7 citations · 29 across the 24 of their papers we have counts for
26 papers
Autodata: An agentic data scientist to create high quality synthetic data
Ilia Kulikov, Chenxi Whitehouse, Tianhao Wu +12
We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data. We show how to train (meta-optimize) s…
Reasoning over mathematical objects: on-policy reward modeling and test time aggregation
Pranjal Aggarwal, Marjan Ghazvininejad, Seungone Kim +18
The ability to precisely derive mathematical objects is a core requirement for downstream STEM applications, including mathematics, physics, and chemistry, where reasoning must cul…
Text-to-Stage: Spatial Layouts from Long-form Narratives
Jefferson Hernandez, Swarnadeep Saha, Chenxi Whitehouse +6
In this work, we probe the ability of a language model to demonstrate spatial reasoning from unstructured text, mimicking human capabilities and automating a process that benefits…
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Leitian Tao, Ilia Kulikov, Swarnadeep Saha +5
Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable,…
The Majority is not always right: RL training for solution aggregation
Wenting Zhao, Pranjal Aggarwal, Swarnadeep Saha +3
Scaling up test-time compute, by generating multiple independent solutions and selecting or aggregating among them, has become a central paradigm for improving large language model…
Jointly Reinforcing Diversity and Quality in Language Model Generations
Tianjian Li, Yiming Zhang, Ping Yu +5
Post-training of Large Language Models (LMs) often prioritizes accuracy and helpfulness at the expense of diversity. This creates a tension: while post-training improves response q…
OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
Pranjal Aggarwal, Seungone Kim, Jack Lanchantin +4
Thinking LLMs solve complex tasks at the expense of increased compute and overthinking on simpler problems, while non-thinking LLMs are faster and cheaper but underthink on harder…
Bridging Offline and Online Reinforcement Learning for LLMs
Jack Lanchantin, Angelica Chen, Janice Lan +9
We investigate the effectiveness of reinforcement learning methods for finetuning large language models when transitioning from offline to semi-online to fully online regimes for b…
J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
Chenxi Whitehouse, Tianlu Wang, Ping Yu +4
The progress of AI is bottlenecked by the quality of evaluation, making powerful LLM-as-a-Judge models a core solution. The efficacy of these judges depends on their chain-of-thoug…
Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
Swarnadeep Saha, Xian Li, Marjan Ghazvininejad +2
LLM-as-a-Judge models generate chain-of-thought (CoT) sequences intended to capture the step-bystep reasoning process that underlies the final evaluation of a response. However, du…
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoning
Justin Chih-Yao Chen, Archiki Prasad, Swarnadeep Saha +2
Large Language Models' (LLM) reasoning can be improved using test-time aggregation strategies, i.e., generating multiple samples and voting among generated samples. While these imp…
System-1.x: Learning to Balance Fast and Slow Planning with Language Models
Swarnadeep Saha, Archiki Prasad, Justin Chih-Yao Chen +3
Language models can be used to solve long-horizon planning problems in two distinct modes: a fast 'System-1' mode, directly generating plans without any explicit search or backtrac…
MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
Justin Chih-Yao Chen, Swarnadeep Saha, Elias Stengel-Eskin +1
Multi-agent interactions between Large Language Model (LLM) agents have shown major improvements on diverse reasoning tasks. However, these involve long generations from multiple m…
Branch-Solve-Merge Improves Large Language Model Evaluation and Generation
Swarnadeep Saha, Omer Levy, Asli Celikyilmaz +3
Large Language Models (LLMs) are frequently used for multi-faceted language generation and evaluation tasks that involve satisfying intricate user constraints or taking into accoun…
ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
Justin Chih-Yao Chen, Swarnadeep Saha, Mohit Bansal
Large Language Models (LLMs) still struggle with natural language reasoning tasks. Motivated by the society of minds (Minsky, 1988), we propose ReConcile, a multi-model multi-agent…
Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization
Swarnadeep Saha, Peter Hase, Mohit Bansal
A hallmark property of explainable AI models is the ability to teach other agents, communicating knowledge of how to perform a task. While Large Language Models perform complex rea…
ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness
Archiki Prasad, Swarnadeep Saha, Xiang Zhou +1
Multi-step reasoning ability is fundamental to many natural language tasks, yet it is unclear what constitutes a good reasoning chain and how to evaluate them. Most existing method…
MURMUR: Modular Multi-Step Reasoning for Semi-Structured Data-to-Text Generation
Swarnadeep Saha, Xinyan Velocity Yu, Mohit Bansal +2
Prompting large language models has enabled significant recent progress in multi-step reasoning over text. However, when applied to text generation from semi-structured data (e.g.,…
Are Hard Examples also Harder to Explain? A Study with Human and Model-Generated Explanations
Swarnadeep Saha, Peter Hase, Nazneen Rajani +1
Recent work on explainable NLP has shown that few-shot prompting can enable large pretrained language models (LLMs) to generate grammatical and factual natural language explanation…
Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
Swarnadeep Saha, Shiyue Zhang, Peter Hase +1
Current abstractive summarization models either suffer from a lack of clear interpretability or provide incomplete rationales by only highlighting parts of the source document. To…
Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning
Swarnadeep Saha, Prateek Yadav, Mohit Bansal
Pre-trained sequence-to-sequence language models have led to widespread success in many natural language generation tasks. However, there has been relatively less work on analyzing…
multiPRover: Generating Multiple Proofs for Improved Interpretability in Rule Reasoning
Swarnadeep Saha, Prateek Yadav, Mohit Bansal
We focus on a type of linguistic formal reasoning where the goal is to reason over explicit knowledge in the form of natural language facts and rules (Clark et al., 2020). A recent…
ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning
Swarnadeep Saha, Prateek Yadav, Lisa Bauer +1
Recent commonsense-reasoning tasks are typically discriminative in nature, where a model answers a multiple-choice question for a certain context. Discriminative tasks are limiting…
ConjNLI: Natural Language Inference Over Conjunctive Sentences
Swarnadeep Saha, Yixin Nie, Mohit Bansal
Reasoning about conjuncts in conjunctive sentences is important for a deeper understanding of conjunctions in English and also how their usages and semantics differ from conjunctiv…