Human Feedback and Eval Paper Explorer

Match reason: Keyword overlap 1/1 across title and protocol fields.

• However, despite these extensive architectural engineering efforts, a significant gap remains: even state-of-the-art (SOTA) AI agents have not yet achieved the human-level accuracy on the BIRD benchmark.
• We introduce ReViSQL, a streamlined framework that achieves human-level accuracy on BIRD for the first time.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Keyword overlap 1/1 across title and protocol fields.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• To this end, we propose a hierarchical multi-table query method based on LLM: Fine-Grained Multi-Table Retrieval FGTR, a new retrieval paradigm that employs a human-like reasoning strategy.
• To comprehensively evaluate the performance of FGTR, we construct two new benchmark datasets based on Spider and BIRD .

Match reason: Keyword overlap 1/1 across title and protocol fields.

• To investigate this potential capability gap, we present CricBench, a comprehensive benchmark suite for evaluating LLMs on specialized cricket data.
• We evaluate six state-of-the-art models, including GPT-4o, Claude 3.7 Sonnet, and open-source models, using a strict evaluation protocol.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• As a result, they struggle to infer target locations in occluded regions, typically caused by furniture or moving humans.

Match reason: Title directly matches "BIRD".

• This article describes a novel language task, the Blackbird Language Matrices (BLM) task, inspired by intelligence tests, and illustrates the BLM datasets, their construction and benchmarking, and targeted experiments on chunking and…

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Overall, XiYan-SQL achieves a new SOTA performance of 75.63% on the notable BIRD benchmark, surpassing all previous methods.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.

Match reason: Title directly matches "BIRD".

• Existing jailbreak defence frameworks for Large Vision-Language Models often suffer from a safety utility tradeoff, where strengthening safety inadvertently degrades performance on general visual-grounded reasoning tasks.
• In this work, we investigate whether safety and utility are inherently antagonistic objectives.

Match reason: Keyword overlap 1/1 across title and protocol fields.

• This perspective has also been extended beyond corpora produced by human adults, including child speech, birdsong, and chimpanzee action sequences.
• Our results indicate that the assumptions do not hold for syntactic structures and that it is difficult to apply the proposed argument not only to sentences by human adults but also to other domains, highlighting the need to reconsider the…

Match reason: Matched by broad semantic/index fallback.

• These results corroborate the value of natural data and of structured set ups in linguistic evaluation for probing LLMs' syntactic and semantic knowledge.

Match reason: Matched by broad semantic/index fallback.

• The paper introduces GUI-Owl-1.5, the latest native GUI agent model that features instruct/thinking variants in multiple sizes (2B/4B/8B/32B/235B) and supports a range of platforms (desktop, mobile, browser, and more) to enable cloud-edge…
• (2) Unified Enhancement of Agent Capabilities: we use a unified thought-synthesis pipeline to enhance the model's reasoning capabilities, while placing particular emphasis on improving key agent abilities, including Tool/MCP use, memory and…