Uploaded March 2026 | Updated September 2026, 7 hours ago
Introducing MolmoWeb, an open visual web agent built on our Molmo 2 multimodal model family in two sizes (4B and 8B parameters) along with the weights, training data, code (training code coming soon), and evaluation tools used to build it.
Blog: allenai.org/blog/molmoweb
Models: huggingface.co/collections/allenai/molmoweb
Demo: molmoweb.allen.ai
Data: huggingface.co/collections/allenai/molmoweb-data
Tech report: allenai.org/papers/molmoweb
Connect with us: discord.gg/ai2
Introducing MolmoWeb, an open visual web agent built on our Molmo 2 multimodal model family in two sizes (4B and 8B parameters) along with the weights, training data, code (training code coming soon), and evaluation tools used to build it.
Blog: allenai.org/blog/molmoweb
Models: huggingface.co/collections/allenai/molmoweb
Demo: molmoweb.allen.ai
Data: huggingface.co/collections/allenai/molmoweb-data
Tech report: allenai.org/papers/molmoweb
Connect with us: discord.gg/ai2

![Transformers as Soft Reasoners over Language | AI2
Beginning with McCarthys Advice Taker (1959), AI has pursued the goal of providing a system with explicit, general knowledge and having the system reason over that knowledge. However, expressing the knowledge in a formal (logical or probabilistic) representation has been a major obstacle to this research. This paper investigates a modern approach to this problem where the facts and rules are provided as natural language sentences, thus bypassing a formal representation. We train transformers to reason (or emulate reasoning) over these sentences using synthetically generated data. We provide the first empirical demonstration that this kind of soft reasoning over language is learnable and can achieve high (99%) accuracy, and in a way that generalizes to test data requiring substantially deeper chaining than seen during training (95%+ scores). We also demonstrate that the models transfer well to two hand-authored rulebases, and to rulebases paraphrased into more natural language. These findings are significant as it suggests a new role for transformers, namely as limited ``soft theorem provers operating over explicit theories in language. This in turn suggests new possibilities for explainability, correctability, and counterfactual reasoning in question-answering.
[IJCAI20 paper at https://www.ijcai.org/proceedings/2020/537] Transformers as Soft Reasoners over Language | AI2](https://i.ytimg.com/vi/P5KS0qj1eqc/mqdefault.jpg)




![Explaining Answers with Entailment Trees
Explaining Answers with Entailment Trees
Bhavana Dalvi
https://allenai.org/team/bhavanad
Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a rationale). If this could be done, new opportunities for understanding and debugging the systems reasoning become possible. Our approach is to generate explanations in the form of entailment trees, namely a tree of multipremise entailment steps from facts that are known, through intermediate conclusions, to the hypothesis of interest (namely the question + answer). To train a model with this skill, we created ENTAILMENTBANK, the first dataset to contain multistep entailment trees. Given a hypothesis (question + answer), we define three increasingly difficult explanation tasks: generate a valid entailment tree given (a) all relevant sentences (b) all relevant and some irrelevant sentences, or (c) a corpus. We show that a strong language model can partially solve these tasks, in particular when the relevant sentences are included in the input (e.g., 35% of trees for (a) are perfect), and with indications of generalization to other domains. This work is significant as it provides a new type of dataset (multistep entailments) and baselines, offering a new avenue for the community to generate richer, more systematic explanations. [ Paper published in EMNLP 2021, https://arxiv.org/abs/2104.08661 ] Explaining Answers with Entailment Trees](https://i.ytimg.com/vi/QPSZQYA1RmA/mqdefault.jpg)



