Papers by Junwei Yang

8 papers
Composable Text Controls in Latent Space with ODEs (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to composable text operations often require plug-and-play . a single LM can perform arbitrary text operation composition in the latent space .
Approach: They propose an efficient approach for composable text operations in the latent space of text . they connect pretrained LMs to the laten space and adapt them to the space .
Outcome: The proposed approach improves on existing methods in the latent space of text.
A Speaker-Aware Co-Attention Framework for Medical Dialogue Information Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: With the development of medical digitization, the extraction and structuring of electronic medical records (EMRs) have become challenging but fundamental tasks.
Approach: They propose a speaker-aware dialogue encoder with multi-task learning which takes the speaker's identity into account and a co-attention fusion network to aggregate the utterance information.
Outcome: The proposed framework outperforms the state-of-the-art methods on the public medical dialogue extraction datasets to demonstrate its superiority.
Don’t Take It Literally: An Edit-Invariant Sequence Loss for Text Generation (2022.naacl-main)

Copied to clipboard

Challenge: Neural text generation models are typically trained by maximizing log-likelihood with the sequence cross entropy (CE) loss.
Approach: They propose an Edit-Invariant Sequence Loss method which computes the matching loss of a target sequence with all n-grams in the generated sequence.
Outcome: The proposed method outperforms the common CE loss and strong baselines on a wide range of tasks.
SciCustom: A Framework for Custom Evaluation of Scientific Capabilities in Large Language Models (2026.acl-long)

Copied to clipboard

Challenge: Existing evaluations of large language models fail to reflect fine-grained capabilities . existing benchmarks are manually curated or domain-generic, limiting scalability and alignment with real use cases.
Approach: They propose a framework that allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific scientific capabilities in LLMs.
Outcome: The proposed framework reveals fine-grained differences in scientific capabilities that standard benchmarks overlook . it allows custom construction of benchmarks from large-scale scientific data to evaluate application-specific capabilities in LLMs.
Failure makes the agent stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions (2026.findings-acl)

Copied to clipboard

Challenge: Existing approaches to self-reflection rely on heuristic prompting or unidirectional reasoning traces.
Approach: They propose a structured reflection method that transforms the "from error to repair" process into a first-class, controllable, and trainable action.
Outcome: The proposed method improves multi-turn tool-call success rates and error recovery while reducing redundant calls.
Pathway2Text: Dataset and Method for Biomedical Pathway Description Generation (2022.findings-naacl)

Copied to clipboard

Challenge: Neural text generation is a novel technique to describe biomedical pathways without manually curation.
Approach: They propose a new dataset Pathway2Text which contains 2,367 pairs of biomedical pathways and textual descriptions.
Outcome: The proposed method improves on both Graph2Text and Text2Graph tasks and can be used as a benchmark for biomedical named entity recognition.
MetaFill: Text Infilling for Meta-Path Generation on Heterogeneous Information Networks (2022.emnlp-main)

Copied to clipboard

Challenge: Existing meta-path generation methods cannot fully exploit rich textual information in HINs.
Approach: They propose a text-infilling-based approach to generate meta-paths from textual information in HINs.
Outcome: The proposed approach can classify edges in the zero-shot setting, where existing methods cannot generate meta-paths.
BaseCal: Unsupervised Confidence Calibration via Base Model Signals (2026.acl-long)

Copied to clipboard

Challenge: Post-trained LLMs typically compromise reliability with severe overconfidence, resulting in inaccurate responses.
Approach: They propose a solution that feeds PoLLMs into the base LLM to get confidence.
Outcome: The proposed solution reduces expected calibration error (ECE) by 42.90% compared to the best unsupervised 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