Papers by Jiacheng Yao

6 papers
From Isolated Scoring to Collaborative Ranking: A Comparison-Native Framework for LLM-Based Paper Evaluation (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are currently used to evaluate scientific papers by assigning an absolute score to each paper independently.
Approach: They propose a comparison-native framework for paper evaluation that integrates comparison into both data construction and model learning.
Outcome: The proposed framework achieves an average relative improvement of 21.8% over the strong baseline DeepReview-14B, while exhibiting robust generalization to five previously unseen datasets.
Mitigating Selection Bias in Large Language Models via Permutation-Aware GRPO (2026.acl-long)

Copied to clipboard

Challenge: Existing inference-time debiasing ignores that the same question should yield consistent answers across permutations.
Approach: They propose a permutation-aware group-relative policy optimization which enforces permutations-consistent semantic reasoning.
Outcome: The proposed model outperforms strong baselines across seven benchmarks while maintaining high overall performance.
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training (2025.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have exceptional capabilities in knowledge-intensive tasks . however, they struggle with knowledge updates due to dynamic nature of world knowledge .
Approach: They propose to identify computational subgraphs that facilitate knowledge storage and processing . they also identify a phase shift from formation to optimization in LLMs .
Outcome: The proposed model can capture factual knowledge from pre-training corpus and encapsulate it as extensive parametric knowledge.
Implicit Relation Linking for Question Answering over Knowledge Graph (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods rely on textual similarities between NL and KG to build relation links.
Approach: They propose an implicit relation linking method called ImRL which links relation phrases in NL to relation paths in KG.
Outcome: The proposed method significantly outperforms state-of-the-art methods on two benchmarks and a newly-created datasets.
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System (2026.acl-long)

Copied to clipboard

Challenge: Existing red-teaming approaches focus on policy-level weaknesses, but they overlook systemic weaknesses . aRES exploits dual-targeting weaknesses in both the core LLM and the RM simultaneously.
Approach: a new framework uncovers weaknesses in both the core and the reward models simultaneously . a "Safety Mentor" generates semantically coherent adversarial prompts .
Outcome: ARES uncovers weaknesses in both the core LLM and the RM simultaneously . it fine-tunes the LM to detect harmful content, then optimizes the core model .
Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models (2025.acl-long)

Copied to clipboard

Challenge: Current methods for improving large language models rely on splitting long contexts into fixed-length chunks, compromising accuracy.
Approach: They propose a method for dynamically separating and selecting chunks of long context, facilitating a more streamlined input for LLMs.
Outcome: The proposed approach outperforms baseline methods on single-hop and multi-hop question-answering benchmarks.

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