Papers by Yong Pan

12 papers
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot (2025.findings-emnlp)

Copied to clipboard

Challenge: In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs).
Approach: They introduce CoT to exemplars of ICL to enhance the reasoning capability . however, it remains unclear whether CoT exemplar is still beneficial for recent, stronger models in such tasks.
Outcome: The enhanced exemplars fail to improve the model’s reasoning performance, despite being constructed using answers from advanced models such as Qwen2.5-Max and DeepSeek-R1.
Trigger-Argument based Explanation for Event Detection (2023.findings-acl)

Copied to clipboard

Challenge: Existing works on ED use words or phrases to explain models’ inner mechanisms, but for ED, the event structure is more enlightening clues to explain model behaviors.
Approach: They propose a Trigger-Argument based Explanation method which can utilize event structure knowledge to uncover a faithful interpretation for existing ED models at neuron level.
Outcome: The proposed method can reveal the process by which the model predicts on the large-scale MAVEN and the widely-used ACE 2005 datasets.
The Instinctive Bias: Spurious Images lead to Illusion in MLLMs (2024.emnlp-main)

Copied to clipboard

Challenge: Existing multi-modal large language models (MLLMs) are able to process visual inputs by converting them into visual tokens that share the same latent space as language tokens in LLMs.
Approach: They propose a benchmark that assesses the visual illusion level given spurious images and a pipeline that converts visual inputs into visual tokens.
Outcome: The proposed benchmark shows that MLLMs suffer from an instinctive bias to varying degrees when presented with spurious images.
Mitigating the Alignment Tax of RLHF (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) acquire a wide range of abilities during pre-training, but aligning LLMs under Reinforcement Learning with Human Feedback (RLHF) can lead to forgetting pretrained abilities, which is also known as the alignment tax.
Approach: They propose to use a model averaging technique to find the most powerful alignment-forging Pareto front among RLHF algorithms.
Outcome: The proposed method achieves the strongest alignment-forging Pareto front among competing methods.
Leveraging Only the Category Name for Aspect Detection through Prompt-based Constrained Clustering (2022.findings-emnlp)

Copied to clipboard

Challenge: Aspect category detection (ACD) aims to automatically identify user-concerned aspects from online reviews.
Approach: They propose a method that relies on the category name of each aspect and a pretrained language model to generate constraints for clustering.
Outcome: The proposed framework performs better than existing weakly supervised methods on nine benchmark datasets.
Event Extraction as Multi-turn Question Answering (2020.findings-emnlp)

Copied to clipboard

Challenge: Current approaches to event extraction fail to model rich interactions among event types and arguments of different roles.
Approach: They propose a new paradigm that formulates event extraction as multi-turn question answering . they propose to use reading comprehension problems to extract triggers and arguments .
Outcome: The proposed approach outperforms current state-of-the-art on argument extraction tasks . it makes full use of dependency among arguments and event types, and generalizes well .
Active Prompting with Chain-of-Thought for Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing methods to annotate large language models rely on a fixed set of human-annotated exemplars, which are not always the most effective for different tasks.
Approach: They propose a method to adapt large language models to different tasks with task-specific example prompts (annotated with human-designed CoT reasoning) they introduce several metrics to characterize uncertainty so as to select the most uncertain questions for annotation.
Outcome: The proposed method significantly improves performance on eight complex reasoning tasks.
No More Stale Feedback: Co-Evolving Critics for Open-World Agent Learning (2026.acl-long)

Copied to clipboard

Challenge: Current methods for training Large Language Model agents rely on static or offline critic models, which fail to adapt as the policy evolves.
Approach: They propose a framework that integrates a critique and a policy to optimize the policy and critic through a synchronized co-evolutionary loop.
Outcome: The proposed framework yields more stable training and higher long-horizon task success across open-world environments.
Beyond Templates: Dynamic Adaptation of Reasoning Demonstrations via Feasibility-Aware Exploration (2026.findings-acl)

Copied to clipboard

Challenge: Existing reasoning datasets that are designed for powerful LLMs often lead to degraded performance when directly applied to weaker models.
Approach: They propose a data adaptation framework that bridges the capability gap between expert reasoning trajectories and diverse SLMs by employing a selective imitation strategy guided by step-wise adaptability estimation via solution simulation.
Outcome: The proposed framework improves generalization and data efficiency over static fine-tuning and can be applied to large models with limited model capacity.
TacoERE: Cluster-aware Compression for Event Relation Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Existing work on event relation extraction focuses on modeling the entire document . existing methods cannot handle long-range dependencies and information redundancy .
Approach: They propose a compression-then-extraction paradigm for event relation extraction . they propose document clustering for modeling event dependencies and then a cluster summarization method .
Outcome: The proposed method simplifies and highlights important text content of clusters for mitigating redundancy and event distance.
CoMave: Contrastive Pre-training with Multi-scale Masking for Attribute Value Extraction (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to extract product features from unstructured text still suffer from problems . e-commerce platforms are focusing on multi-scale values, which can be confusing .
Approach: They propose a pre-training technique to automatically obtain attribute value pairs from product descriptions to aid e-commerce.
Outcome: The proposed method improves on the existing token-level masking strategy and achieves state-of-the-art on four benchmarks.
Beyond Itinerary Planning—A Real-World Benchmark for Multi-Turn and Tool-Using Travel Tasks (2026.acl-long)

Copied to clipboard

Challenge: Existing studies on LLM performance on travel planning have shown that existing settings are limited due to limited domain coverage, insufficient modeling of users’ implicit preferences in multi-turn conversations, and a lack of evaluation of agents’ capability boundaries.
Approach: They propose a benchmark to evaluate LLMs' planning and tool-use abilities in real-world settings by collecting user queries, user preferences, and tools from real scenarios.
Outcome: The proposed benchmark evaluates agents' capabilities in real-world settings and shows that even advanced models exhibit imbalanced performance across different capabilities.

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