Alessandro Sordoni

Daniel Toyama

Aaron Courville

Rishabh Agarwal

2024-10-09

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

VinePPO: Accurate Credit Assignment in RL for LLM Mathematical Reasoning

Amirhossein Kazemnejad

Milad Aghajohari

Eva Portelance

Large language models (LLMs) are increasingly required to solve complex reasoning tasks, like mathematical problems, that involve multiple r… (see more)easoning steps before feedback is received. Effectively identifying and prioritizing key steps by accurately assigning credit to these intermediate steps is essential for enhancing model performance. Proximal Policy Optimization (PPO), a state-of-the-art reinforcement learning algorithm for finetuning LLMs, addresses the credit assignment problem by employing value networks to predict the expected cumulative rewards of intermediate states. In this work, we identify significant limitations with this value estimation method. To address this, we propose \methodname that leverages the flexibility of language environments to compute unbiased Monte Carlo-based estimates of the intermediate values. VinePPO consistently outperforms standard PPO, doing so more efficiently and with lower divergence from the reference model. Our findings underscore the critical importance of accurate credit assignment in LLM post-training and present a simple, yet effective solution.

2024-10-09

NeurIPS.cc/2024/Workshop/MATH-AI (accepted)

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

Amirhossein Kazemnejad

Milad Aghajohari

Eva Portelance

2024-10-02

ArXiv (preprint)

Efficient Adversarial Training in LLMs with Continuous Attacks

Sophie Xhonneux

Stephan Günnemann

Gauthier Gidel

Leo Schwinn

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial tra… (see more)ining has proven to be one of the most promising methods to reliably improve robustness against such attacks. Yet, in the context of LLMs, current methods for adversarial training are hindered by the high computational costs required to perform discrete adversarial attacks at each training iteration. We address this problem by instead calculating adversarial attacks in the continuous embedding space of the LLM, which is orders of magnitudes more efficient. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses: the first makes the model robust on continuous embedding attacks computed on an adversarial behaviour dataset; the second ensures the usefulness of the final model by fine-tuning on utility data. Moreover, we introduce C-AdvIPO, an adversarial variant of IPO that does not require utility data for adversarially robust alignment. Our empirical evaluation on five models from different families (Gemma, Phi3, Mistral, Zephyr, Llama2) and at different scales (2B, 3.8B, 7B) shows that both algorithms substantially enhance LLM robustness against discrete attacks (GCG, AutoDAN, PAIR), while maintaining utility. Our results demonstrate that robustness to continuous perturbations can extrapolate to discrete threat models. Thereby, we present a path toward scalable adversarial training algorithms for robustly aligning LLMs.

2024-09-25

NeurIPS.cc/2024/Conference (spotlight)

Efficient Reinforcement Learning by Discovering Neural Pathways

Samin Yeasar Arnob

Riyasat Ohib

Sergey Plis

Amy Zhang

Doina Precup

Reinforcement learning (RL) algorithms have been very successful at tackling complex control problems, such as AlphaGo or fusion control. Ho… (see more)wever, current research mainly emphasizes solution quality, often achieved by using large models trained on large amounts of data, and does not account for the financial, environmental, and societal costs associated with developing and deploying such models. Modern neural networks are often overparameterized and a significant number of parameters can be pruned without meaningful loss in performance, resulting in more efficient use of the model's capacity lottery ticket. We present a methodology for identifying sub-networks within a larger network in reinforcement learning (RL). We call such sub-networks, neural pathways. We show empirically that even very small learned sub-networks, using less than 5% of the large network's parameters, can provide very good quality solutions. We also demonstrate the training of multiple pathways within the same networks in a multitask setup, where each pathway is encouraged to tackle a separate task. We evaluate empirically our approach on several continuous control tasks, in both online and offline training

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Improving Context-Aware Preference Modeling for Language Models

Silviu Pitis

Ziang Xiao

Nicolas Le Roux

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language pr… (see more)esents critical challenges. Direct preference feedback is uninterpretable, difficult to provide where multidimensional criteria may apply, and often inconsistent, either because it is based on incomplete instructions or provided by diverse principals. To address these challenges, we consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context. We decompose reward modeling error according to these two steps, which suggests that supervising context in addition to context-specific preference may be a viable approach to aligning models with diverse human preferences. For this to work, the ability of models to evaluate context-specific preference is critical. To this end, we contribute context-conditioned preference datasets and accompanying experiments that investigate the ability of language models to evaluate context-specific preference. Unlike past datasets, where context-specific preference is highly correlated with general preference, our "preference reversal" datasets disentangle context-specific and general preferences to isolate context-specific capabilities. We use our datasets to (1) show that existing preference models benefit from, but fail to fully consider, added context, (2) finetune a context-aware reward model with context-specific performance exceeding that of GPT-4 and Llama 3 70B, and (3) investigate the potential value of context-aware preference modeling.

2024-09-25

NeurIPS.cc/2024/Conference (poster)

A Survey on Model MoErging: Recycling and Routing Among Specialized Experts for Collaborative Learning

Prateek Yadav

Colin Raffel

Mohammed Muqeeth

Lucas Caccia

Haokun Liu

Tianlong Chen

Mohit Bansal

Leshem Choshen

The availability of performant pre-trained models has led to a proliferation of fine-tuned expert models that are specialized to a particula… (see more)r domain or task. Model MoErging methods aim to recycle expert models to create an aggregate system with improved performance or generalization. A key component of MoErging methods is the creation of a router that decides which expert model(s) to use for a particular input or application. The promise, effectiveness, and large design space of MoErging has spurred the development of many new methods over the past few years. This rapid pace of development has made it challenging to compare different MoErging methods, which are rarely compared to one another and are often validated in different experimental setups. To remedy such gaps, we present a comprehensive survey of MoErging methods that includes a novel taxonomy for cataloging key design choices and clarifying suitable applications for each method. Apart from surveying MoErging research, we inventory software tools and applications that make use of MoErging. We additionally discuss related fields of study such as model merging, multitask learning, and mixture-of-experts models. Taken as a whole, our survey provides a unified overview of existing MoErging methods and creates a solid foundation for future work in this burgeoning field.

2024-08-13

ArXiv (preprint)

Improving Context-Aware Preference Modeling for Language Models

Silviu Pitis

Ziang Xiao

Nicolas Le Roux

While finetuning language models from pairwise preferences has proven remarkably effective, the underspecified nature of natural language pr… (see more)esents critical challenges. Direct preference feedback is uninterpretable, difficult to provide where multidimensional criteria may apply, and often inconsistent, either because it is based on incomplete instructions or provided by diverse principals. To address these challenges, we consider the two-step preference modeling procedure that first resolves the under-specification by selecting a context, and then evaluates preference with respect to the chosen context. We decompose reward modeling error according to these two steps, which suggests that supervising context in addition to context-specific preference may be a viable approach to aligning models with diverse human preferences. For this to work, the ability of models to evaluate context-specific preference is critical. To this end, we contribute context-conditioned preference datasets and accompanying experiments that investigate the ability of language models to evaluate context-specific preference. We use our datasets to (1) show that existing preference models benefit from, but fail to fully consider, added context, (2) finetune a context-aware reward model with context-specific performance exceeding that of GPT-4 and Llama 3 70B on tested datasets, and (3) investigate the value of context-aware preference modeling.

2024-07-20

ArXiv (preprint)

Guiding Language Model Reasoning with Planning Tokens

Xinyi Wang

Lucas Caccia

Oleksiy Ostapenko

Xingdi Yuan

William Yang Wang

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as cha… (see more)in-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely heavily on data-driven methods, while neglecting the structural aspects of the model's reasoning capacity. To encourage a more structural generation of CoT steps, we propose a hierarchical generation scheme: we let the LM generate a planning token at the start of each reasoning step, intuitively serving as a high-level plan of the current step, and add their embeddings to the model parameters. Our approach requires a negligible increase in trainable parameters (0.001%) and can be applied through either full fine-tuning or a more parameter-efficient scheme. We demonstrate our method's effectiveness by applying it to three different LLMs, showing notable accuracy improvements across three math word problem datasets and one multihop QA dataset with respect to standard fine-tuning baselines.

2024-07-10

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

V-STaR: Training Verifiers for Self-Taught Reasoners

Arian Hosseini

Xingdi Yuan

Nikolay Malkin

Aaron Courville

Rishabh Agarwal

Common self-improvement approaches for large language models (LLMs), such as STaR (Zelikman et al., 2022), iteratively fine-tune LLMs on sel… (see more)f-generated solutions to 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.

2024-07-10

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

Towards Modular LLMs by Building and Reusing a Library of LoRAs

Oleksiy Ostapenko

Zhan Su

Edoardo Ponti

Laurent Charlin

Nicolas Le Roux

Matheus Pereira

Lucas Caccia

2024-07-08

Proceedings of the 41st International Conference on Machine Learning (published)

Efficient Adversarial Training in LLMs with Continuous Attacks

Sophie Xhonneux

Stephan Günnemann

Gauthier Gidel

Leo Schwinn

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial tra… (see more)ining has proven to be one of the most promising methods to reliably improve robustness against such attacks. Yet, in the context of LLMs, current methods for adversarial training are hindered by the high computational costs required to perform discrete adversarial attacks at each training iteration. We address this problem by instead calculating adversarial attacks in the continuous embedding space of the LLM, which is orders of magnitudes more efficient. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses: the first makes the model robust on continuous embedding attacks computed on an adversarial behaviour dataset; the second ensures the usefulness of the final model by fine-tuning on utility data. Moreover, we introduce C-AdvIPO, an adversarial variant of IPO that does not require utility data for adversarially robust alignment. Our empirical evaluation on four models from different families (Gemma, Phi3, Mistral, Zephyr) and at different scales (2B, 3.8B, 7B) shows that both algorithms substantially enhance LLM robustness against discrete attacks (GCG, AutoDAN, PAIR), while maintaining utility. Our results demonstrate that robustness to continuous perturbations can extrapolate to discrete threat models. Thereby, we present a path toward scalable adversarial training algorithms for robustly aligning LLMs.

2024-05-24

ArXiv (preprint)