arXiv AI
CARAT: Do Materials LLMs Reason or Recite?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computation and Language
Sep 10
The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs
The paper investigates how different components of a graph retrieval‑augmented generation pipeline affect large language model performance on knowledge‑graph question answering. It examines four variables—whether the answer path is included, the syntax of triples, the order of triples, and the subgraph size—across six LLMs and two benchmarks. The study finds that including the answer path is crucial, while the grounding instruction dramatically reduces accuracy when no facts are provided, and that syntax, order, and subgraph size have negligible measurable impact at multi‑hop depth.
arXiv Computation and Language
Sep 22
Beyond Linear Context: Graph-Guided Evidence Navigation for Long-Novel Reasoning with a Local 9B Language Model
arXiv:2609.22939v1 Announce Type: cross Abstract: Long-context models read a novel the way a person reads a printout: one token after another, in narrative order, with the whole history competing for...
arXiv Computation and Language
Sep 17
PageRecall: Measuring Page Selection in Literature-Grounded Question Answering
arXiv:2609.18154v1 Announce Type: cross Abstract: We describe our system for LitTraceQA (GroundLM @ EMNLP 2026): given a research question, retrieve the relevant papers from a pool of 27,487, cite th...
arXiv Machine Learning
Jul 31
Sample More, Reflect Less: Self-Refine and Reflexion Lose to Repeated Sampling at Equal Token Cost, from 1.5B to 7B
arXiv:2607. 28576v1 Announce Type: cross Abstract: Methods that make a language model plan, criticise and rewrite its own answer, reflect on mistakes, pick the best of several attempts, or debate with copies of itself nearly all make it generate far more text than a single chain of thought.
arXiv AI
Aug 11
REIN: Bridging the Gap between Reasoning and Reliability via Reflection and Abstention Alignment
arXiv:2608. 07931v1 Announce Type: new Abstract: Large reasoning models (LRMs) are prone to hallucination, which undermines their reliability and poses challenges for safe deployment.
arXiv Computer Vision
Sep 15
Structure-Token Evidence-Anchored Reasoning for Scientific Chart Understanding
arXiv:2609.13267v1 Announce Type: new Abstract: Scientific charts encode quantities in axes, legends, and geometric marks, yet large vision-language models still treat them as natural photographs. Vi...