Papers by Shibo Zhang

6 papers
Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models (2026.acl-long)

Copied to clipboard

Challenge: closed-ended question-based benchmarks struggle with saturation as newer models emerge . crowd-sourced leaderboards rely on costly and slow human judges .
Approach: They propose a framework that leverages collective intelligence from all large language models to evaluate each other.
Outcome: a new framework enables a democratic, pairwise evaluation of all large language models . it achieves 97% correlation with human judgements, while significantly reducing the cost.
One Battle After Another: Probing LLMs’ Limits on Multi-Turn Instruction Following with a Benchmark Evolving Framework (2026.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for instruction-following in multi-topic dialogues are limited to a fixed number of turns, susceptible to saturation and failing to account for users’ interactive experience.
Approach: They propose a framework featuring a three-layer tracking mechanism and a query synthesis agent to mimic sequential user behaviors.
Outcome: The proposed framework outperforms existing benchmarks in the evaluation of instruction following in multi-topic dialogues and demonstrates deficiencies in failure recovery and fine-grained instruction following.
Offline Reinforcement Learning for LLM Multi-step Reasoning (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly applied to complex tasks requiring multi-step reasoning.
Approach: They propose an offline method for enhancing multi-step reasoning by optimizing the soft Bellman Equation by combining a policy model and a value function.
Outcome: The proposed method surpasses existing methods on multi-step reasoning benchmarks and can be extended to multi-iteration frameworks when additional resources are available.
DIDS: Domain Impact-aware Data Sampling for Large Language Model Training (2025.emnlp-main)

Copied to clipboard

Challenge: Existing approaches for optimizing domain-level sampling strategies struggle with maintaining intra-domain consistency and accurately measuring domain impact.
Approach: They propose to use a Fisher-Information Matrix-guided metric to measure domain impact to ensure intra-domain consistency and accuracy.
Outcome: The proposed model achieves 3.4% higher average performance while maintaining comparable training efficiency.
Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset (2021.emnlp-main)

Copied to clipboard

Challenge: Existing evaluations on the population task are either not accurate (automatic evaluation with randomly sampled negative examples) or of small scale (human annotation).
Approach: They propose a reasoning over commonsense knowledge bases (CSKBs) that are free-text and have a human annotation set to probe commonsensical reasoning.
Outcome: The proposed model is based on a human-annotated evaluation set and is compared with existing models on the population task.
BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to construct knowledge graphs are limited to a small set of relations due to manual cost or restrictions in text corpus.
Approach: They propose to automatically construct knowledge graphs (KGs) of diverse new relations from pretrained language models that accept knowledge queries with prompts.
Outcome: The proposed framework extracts knowledge of over 400 new relations from pretrained language models, including RoBERTaNet, with minimal input of a relation definition and a few shot of example entity pairs.

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