Papers by Yue Niu

13 papers
Ethos: Rectifying Language Models in Orthogonal Parameter Space (2024.findings-naacl)

Copied to clipboard

Challenge: Language models (LMs) generate toxic, biased content and reveal private training records.
Approach: They propose an efficient approach that rectifies LMs to mitigate toxicity and bias . Ethos distinguishes general beneficial and undesired knowledge when reconstructing task vectors .
Outcome: The proposed approach mitigates toxicity and bias in outputs and avoids privacy leakage.
Small Models Struggle to Learn from Strong Reasoners (2025.findings-acl)

Copied to clipboard

Challenge: a small learning gap exists between large and small language models . long CoT data and large model responses are not beneficial for small models - a problem that may be due to the small student model's ability to handle distribution shifts.
Approach: They propose a mix distillation strategy that balances reasoning complexity by combining long and short CoT examples or reasoning from both larger and smaller models.
Outcome: The proposed strategy outperforms training on large and small models on short CoT and small model CoT.
ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to multi-turn dialogues lack contextual consistency and dependencies, and models struggle to maintain factual faithfulness as interaction turns increase.
Approach: They propose an adaptive context refactoring framework that monitors and reshapes the interaction history to mitigate contextual inertia and state drift.
Outcome: The proposed model outperforms baselines while reducing token consumption.
Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches typically assume access to ground-truth labeled data . Existing methods require a classifier to select models given an input .
Approach: They propose a routing setting where routers are trained exclusively on generated queries and answers from LLMs.
Outcome: The proposed router outperforms the best query-answer router by 4.6% absolute accuracy when trained on weak generator data.
Machine Unlearning of Pre-trained Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Using curated datasets, we establish a robust benchmark for unlearning performance, demonstrating that these methods are over 105 times more computationally efficient than retraining.
Approach: They propose a framework for machine unlearning in pre-trained LLMs and integrate gradient ascent with gradient descent on in-distribution data to achieve robustness.
Outcome: The proposed framework is over 105 times more efficient than retraining on in-distribution data and provides detailed guidelines for efficient hyperparameter tuning in the unlearning process.
Can We Steer Reasoning Direction by Thinking Intervention? (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Reason Models suffer from overthinking and erroneous reasoning problems due to the lack of fine-grained control over their reasoning behaviors.
Approach: They propose a paradigm to enable fine-grained control over LRMs’ reasoning behaviors by aligning reasoning trajectories with specific cognitive patterns.
Outcome: The proposed paradigm achieves integration intervention throughout model reasoning processes.
RSDA: Restoring Stale Data Affinity via Dynamic Renovation Strategy for Mitigating Data Scarcity (2026.acl-long)

Copied to clipboard

Challenge: High-quality data is the cornerstone of advancing large language models, but the supply of premium data is nearing depletion, while vast stale corpora remain underutilized.
Approach: They propose a framework to restore stale data affinity by quantifying the latent value of samples and employing a dynamic renovation strategy selection mechanism to determine the optimal component-level strategy.
Outcome: The proposed framework achieves performance improvements using less than 10% of the data volume, underscoring that the latent potential of stale corpora remains largely untapped.
Temporal Sampling for Forgotten Reasoning in LLMs (2026.acl-long)

Copied to clipboard

Challenge: a new metric measures the percentage of questions that were answered incorrectly during fine-tuning .
Approach: They propose a decoding strategy that draws outputs from multiple checkpoints along the training trajectory.
Outcome: The proposed method improves reasoning performance and consistency across benchmarks.
KCVR: Knowledge-Centric Video Reconstruction for Structured Pedagogical Summarization via Dynamic Graph Planning (2026.acl-long)

Copied to clipboard

Challenge: Existing summarization methods compress content for gist browsing, but they break prerequisite logic in instructional videos.
Approach: They propose a framework that decouples epistemic planning from content generation.
Outcome: The proposed framework outperforms strong end-to-end baselines on Knowledge Progression Consistency and Learning Objective Coverage.
CFlowPsyD: An Analysis-Enhanced Dataset for Asynchronous Psychological Counseling through Self-Optimizing Multi-Agent Framework (2026.findings-acl)

Copied to clipboard

Challenge: Asynchronous psychological counseling (APC) is a crucial mental health service modality that transcends temporal and spatial constraints.
Approach: They propose a self-optimizing multi-agent framework for counseling dialogue generation, CFlowPsy, which utilizes real anonymized counseling cases as seed data to synthesize diverse problem-solving-oriented APC conversations through large language models.
Outcome: The proposed framework synthesizes diverse problem-solving-oriented APC conversations through large language models.
MelTrim: Coarse-to-Fine Data Pruning for Speech Classification (2026.findings-acl)

Copied to clipboard

Challenge: Unlike image or text classification, speech classification tasks are particularly challenging due to the difficulty in capturing the acoustic, semantic, and contextual representations.
Approach: They propose a dataset pruning method that coarsely filters redundant samples using DBSCAN clustering on Mel-Frequency Cepstral Coefficients (MFCC) features.
Outcome: The proposed method achieves 49.5% improvement in WA on the MEAD dataset and 41.9% reduction in EER on speaker identification tasks.
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines (2025.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are currently pre-trained and fine-tuned on large cloud servers . fine-timing on resource-constrained edge devices presents significant memory and computational demands .
Approach: They propose a resource-efficient fine-tuning framework for LLMs specifically designed for edge devices.
Outcome: Experiments show that MobiZO achieves substantial runtime speedups and memory savings while improving fine-tuning accuracy.
Learning to Generalize for Cross-domain QA (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for QA are hampered by increased training costs . current methods suffer significant performance degradation when applied to out-of-domain examples.
Approach: They propose a method that combines prompting methods and linear probing with fine-tuning strategy, which does not entail additional cost.
Outcome: The proposed method outperforms state-of-the-art baselines with an average increase in F1 score of 4.5%-7.9%.

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