Arian Hosseini

Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks

Sebastian Fischmeister

Rishabh Agarwal

Navin Goyal

Aaron Courville

2025-11-30

arXiv (published)

doi.org

arxiv.org

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

Morgane M Moss

2025-07-06

colmweb.org/COLM/2025/Conference (accepted)

doi.org

openreview.net

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

Shengyi Huang

The dominant paradigm for RLHF is online and on-policy RL: synchronously generating from the large language model (LLM) policy, labelling wi… (see more)th a reward model, and learning using feedback on the LLM's own outputs. While performant, this paradigm is computationally inefficient. Inspired by classical deep RL literature, we propose separating generation and learning in RLHF. This enables asynchronous generation of new samples while simultaneously training on old samples, leading to faster training and more compute-optimal scaling. However, asynchronous training relies on an underexplored regime, online but off-policy RLHF: learning on samples from previous iterations of our model which give a worse training signal. We tackle the fundamental challenge in this regime: how much off-policyness can we tolerate for asynchronous training to speed up learning but maintain performance? Among several RLHF algorithms we test, online DPO is found to be most robust to off-policy data, and robustness increases with the scale of the policy model. We study further compute optimizations for asynchronous RLHF but find that they come at a performance cost, giving rise to a trade-off. We verify the scalability of asynchronous RLHF by training a general-purpose chatbot from LLaMA 3.1 8B on an instruction-following task ~40% faster than a synchronous run while matching final performance. Finally, we extend our results to math and reasoning to demonstrate asynchronous RL can finetune Rho 1B on GSM8k ~70% faster while matching synchronous accuracy.

2025-01-21

ICLR.cc/2025/Conference (poster)

doi.org

openreview.net

Not All LLM Reasoners Are Created Equal

Daniel Toyama

We study the depth of grade-school math (GSM) problem-solving capabilities of LLMs. To this end, we evaluate their performance on pairs of e… (see more)xisting math word problems together so that the answer to the second problem depends on correctly answering the first problem. Our findings reveal a significant reasoning gap in most LLMs, that is performance difference between solving the compositional pairs and solving each question independently. This gap is more pronounced in smaller, more cost-efficient, and math-specialized models. Moreover, instruction-tuning recipes and code generation have varying effects across LLM sizes, while finetuning on GSM can lead to task overfitting. Our analysis indicates that large reasoning gaps are not because of test-set leakage, but due to distraction from additional context and poor second-hop reasoning. Overall, LLMs exhibit systematic differences in their reasoning abilities, despite what their performance on standard benchmarks indicates.

2024-10-08

NeurIPS.cc/2024/Workshop/Sys2-Reasoning (poster)

doi.org

openreview.net

V-STaR: Training Verifiers for Self-Taught Reasoners

Xingdi Yuan

Common self-improvement approaches for large language models (LLMs), such as STaR, iteratively fine-tune LLMs on self-generated solutions to… (see more) improve their problem-solving ability. However, these approaches discard the large amounts of incorrect solutions generated during this process, potentially neglecting valuable information in such solutions. To address this shortcoming, we propose V-STaR that utilizes both the correct and incorrect solutions generated during the self-improvement process to train a verifier using DPO that judges correctness of model-generated solutions. This verifier is used at inference time to select one solution among many candidate solutions. Running V-STaR for multiple iterations results in progressively better reasoners and verifiers, delivering a 4% to 17% test accuracy improvement over existing self-improvement and verification approaches on common code generation and math reasoning benchmarks with LLaMA2 models.

2024-07-09

colmweb.org/COLM/2024/Conference (accepted)

doi.org

openreview.net

Joint Prompt Optimization of Stacked LLMs using Variational Inference

Alessandro Sordoni

Xingdi Yuan

Marc-Alexandre Côté

Matheus Pereira

Adam Trischler

Ziang Xiao

Arian Hosseini

Friederike Niedtner

Nicolas Le Roux

Large language models (LLMs) can be seen as atomic units of computation mapping sequences to a distribution over sequences. Thus, they can b… (see more)e seen as stochastic language layers in a language network, where the learnable parameters are the natural language prompts at each layer. By stacking two such layers and feeding the output of one layer to the next, we obtain a Deep Language Network (DLN). We first show how to effectively perform prompt optimization for a 1-Layer language network (DLN-1). Then, we present an extension that applies to 2-layer DLNs (DLN-2), where two prompts must be learned. The key idea is to consider the output of the first layer as a latent variable, which requires inference, and prompts to be learned as the parameters of the generative distribution. We first test the effectiveness of DLN-1 in multiple reasoning and natural language understanding tasks. Then, we show that DLN-2 can reach higher performance than a single layer, showing promise that we might reach comparable performance to GPT-4, even when each LLM in the network is smaller and less powerful.

2023-09-20

NeurIPS.cc/2023/Conference (poster)

doi.org

openreview.net

On the Compositional Generalization Gap of In-Context Learning

Pretrained large generative language models have shown great performance on many tasks, but exhibit low compositional generalization abiliti… (see more)es. Scaling such models has been shown to improve their performance on various NLP tasks even just by conditioning them on a few examples to solve the task without any fine-tuning (also known as in-context learning). In this work, we look at the gap between the in-distribution (ID) and out-of-distribution (OOD) performance of such models in semantic parsing tasks with in-context learning. In the ID settings, the demonstrations are from the same split (test or train) that the model is being evaluated on, and in the OOD settings, they are from the other split. We look at how the relative generalization gap of in-context learning evolves as models are scaled up. We evaluate four model families, OPT, BLOOM, CodeGen and Codex on three semantic parsing datasets, CFQ, SCAN and GeoQuery with different number of exemplars, and observe a trend of decreasing relative generalization gap as models are scaled up.

2022-11-14

ArXiv (preprint)

doi.org

arxiv.org

Understanding by Understanding Not: Modeling Negation in Language Models

R Devon Hjelm

Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language mode… (see more)ls often handle negation incorrectly. To improve language models in this regard, we propose to augment the language modeling objective with an unlikelihood objective that is based on negated generic sentences from a raw text corpus. By training BERT with the resulting combined objective we reduce the mean top~1 error rate to 4% on the negated LAMA dataset. We also see some improvements on the negated NLI benchmarks.

2021-05-31

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (published)

Ordered Memory

Stack-augmented recurrent neural networks (RNNs) have been of interest to the deep learning community for some time. However, the difficulty… (see more) of training memory models remains a problem obstructing the widespread use of such models. In this paper, we propose the Ordered Memory architecture. Inspired by Ordered Neurons (Shen et al., 2018), we introduce a new attention-based mechanism and use its cumulative probability to control the writing and erasing operation of the memory. We also introduce a new Gated Recursive Cell to compose lower-level representations into higher-level representation. We demonstrate that our model achieves strong performance on the logical inference task (Bowman et al., 2015)and the ListOps (Nangia and Bowman, 2018) task. We can also interpret the model to retrieve the induced tree structure, and find that these induced structures align with the ground truth. Finally, we evaluate our model on the Stanford SentimentTreebank tasks (Socher et al., 2013), and find that it performs comparatively with the state-of-the-art methods in the literature.

2019-10-28

ArXiv (preprint)

doi.org

arxiv.org

TRAIL: Responsible AI for Professionals and Leaders

Mila Ventures Founder in Residence

AI Advantage: Productivity in Public Service

Arian Hosseini

Publications

TRAIL: Responsible AI for Professionals and Leaders

Mila Ventures Founder in Residence

AI Advantage: Productivity in Public Service

Popular keywords:

Arian Hosseini

Publications