We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| Sri-Harsha/scpp | canonical | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| clean_text | Ran | Sri-Harsha/scpp/generate_sugarcrepe_plus-mistral.py code served (permissive licence) · get_code("7c6b861ca90aa566") |
| prepare_prompt | Ran | Sri-Harsha/scpp/generate_sugarcrepe_plus-mistral.py code served (permissive licence) · get_code("cd7870b8098d6090") |
| prepare_prompt_to_generate_again | Ran | Sri-Harsha/scpp/generate_sugarcrepe_plus-mistral.py code served (permissive licence) · get_code("ce2c7f90934b82d4") |
| setup_logger | Ran | Sri-Harsha/scpp/evaluate_ulms.py code served (permissive licence) · get_code("9bc8d3fbbbad0be2") |
| summarize_results | Not yet run | Sri-Harsha/scpp/evaluate_ulms.py code served (permissive licence) · get_code("181b4e43c1c329ce") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Despite their remarkable successes, state-of-the-art large language models (LLMs), including vision-and-language models (VLMs) and unimodal language models (ULMs), fail to understand precise semantics. For example, semantically equivalent sentences expressed using different lexical compositions elicit diverging representations. The degree of this divergence and its impact on encoded semantics is not very well understood. In this paper, we introduce the SUGARCREPE++ dataset to analyze the sensitivity of VLMs and ULMs to lexical and semantic alterations. Each sample in SUGARCREPE++ dataset consists of an image and a corresponding triplet of captions: a pair of semantically equivalent but lexically different positive captions and one hard negative caption. This poses a 3-way semantic (in)equivalence problem to the language models. We comprehensively evaluate VLMs and ULMs that differ in architecture, pre-training objectives and datasets to benchmark the performance of SUGARCREPE++ dataset. Experimental results highlight the difficulties of VLMs in distinguishing between lexical and semantic variations, particularly in object attributes and spatial relations. Although VLMs with larger pre-training datasets, model sizes, and multiple pre-training objectives achieve better performance on SUGARCREPE++, there is a significant opportunity for improvement. We show that all the models which achieve better performance on compositionality datasets need not perform equally well on SUGARCREPE++, signifying that compositionality alone may not be sufficient for understanding semantic and lexical alterations. Given the importance of the property that the SUGARCREPE++ dataset targets, it serves as a new challenge to the vision-and-language community.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2406.11171")
get_code_for_paper("2406.11171")
have("2406.11171")
Connect an agent — have() is free.