Papers by Xingyu Shi

8 papers
Topic-Aware Evidence Reasoning and Stance-Aware Aggregation for Fact Verification (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for fact verification focus on analyzing semantic interaction between claim and evidence but fail to capture their topical consistency . Existing models focus on the aggregation of multiple pieces of evidence without considering their implicit stances to the claim, thereby introducing spurious information.
Approach: They propose a topic-aware evidence reasoning and stance-again aggregation model that checks topical consistency between claims and evidence.
Outcome: The proposed model outperforms state-of-the-art models on two benchmark datasets.
Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare Dictator (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) are increasingly entrusted with high-stakes decisions that affect human welfare.
Approach: They evaluate 20 state-of-the-art Large language models (LLMs) and 20 LLM dictators to create a social welfare function benchmark.
Outcome: The proposed model creates dilemma between maximizing collective efficiency and ensuring distributive fairness.
MENTOR: Mitigating Identity Drift in Dynamic Role-Playing via Dual-Chain Structured Memory (2026.findings-acl)

Copied to clipboard

Challenge: Long-context LLMs are evolving into long-term agents that interact with users over extended horizons.
Approach: They propose a cognitive architecture that mitigates identity drift without fine-tuning . MENTOR uses a Dual-Chain Memory Mechanism: a Global Chain (G) for long-term event logging and isolated Role Chains (Rr) as per-role working memories.
Outcome: The proposed architecture improves the overall score (Avg) from 0.46 to 0.75 on average, with substantial gains in identity adherence and knowledge fidelity.
Design Challenges in Low-resource Cross-lingual Entity Linking (2020.emnlp-main)

Copied to clipboard

Challenge: Existing techniques for grounding mentions of entities in a foreign language do not rise to the challenges introduced by text in low-resource languages (LRL) and fail to generalize to text not taken from Wikipedia, on which they are usually trained.
Approach: They propose a cross-lingual XEL technique that uses search engines to locate and search for foreign language entries in Wikipedia.
Outcome: The proposed system shows an increase of 25% in gold candidate recall and 13% in end-to-end linking accuracy over state-of-the-art baselines.
TPTU-v2: Boosting Task Planning and Tool Usage of Large Language Model-based Agents in Real-world Industry Systems (2024.emnlp-industry)

Copied to clipboard

Challenge: Large language models have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools.
Approach: They propose a framework to enhance the task planning and tool usage abilities of LLMs in industrial systems.
Outcome: The proposed framework enhances the task planning and tool usage abilities of LLM-based agents in industrial systems.
Rethinking Word-Level Auto-Completion in Computer-Aided Translation (2023.emnlp-main)

Copied to clipboard

Challenge: Existing models for word-level auto-completion (WLAC) do not meet the criterion of good auto-completes.
Approach: They propose a measurable criterion to address the question: what kind of words are good auto-completions? they propose an approach to enhance WLAC performance by promoting adherence to the cri-terion.
Outcome: The proposed approach outperforms the top-performing system submitted to the WLAC shared tasks in WMT2022 while using significantly smaller model sizes.
BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches often fail to leverage the linguistic intelligence of Large Language Models (LLMs) Existing models lack the ability to follow text instructions for controllable Text-to-Speech (TTS).
Approach: They propose a framework where an LLM acts as a conductor, understanding user instructions and generating a textual plan - explicit vocal features.
Outcome: The proposed model outperforms open- and closed-source models in speech synthesis and achieves zero-shot cross-lingual generalization.
UniCreative: Unifying Long-form Logic and Short-form Sparkle via Reference-Free Reinforcement Learning (2026.findings-acl)

Copied to clipboard

Challenge: Existing alignment paradigms for creative writing use static reward signals and supervised data.
Approach: They propose a constraint-aware reward model that synthesizes query-specific criteria to provide fine-grained preference judgments.
Outcome: The proposed framework aligns models with human preferences across content quality and structural paradigms without supervised fine-tuning and ground-truth references.

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