Neural Information Processing Systems http://nips.cc/

Generalization to out-of-distribution (OOD) data is one of the central problems in modern machine learning. Recently, there is a surge of attempts to propose algorithms that mainly build upon the idea of extracting invariant features.

To compare thequality oftargetsamples being selected fortraining, wemeasure reliability precision (howmanyofthe selected target samples were actually predicted correctly?) We report expected calibration error (ECE [7]), lower is better. We separately visualize features before and after in-domain pretraining with MAE 7and DINO 8. Wenote that these features are completely selfsupervised as the model has not seen task labels yet. Regardless, we observe a small degree of taskdiscriminativeness (examples ofthesame class areclustered together) anddomain invariance (examples of the same class but different domains are close) before additional pretraining. We now measure the degree of label overlap between ImageNet-22K and these 3 benchmarks.

Neural Information Processing Systems http://nips.cc/

Generalization to out-of-distribution (OOD) data is one of the central problems in modern machine learning. Recently, there is a surge of attempts to propose algorithms that mainly build upon the idea of extracting invariant features.

The recent success of using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks like question answering, mathematical reasoning, and code generation. However,3 achieving effective LLM alignment depends on high-quality human preference datasets. Collecting these datasets requires human preference annotation, which is costly and resource-intensive, necessitating efficient active data selection methods. Existing methods either lack a strong theoretical foundation or depend on restrictive reward function assumptions (e.g., linearity). To this end, we propose an algorithm, ActiveDPO, that uses a theoretically grounded data selection criterion for non-linear reward functions while directly leveraging the LLM itself to parameterize the reward model that is used for active data selection. As a result, ActiveDPO explicitly accounts for the influence of LLM on data selection, unlike methods that select the data without considering the LLM that is being aligned, thereby leading to more effective and efficient data collection. Extensive experiments show that ActiveDPO outperforms existing methods across various models and datasets.

In various operational problems, risk-sensitive decision makers often encounter the challenge of selecting an alternative with minimal tail risk from a collection of stochastic alternatives that generate random losses. Tail risk, in this context, refers to the potential for experiencing substantial losses, which will be formally defined shortly. Despite the significance of addressing this challenge, the majority of related studies still focus on identifying a subset of the alternatives with acceptable (or minimal) expected losses, rather than using tail risk as a ranking criterion. Our objective is to develop a tractable and effective solution to this problem in situations where decision makers aim to compare the alternatives based only on their tail risk. In practical scenarios, it would be ideal to apply our proposed solution to the aforementioned subset of the alternatives, which can be obtained via existing approaches, so that decision makers can ultimately find an alternative with both acceptable expected loss and minimal tail risk.

The authors present an algorithm for transfer learning using a symbolic program synthesizer for finding the most adequate neural network architecture and selecting relevant neural network modules from previous tasks for transfer. The approach is heavily based on concepts from programming languages, but also studies the relevant concept of high-level transfer that is crucial for true lifelong learning. Results show how the algorithm is capable of selectively transferring (high- and low-level) knowledge in a meaningful way, and numerical results validate the significance of the approach. The authors claim that their method targets the lifelong learning problem, but theirs is really a transfer learning approach. Solving catastrophic forgetting by completely freezing the network parameters precludes the method from being true lifelong learning, in which the learning of subsequent tasks affects the performance of earlier tasks.

Speech Emotion Recognition (SER) is a crucial component in developing general-purpose AI agents capable of natural human-computer interaction. However, building robust multilingual SER systems remains challenging due to the scarcity of labeled data in languages other than English and Chinese. In this paper, we propose an approach to enhance SER performance in low SER resource languages by leveraging data from high-resource languages. Specifically, we employ expressive Speech-to-Speech translation (S2ST) combined with a novel bootstrapping data selection pipeline to generate labeled data in the target language. Extensive experiments demonstrate that our method is both effective and generalizable across different upstream models and languages. Our results suggest that this approach can facilitate the development of more scalable and robust multilingual SER systems.

Dialogue summarization aims to provide a concise and coherent summary of conversations between multiple speakers. While recent advancements in language models have enhanced this process, summarizing dialogues accurately and faithfully remains challenging due to the need to understand speaker interactions and capture relevant information. Indeed, abstractive models used for dialog summarization may generate summaries that contain inconsistencies. We suggest using the semantic information proposed for performing Spoken Language Understanding (SLU) in human-machine dialogue systems for goal-oriented human-human dialogues to obtain a more semantically faithful summary regarding the task. This study introduces three key contributions: First, we propose an exploration of how incorporating task-related information can enhance the summarization process, leading to more semantically accurate summaries. Then, we introduce a new evaluation criterion based on task semantics. Finally, we propose a new dataset version with increased annotated data standardized for research on task-oriented dialogue summarization. The study evaluates these methods using the DECODA corpus, a collection of French spoken dialogues from a call center. Results show that integrating models with task-related information improves summary accuracy, even with varying word error rates.