Papers by Tianyang Liu

13 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.
Neutralizing Bias in LLM Reasoning using Entailment Graphs (2025.findings-acl)

Copied to clipboard

Challenge: Natural Language Inference (NLI) is a foundational understanding task in language understanding.
Approach: They propose a framework to construct counterfactual reasoning data and fine-tune LLMs to reduce attestation bias.
Outcome: The proposed framework reduces hallucinations from attestation bias on original and bias-neutralized datasets while keeping hypotheses unchanged.
HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Existing approaches to lifelong model editing apply parameter perturbations to static and dense layers for all instances.
Approach: They propose a hierarchical reinforcement learning framework that identifies the most knowledge-relevant layers for each editing instance.
Outcome: The proposed framework boosts the performance of the competitive RLEdit by 8.48% with perturbing only half of the layers per edit.
Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Empirical evaluations on eight recent LLMs reveal that DRPO significantly enhances alignment performance, enabling base models to outperform their SFT/RLHF-tuned counterparts.
Approach: They propose a tuning-free approach to self-alignment called Dynamic Rewarding with Prompt Optimization (DRPO) it leverages a dynamic rewarding mechanism to identify and rectify alignment weaknesses .
Outcome: The proposed approach outperforms existing methods and is highly adaptable to various alignment challenges.
Explicit Inductive Inference using Large Language Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) suffer a signifi- cant performance drop when entailment labels disagree with the attestation label of hypothesis H.
Approach: They propose a pipeline that exploits an LLM's attestation bias to do explicit inductive inference . they transform a premise into attested alternatives and aggregate the results .
Outcome: The proposed pipeline improves the performance of large language models on inference tasks and alleviates the attestation bias.
SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have transformed machine learning but have raised significant legal concerns due to their potential to produce text that infringes on copyrights.
Approach: They propose a lightweight, real-time defense mechanism to prevent the generation of copyrighted text by evaluating methods and testing attack strategies.
Outcome: The proposed defense significantly reduces the volume of copyrighted text generated by LLMs by effectively refusing malicious requests.
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to elicit confidence from large language models are limited to binary or inaccurate group-level confidence estimates.
Approach: They propose a training framework that teaches LLMs to express more fine-grained confidence estimates.
Outcome: The proposed training framework reduces the confidence calibration error and maintains the performance of the model.
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation (2026.acl-long)

Copied to clipboard

Challenge: Low-Rank Adaptation (LoRA) is a key parameter-efficient fine-tuning method . however, its effectiveness is hampered by semantic drift and structural incoherence .
Approach: They propose a low-rank Adaptation framework that tackles semantic drift and structural incoherence by pruning task-irrelevant directions.
Outcome: Experiments on large language models, vision models, and vision models show that the proposed framework outperforms LoRA and advanced dynamic rank allocation and sparsity-based methods.
RAG4ITOps: A Supervised Fine-Tunable and Comprehensive RAG Framework for IT Operations and Maintenance (2024.emnlp-industry)

Copied to clipboard

Challenge: Large Language Models (LLMs) have improved the open-domain QA’s performance, but how to efficiently handle enterprise-exclusive corpora and build domain-specific QA systems are still not studied for industrial applications.
Approach: They propose a general and comprehensive framework based on Retrieval Augmented Generation (RAG) and facilitate the whole business process of establishing QA systems for IT operations and maintenance.
Outcome: The proposed framework achieves superior results on two kinds of QA tasks.
Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMs (2025.emnlp-main)

Copied to clipboard

Challenge: Recent breakthrough models like OpenAI-o1 and DeepSeek-R1 show powerful task-solving capabilities, particularly advances in reasoning.
Approach: They propose future research directions that may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence.
Outcome: The proposed research may deepen the synergy, ultimately advancing LLM performance in both complex reasoning and code intelligence.
Personalized Question Answering with User Profile Generation and Compression (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models are prone to providing “midguy” answers regardless of users’ knowledge background, thereby failing to meet each user’s personalized needs.
Approach: They propose to generate personalized answers with LLMs based on users’ past question-answering records.
Outcome: The proposed method generates personalized answers based on user's past question-answering records.
Rethinking Tabular Data Understanding with Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are capable of various tasks, yet their capability in interpreting and reasoning over tabular data remains an underexplored area.
Approach: They propose a method for table structure normalization to improve model performance . they propose aggregation of multiple reasoning pathways to improve performance based on textual and symbolic reasoning.
Outcome: The proposed method improves performance on symbolic reasoning tasks with textual reasoning slightly outperforming symbolic reasoning on tables.
How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence (2020.acl-main)

Copied to clipboard

Challenge: Legal Artificial Intelligence (LegalAI) focuses on applying artificial intelligence to help legal tasks.
Approach: They introduce the history, current state, and future directions of research in LegalAI . they illustrate the tasks from the perspectives of legal professionals and NLP researchers .
Outcome: The proposed system can reduce heavy and redundant work for legal professionals . it can also provide a reliable reference to those who are not familiar with the legal domain .

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