Papers by Yongmei Liu
Learning to Generate Programs for Table Fact Verification via Structure-Aware Semantic Parsing (2022.acl-long)
Copied to clipboard
| Challenge: | Existing methods for table fact verification do not study generating latent programs from statements . current weakly supervised methods are limited due to huge search space with lots of spurious programs. |
| Approach: | They propose a structure-aware approach to do table fact verification by structure-based parsing . they leverage lexical features and structure features to generate program from statements . |
| Outcome: | The proposed method generates programs more accurately than existing parsers and achieves comparable performance to the SOTA on the large-scale benchmark TABFACT. |
Exploring the Capacity of Pretrained Language Models for Reasoning about Actions and Change (2023.acl-long)
Copied to clipboard
| Challenge: | Recent transformer-based language models (LMs) provide reasoning over textual benchmarks . RAC is essential to understand and interact with the ever-changing environment . |
| Approach: | They propose to use a transformer-based language model to learn to reason over textual benchmarks. |
| Outcome: | The proposed model minimizes the influence of other linguistic requirements to focus on RAC. |
LTRAG: Enhancing Autoformalization and Self-refinement for Logical Reasoning with Thought-Guided RAG (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have shown promise in natural language reasoning, especially with techniques like chain-of-thought prompting. |
| Approach: | They propose a framework to enhance autoformalization and self-refinement for logical reasoning with Retrieval-Augmented Generation (RAG) by building knowledge bases of thought-guided examples. |
| Outcome: | The proposed framework outperforms Logic-LM and LINC on FOLIO and AR-LSAT, and achieves an accuracy gain of 13% over Logic LM and the proposed methods on GPT-4 and AR LSAT. |
MultiLogicNMR(er): A Benchmark and Neural-Symbolic Framework for Non-monotonic Reasoning with Multiple Extensions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Non-monotonic reasoning is widely used in daily life and legal reasoning. |
| Approach: | They propose a neural-symbolic framework for multi-extension NMR and propose to build two variants with more extensions or text diversity. |
| Outcome: | The proposed framework outperforms prompt-based methods and outperformed some fine-tuning methods. |
WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge (2021.emnlp-main)
Copied to clipboard
| Challenge: | Recent success of neural language models on the Winograd Schema Challenge has called for further investigation of commonsense reasoning ability of these models. |
| Approach: | They propose a logic-based framework that focuses on high-quality commonsense knowledge. |
| Outcome: | The proposed framework focuses on high-quality commonsense knowledge. |
PrefRAG: Correcting Semantic Errors in Auto-Formalization for Logical Reasoning with Program Preference RAG (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing auto-formalization methods for logical reasoning are prone to syntactic and semantic errors. |
| Approach: | They propose a neuro-symbolic paradigm for logical reasoning based on auto-formalization . they propose 'programme preference retrieval-augmented generation' to detect and repair syntactic and semantic errors. |
| Outcome: | The proposed approach outperforms baselines on in-distribution and out-of-difference datasets. |
Improving Unsupervised Commonsense Reasoning Using Knowledge-Enabled Natural Language Inference (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Recent methods based on pre-trained language models have shown strong supervised performance on commonsense reasoning. |
| Approach: | They propose to use a common framework to solve commonsense reasoning tasks using a dataset from NLI. |
| Outcome: | The proposed method achieves state-of-the-art unsupervised performance on two commonsense reasoning tasks. |
LogicNMR: Probing the Non-monotonic Reasoning Ability of Pre-trained Language Models (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work examines the non-monotonic reasoning ability of pre-trained language models. |
| Approach: | They construct a non-monotonic reasoning benchmark with explicit default rules and iterative updates. |
| Outcome: | The proposed model achieves a higher accuracy than the benchmark, but performs poorly on the benchmark. |