Papers by Nakyeong Yang
FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledge (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for unlearning undesirable knowledge have overlooked complexity and interconnectedness of knowledge, authors say . previous studies have neglected the complex nature of knowledge and neglected its internal dependencies. |
| Approach: | They propose a new concept called superficial unlearning to evaluate faithfulness of unlearning in knowledge QA settings. |
| Outcome: | The proposed method shows significant effectiveness in real-world knowledge QA settings. |
How Training Data Shapes the Use of Parametric and In-Context Knowledge in Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models leverage parametric and in-context knowledge in training . however, when these sources conflict, models arbitrate based on their internal confidence . |
| Approach: | They conduct controlled experiments using synthetic corpora to identify data properties that shape knowledge utilization. |
| Outcome: | The results show that the robust use of both knowledge sources is an emergent property . the results provide guidance for designing training data that supports the reliability of parametric and in-context knowledge in language models. |
Mitigating Biases for Instruction-following Language Models via Bias Neurons Elimination (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods to mitigate undesirable biases in instruction-following language models are not effective in accelerating instruction-based learning. |
| Approach: | They propose a method to eliminate bias neurons of language models in instruction-following settings by defining the bias neuron and prove its existence empirically. |
| Outcome: | The proposed method dramatically increases the task performance of language models under zero-shot instruction-following settings without losing the model’s knowledge. |
Persona Switch: Mixing Distinct Perspectives in Decoding Time (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies show that role-play prompting improves zero-shot reasoning, but these improvements are inconsistent across tasks and instances. |
| Approach: | They propose a method that dynamically combines the benefits of both prompting strategies. |
| Outcome: | The proposed method outperforms baselines and shows that output confidence is an important measure for selecting the more reliable output. |
Task-specific Compression for Multi-task Language Models using Attribution-based Pruning (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing compression methods for multi-task language models use large number of parameter parameters even when performing only a specific task. |
| Approach: | They propose a training-free compression method for multi-task language models using pruning method . they use an attribution method to determine which neurons are essential for performing a specific task . |
| Outcome: | The proposed method outperforms baseline pruning methods on six widely-used datasets. |
Reliability-Aware Adaptive Self-Consistency for Efficient Sampling in LLM Reasoning (2026.findings-acl)
Copied to clipboard
| Challenge: | Self-consistency improves reasoning reliability but incurs substantial inference cost . Adaptive self-consistent methods rely on count-based stopping rules that treat all responses equally . |
| Approach: | They propose a method that reframs adaptive sampling from response counting to evidence sufficiency by leveraging response-level confidence. |
| Outcome: | The proposed method reduces inference cost by up to 70% while preserving accuracy on GSM8K. |
Avoidance Decoding for Diverse Multi-Branch Story Generation (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies have attempted to increase the diversity of generated texts through decoding-time methods. |
| Approach: | They propose a decoding strategy that penalizes similarity to previously generated logits to encourage more diverse multi-branch stories. |
| Outcome: | The proposed method achieves up to **2.6** times higher output diversity and reduces repetition by an average of 30% compared to strong baselines, while effectively mitigating text degeneration. |
Rethinking Post-Unlearning Behavior of Large Vision-Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to remove knowledge from large vision-Language Models often fail to provide quality and informative post-unlearning responses. |
| Approach: | They propose a task that requires models to provide privacy-preserving yet informative responses for LVLMs. |
| Outcome: | The proposed method reduces the risk of unlearning after naive suppression by providing informative and visually grounded responses. |