Papers by Yikang Liu

4 papers
MELA: Multilingual Evaluation of Linguistic Acceptability (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks on linguistic acceptability have been used to evaluate language models' ability to distinguish between acceptable and unacceptable sentences.
Approach: They present the largest benchmark to date on linguistic acceptability: MELA . they establish LLM baselines on this benchmark and investigate cross-lingual transfer in acceptability judgements with XLM-R.
Outcome: The proposed model outperforms open-source models on cross-lingual transfer in acceptability judgements.
A Systematic Assessment of Language Models with Linguistic Minimal Pairs in Chinese (2026.tacl-1)

Copied to clipboard

Challenge: Using sub-linear length normalized log-probabilities (SLLN-LP), we find unequal lengths of sentences in minimal pairs difficult for LMs even up to 32B parameters.
Approach: They propose to use ZhoBLiMP as a linguistic minimal pair benchmark for Chinese language models to mitigate biases.
Outcome: The proposed metric mitigates biases in Chinese language models with over 100 paradigms . Anaphor, Quantifiers, and Ellipsis are difficult for LMs even up to 32B parameters .
Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese (2025.emnlp-main)

Copied to clipboard

Challenge: Translationese is a linguistic property that is often introduced in the translation process that is different from those of original texts.
Approach: They propose to use synthesized translations and translations in the wild to evaluate T-index's generalizability in cross-domain settings and its validity against human judgments.
Outcome: The proposed measure can generalize to unseen genres, authors, and language pairs.
Aligning Large Multimodal Models with Factually Augmented RLHF (2024.findings-acl)

Copied to clipboard

Challenge: Large Multimodal Models (LMMs) are built across modalities and the misalignment between two modality can result in "hallucination" . developing LMMs faces challenges such as a lack of data and a limited number of data sets.
Approach: They propose a new algorithm that augments the reward model with additional factual information such as image captions and ground-truth multi-choice options.
Outcome: The proposed approach improves on the LLaVA-Bench dataset with the 96% performance level of the text-only GPT-4 and an improvement of 60% on MMHAL-BENCH over other baselines.

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