for LLMs with Training-Free Dynamic Triangular Attention Pattern.

[BibT_eX]

[DOI]

CoRR, 2024

Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision.

[BibT_eX]

[DOI]

CoRR, 2024

Mitigating Tail Narrowing in LLM Self-Improvement via Socratic-Guided Sampling.

[BibT_eX]

[DOI]

CoRR, 2024

Multi-Programming Language Sandbox for LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

EPS-MoE: Expert Pipeline Scheduler for Cost-Efficient MoE Inference.

[BibT_eX]

[DOI]

CoRR, 2024

LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning.

[BibT_eX]

[DOI]

CoRR, 2024

Length Desensitization in Directed Preference Optimization.

[BibT_eX]

[DOI]

CoRR, 2024

How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data.

[BibT_eX]

[DOI]

CoRR, 2024

S3c-Math: Spontaneous Step-level Self-correction Makes Large Language Models Better Mathematical Reasoners.

[BibT_eX]

[DOI]

CoRR, 2024

EAGLE: Elevating Geometric Reasoning through LLM-empowered Visual Instruction Tuning.

[BibT_eX]

[DOI]

CoRR, 2024

What's Wrong with Your Code Generated by Large Language Models? An Extensive Study.

[BibT_eX]

[DOI]

CoRR, 2024

Parallel Decoding via Hidden Transfer for Lossless Large Language Model Acceleration.

[BibT_eX]

[DOI]

CoRR, 2024

Unraveling the Mystery of Scaling Laws: Part I.

[BibT_eX]

[DOI]

CoRR, 2024

What Makes Quantization for Large Language Models Hard? An Empirical Study from the Lens of Perturbation.

[BibT_eX]

[DOI]

CoRR, 2024

DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning.

[BibT_eX]

[DOI]

CoRR, 2024

FIRP: Faster LLM Inference via Future Intermediate Representation Prediction.

[BibT_eX]

[DOI]

Proceedings of the Natural Language Processing and Chinese Computing, 2024

Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Hallu-PI: Evaluating Hallucination in Multi-modal Large Language Models within Perturbed Inputs.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

How Do Your Code LLMs perform? Empowering Code Instruction Tuning with Really Good Data.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Not All Contexts Are Equal: Teaching LLMs Credibility-aware Generation.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Rethinking the Reversal Curse of LLMs: a Prescription from Human Knowledge Reversal.

[BibT_eX]

[DOI]

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Beyond the Known: Investigating LLMs Performance on Out-of-Domain Intent Detection.

[BibT_eX]

[DOI]

Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

Pattern Shifting or Knowledge Losing? A Forgetting Perspective for Understanding the Effect of Instruction Fine-Tuning.

[BibT_eX]

[DOI]

Proceedings of the Chinese Computational Linguistics - 23rd China National Conference, 2024

DolphCoder: Echo-Locating Code Large Language Models with Diverse and Multi-Objective Instruction Tuning.

[BibT_eX]

[DOI]

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Learning or Self-aligning? Rethinking Instruction Fine-tuning.

[BibT_eX]

[DOI]

Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

Speculative Decoding via Early-exiting for Faster LLM Inference with Thompson Sampling Control Mechanism.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2024

Graph-Structured Speculative Decoding.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2024

What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression.

[BibT_eX]

[DOI]

CoRR, 2023

Stochastic Feature Averaging for Learning with Long-Tailed Noisy Labels.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

Progressive Event Alignment Network for Partial Relevant Video Retrieval.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Multimedia and Expo, 2023

APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Large Language Models Meet Open-World Intent Discovery and Recognition: An Evaluation of ChatGPT.

[BibT_eX]

[DOI]

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2023

Retrieval-based Knowledge Transfer: An Effective Approach for Extreme Large Language Model Compression.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

Improving Input-label Mapping with Demonstration Replay for In-context Learning.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2023, 2023

2022

Dialogue Topic Segmentation via Parallel Extraction Network with Neighbor Smoothing.

[BibT_eX]

[DOI]

Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022

Structure-Aware Semantic-Aligned Network for Universal Cross-Domain Retrieval.

[BibT_eX]

[DOI]

Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022

Instance-Level Semantic Alignment for Zero-Shot Cross-Modal Retrieval.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Multimedia and Expo, 2022

GTLR: Graph-Based Transformer with Language Reconstruction for Video Paragraph Grounding.

[BibT_eX]

[DOI]

Proceedings of the IEEE International Conference on Multimedia and Expo, 2022

Deep Graph Mutual Learning for Cross-domain Recommendation.

[BibT_eX]

[DOI]

Proceedings of the Database Systems for Advanced Applications, 2022

Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Distant Supervision based Machine Reading Comprehension for Extractive Summarization in Customer Service.

[BibT_eX]

[DOI]

Proceedings of the SIGIR '21: The 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2021

Domain-Lifelong Learning for Dialogue State Tracking via Knowledge Preservation Networks.

[BibT_eX]

[DOI]

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021

Density-Based Dynamic Curriculum Learning for Intent Detection.

[BibT_eX]

[DOI]

Proceedings of the CIKM '21: The 30th ACM International Conference on Information and Knowledge Management, Virtual Event, Queensland, Australia, November 1, 2021

From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding.

[BibT_eX]

[DOI]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021

Xunliang Cai

Bibliography

Loading...