Thinking Beyond the Local: Multi-View Instructed Adaptive Reasoning in KG-Enhanced LLMs (2026 · 1 citation)
Systems that pair knowledge graphs with LLMs for question answering usually walk the graph outward from the entities named in the query.
CompTab: A Comprehensive Benchmark for Real-World TableQA with Complex Reasoning and Irregular Tables (2026)
Most TableQA benchmarks use tidy, well-formed tables, so they overstate how well LLMs handle the messy tables found in practice.
Execution as Verification: Fine-Grained Self-Correcting Reasoning for Complex KBQA (2026)
LLM-based semantic parsing for KBQA usually writes a complete logical form in one pass and only then runs it.
Rejection-to-Acceptance Transition: Model Editing-Based Jailbreak Backdoor Injection Not Limited to Few Output Tokens (2026)
The paper examines jailbreak backdoors planted in safety-aligned LLMs through lightweight model editing. Earlier editing attacks, such as JailbreakEdit, tie a trigger to compliant opening phrases like "Sure,". The model can still refuse later in its answer, and adding more bound phrases raises both run time and cost.…

Co-authors here

12 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 1 time (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 2 November 2026