Papers by Hongwei Feng

8 papers
GAPO: Learning Preferential Prompt through Generative Adversarial Policy Optimization (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for achieving this require a limited understanding of constraints and can be hallucinating or brittle.
Approach: They propose a framework that combines adversarial training dynamics with an encoder-only reward model to progressively learn and adapt to increasingly complex constraints.
Outcome: Extensive experiments show that GAPO significantly outperforms existing methods like PPO, DPO, and KTO in fine-grained constraints.
MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling (2025.findings-emnlp)

Copied to clipboard

Challenge: MT-RewardTree provides a framework for constructing, evaluating, and deploying process reward models in machine translation (MT)
Approach: They propose a method for automatically generating token-level preference pairs using approximate Monte Carlo Tree Search.
Outcome: The proposed framework achieves state-of-the-art performance in token-level evaluation and sequence-level analysis.
DetectBench: Can Large Language Model Detect and Piece Together Implicit Evidence? (2024.findings-emnlp)

Copied to clipboard

Challenge: Existing LLMs' abilities to detect evidence in long contexts are far inferior to humans.
Approach: They propose a benchmark to assess LLMs' abilities in evidence and multi-step commonsense reasoning within a long context.
Outcome: The proposed method improves the performance of LLMs in evidence detection and commonsense reasoning.
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters (2026.acl-industry)

Copied to clipboard

Challenge: Existing efforts focus on activation within ongoing dialogues, while overlooking a key real-world bottleneck.
Approach: They propose a conversation starter generation system that generates personalized starters to guide users into conversation without explicit user intent.
Outcome: The proposed system improves user active days by +1.84 and click-through rate by +94.25 and has been deployed in production.
StrucText-Eval: Evaluating Large Language Model’s Reasoning Ability in Structure-Rich Text (2025.acl-long)

Copied to clipboard

Challenge: Structured data has been central to corporate data strategies for decades . however, with the advancement of large language models (LLMs), there has been a significant shift towards the effective utilization of unstructured data.
Approach: They propose an automatic evaluation data generation method to assess LLMs’ reasoning capabilities on structure-rich text.
Outcome: The proposed method supports 8 structured languages and 29 tasks, generating data with adjustable complexity through controllable nesting and structural width.
MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive Environments (2025.acl-short)

Copied to clipboard

Challenge: Large Language Models (LLMs) have shown remarkable capabilities in environmental perception, reasoning-based decision-making, and simulating complex human behaviors, particularly in interactive role-playing contexts.
Approach: They propose a framework to assess LLMs' proficiency in portraying advanced human behaviors through murder mystery games using eight intricately crafted scripts.
Outcome: The framework evaluates LLMs' performance in portraying advanced human behaviors through murder mystery games.
HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns (2026.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated remarkable capabilities in reasoning and generation, serving as the foundation for advanced persona simulation and Role-Playing Language Agents (RPLAs).
Approach: They propose a framework that treats psychological patterns as interacting causal forces and synthesizes 113 scenarios where 2-5 patterns reinforce, conflict, or modulate each other.
Outcome: The proposed framework outperforms Qwen3-32B on multi-pattern dynamics despite 4 fewer parameters.
M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation Evaluation (2025.acl-long)

Copied to clipboard

Challenge: Recent advances in large language models (LLMs) have shown their potential to deliver human-like judgments.
Approach: They propose a systematic LLM-based multi-agent framework for advanced LLM as-a-judge MT evaluation that integrates dimension-specific results into a final evaluation judgment.
Outcome: The proposed framework outperforms existing LLM-as-a-judge methods and competes with state-of-the-art automatic metrics even when powered by a suboptimal model like GPT-4o mini.

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