arXiv AI
Jun 11
On the Limits of LLM-as-Judge for Scientific Novelty Assessment
arXiv:2606. 12071v1 Announce Type: cross Abstract: LLMs are increasingly used to generate and judge scientific ideas.
Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty
The paper introduces Think‑Probe‑Respond (TPR), a lightweight method to improve large language models’ ability to judge the novelty of research ideas. It identifies a systematic bias where models tend to label ideas as "medium novel" despite generating human‑like rationales, and shows that probing hidden states during reasoning and conditioning the final response on these probes boosts novelty judgment accuracy by 22.30%. TPR effectively reduces the medium‑novelty bias across strong baseline models.
Related stories
arXiv AI
Sep 12
NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment
NovGauge is a new benchmark designed to diagnose large language models’ ability to assess scientific paper novelty. It contains 619 paper pairs and 50 multi-paper sets, each labeled along three dimensions—task, problem, and method—by experts from ICLR reviewer overlap claims and survey co-citations. The study evaluates 18 LLMs, revealing high hallucination rates and weak evidence grounding, with the best model achieving only 43‑72% verified F1 across dimensions.
arXiv AI
Aug 7
An Axiomatic Benchmark for Evaluation of Scientific Novelty Metrics
arXiv:2604. 15145v2 Announce Type: replace Abstract: The rigorous evaluation of the novelty of a scientific paper is, even for human scientists, a challenging task.
arXiv AI
Jul 31
Do Methods Support the Claims? Intra-Paper Verification for Peer Review
arXiv:2607. 26066v1 Announce Type: cross Abstract: The growing volume of scientific submissions has motivated interest in using large language models (LLMs) to assist peer review.
arXiv AI
Jun 9
Contemporary AI lacks the imagination to diverge or negate in science
arXiv:2606. 08251v1 Announce Type: cross Abstract: Bold projections that artificial intelligence will accelerate scientific discovery have raced ahead of evidence from working scientists, and the field still lacks large-scale, scientist-in-the-loop tests of these claims.
arXiv Computation and Language
Sep 15
Measuring the Creativity of Frontier LLMs in Automated Research
arXiv:2609.14057v1 Announce Type: new Abstract: Frontier LLMs are increasingly capable of conducting automated research, yet their creativity in this setting has not been systematically evaluated. In...
arXiv AI
Jun 30
Evidence-Informed LLM Beliefs for Continual Scientific Discovery
arXiv:2606. 29182v1 Announce Type: new Abstract: Open-ended scientific discovery with large language models (LLMs) increasingly operates as a long-horizon loop of hypothesis search and verification, where a reward signal guides which hypotheses to test next.
arXiv AI
Jul 2
Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty
arXiv:2606. 25198v2 Announce Type: replace Abstract: Autonomous AI Research promises to accelerate the scientific progress of machine learning.
arXiv Computation and Language
Sep 22
DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation
arXiv:2609.22104v1 Announce Type: new Abstract: As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottle...
arXiv Machine Learning
Aug 4
LLM generation novelty through the lens of semantic similarity
arXiv:2510. 27313v3 Announce Type: replace Abstract: Generation novelty is a key indicator of an LLM's ability to generalize, yet measuring it against full pretraining corpora is computationally challenging.
arXiv AI
Jul 2
Measuring the Gap Between Human and LLM Research Ideas
arXiv:2607. 01233v1 Announce Type: cross Abstract: LLMs are increasingly used to brainstorm research ideas, but existing evaluations mostly judge individual ideas by novelty, feasibility, or expert preference.
arXiv Computation and Language
Aug 25
On the Threat Model of Weird Generalization and Emergent Misalignment
arXiv:2608.23476v1 Announce Type: new Abstract: Narrow fine-tuning on small, domain-specific datasets can produce broad and surprising changes in model behavior-a phenomenon called weird generalizati...