ServiceNow AI Research

Large Language Models

Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework
Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework
Graph databases like Neo4j are gaining popularity for handling complex, interconnected data, over traditional relational databases in …
North American Chapter of the Association for Computational Linguistics (NAACL),  2025.
Paper Cite
M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models
M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models
Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT …
North American Chapter of the Association for Computational Linguistics (NAACL),  2025.
Paper Cite Code
Prompting with Phonemes: Enhancing LLM Multilinguality for non-Latin Script Languages
Prompting with Phonemes: Enhancing LLM Multilinguality for non-Latin Script Languages
Multilingual LLMs have achieved remarkable benchmark performance, but we find they continue to underperform on non-Latin script …
North American Chapter of the Association for Computational Linguistics (NAACL),  2025.
Paper Cite
Learning to Defer for Causal Discovery with Imperfect Experts
Learning to Defer for Causal Discovery with Imperfect Experts
Integrating expert knowledge, e.g. from large language models, into causal discovery algorithms can be challenging when the knowledge …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Paper Cite
Societal Alignment Frameworks Can Improve LLM Alignment
Societal Alignment Frameworks Can Improve LLM Alignment
Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Paper Cite
Unifying Autoregressive and Diffusion-Based Sequence Generation
Unifying Autoregressive and Diffusion-Based Sequence Generation
We take significant steps toward unifying autoregressive and diffusion-based sequence generation by extending the SEDD discrete …
Workshop at the International Conference of Learning Representation (ICLR),  2025.
Paper Cite
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
Decoder-only Transformers often struggle with complex reasoning tasks, particularly arithmetic reasoning requiring multiple sequential …
International Conference of Learning Representations (ICLR),  2025.
Paper Cite Code Slides Video
LitLLMs, LLMs for Literature Review: Are We There Yet?
LitLLMs, LLMs for Literature Review: Are We There Yet?

Literature reviews are an essential component of scientific research, but they remain time-intensive and challenging to write, …

Transactions on Machine Learning Research (TMLR),  2025.
Paper Cite Code Video
Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models
Do LLMs Know When to NOT Answer? Investigating Abstention Abilities of Large Language Models
Abstention Ability (AA) is a critical aspect of Large Language Model (LLM) reliability, referring to an LLM’s capability to …
International Conference on Computational Linguistics (COLING),  2025.
Paper Cite
AgentMerge: Enhancing Generalization in Fine-Tuned LLM Agents
AgentMerge: Enhancing Generalization in Fine-Tuned LLM Agents
Recent advancements in large language models (LLMs) have spurred interest in developing autonomous agents capable of performing complex …
Workshop at the Neural Information Processing Systems (NeurIPS),  2024.
Paper Cite