Papers by Xiangchen Song

4 papers
Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders (2026.acl-long)

Copied to clipboard

Challenge: Sparse Autoencoders (SAEs) are a tool in mechanistic interpretability (MI) but the aspiration to identify a canonical set of features is challenged by the observed inconsistency of learned SAE features across different training runs.
Approach: They propose to use the Pairwise Dictionary Mean Correlation Coefficient to quantify SAE feature consistency as an evaluation axis alongside reconstruction and sparsity.
Outcome: The proposed measure is based on the pairwise dictionary mean correlation coefficient (PW-MCC) on LLM activations.
ChemNER: Fine-Grained Chemistry Named Entity Recognition with Ontology-Guided Distant Supervision (2021.emnlp-main)

Copied to clipboard

Challenge: Named entity recognition (NER) is a fundamental step in scientific literature analysis to build AI-driven systems for molecular discovery, synthetic strategy designing, and manufacturing.
Approach: They propose an ontology-guided method for fine-grained named entity recognition (NER) it leverages the chemistry type ontologies to generate distant labels with flexible KB-matching .
Outcome: The proposed method significantly outperforms the state-of-the-art methods with a .25 absolute F1 improvement.
COVID-19 Literature Knowledge Graph Construction and Drug Repurposing Report Generation (2021.naacl-demos)

Copied to clipboard

Challenge: a new framework to digest relevant biomedical knowledge is needed to combat COVID-19 . quantity of research results is a bottleneck, and false information promoted in publications .
Approach: a team of researchers has developed a framework to extract multimedia knowledge elements from scientific literature to combat COVID-19.
Outcome: a new framework extracts fine-grained multimedia knowledge elements from scientific literature . it provides detailed contextual sentences, subfigures, and knowledge subgraphs as evidence . the framework is based on a case study of drug repurposing .
Advancing Reasoning in Diffusion Language Models with Denoising Process Rewards (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for improving reasoning in diffusion language models rely on outcome-based rewards that provide no direct supervision over the denoising process.
Approach: They propose a method that provides a process-level reinforcement signal over denoising trajectory of diffusion language models.
Outcome: Experiments on challenging reasoning benchmarks show that the proposed model improves reasoning stability, interpretability and overall performance.

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