Large language models (LLMs), typically designed as a function of next-word prediction, have excelled across extensive NLP tasks. Despite the generality, next-word prediction is often not an efficient formulation for many of the tasks, demanding an extreme scale of model parameters (10s or 100s of billions) and sometimes yielding suboptimal performance. In practice, it is often desirable to build more efficient models--despite being less versatile, they still apply to a substantial subset of problems, delivering on par or even superior performance with much smaller model sizes.

Ensuring factual consistency in generated text is crucial for reliable natural language processing applications. However, there is a lack of evaluation tools for factual consistency in Russian texts, as existing tools primarily focus on English corpora. To bridge this gap, we introduce AlignRuScore, a comprehensive adaptation of the AlignScore metric for Russian. To adapt the metric, we fine-tuned a RuBERT-based alignment model with task-specific classification and regression heads on Russian and translated English datasets. Our results demonstrate that a unified alignment metric can be successfully ported to Russian, laying the groundwork for robust multilingual factual consistency evaluation. We release the translated corpora, model checkpoints, and code to support further research.

Aligning AI systems with human values and the value-based preferences of various stakeholders (their value systems) is key in ethical AI. In value-aware AI systems, decision-making draws upon explicit computational representations of individual values (groundings) and their aggregation into value systems. As these are notoriously difficult to elicit and calibrate manually, value learning approaches aim to automatically derive computational models of an agent's values and value system from demonstrations of human behaviour. Nonetheless, social science and humanities literature suggest that it is more adequate to conceive the value system of a society as a set of value systems of different groups, rather than as the simple aggregation of individual value systems. Accordingly, here we formalize the problem of learning the value systems of societies and propose a method to address it based on heuristic deep clustering. The method learns socially shared value groundings and a set of diverse value systems representing a given society by observing qualitative value-based preferences from a sample of agents. We evaluate the proposal in a use case with real data about travelling decisions.

Large Language Models (LLMs) have surged in popularity in recent months, yet they possess concerning capabilities for generating harmful content when manipulated. This study introduces the Query-Response Optimization Attack (QROA), an optimization-based strategy designed to exploit LLMs through a black-box, query-only interaction. QROA adds an optimized trigger to a malicious instruction to compel the LLM to generate harmful content. Unlike previous approaches, QROA does not require access to the model's logit information or any other internal data and operates solely through the standard query-response interface of LLMs. Inspired by deep Q-learning and Greedy coordinate descent, the method iteratively updates tokens to maximize a designed reward function. We tested our method on various LLMs such as Vicuna, Falcon, and Mistral, achieving an Attack Success Rate (ASR) over 80%. We also tested the model against Llama2-chat, the fine-tuned version of Llama2 designed to resist Jailbreak attacks, achieving good ASR with a suboptimal initial trigger seed. This study demonstrates the feasibility of generating jailbreak attacks against deployed LLMs in the public domain using black-box optimization methods, enabling more comprehensive safety testing of LLMs. The code will be made public on the following link: https://github.com/qroa/qroa

Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications. In spite of these successes, there exist concerns that limit the wide application of LLMs. A key problem is the problem of hallucination. Hallucination refers to the fact that in addition to correct responses, LLMs can also generate seemingly correct but factually incorrect responses. This report aims to present a comprehensive review of the current literature on both hallucination detection and hallucination mitigation. We hope that this report can serve as a good reference for both engineers and researchers who are interested in LLMs and applying them to real world tasks.

Drug combination refers to the use of two or more drugs to treat a specific disease at the same time. It is currently the mainstream way to treat complex diseases. Compared with single drugs, drug combinations have better efficacy and can better inhibit toxicity and drug resistance. The computational model based on deep learning concatenates the representation of multiple drugs and the corresponding cell line feature as input, and the output is whether the drug combination can have an inhibitory effect on the cell line. However, this strategy of concatenating multiple representations has the following defects: the alignment of drug representation and cell line representation is ignored, resulting in the synergistic relationship not being reflected positionally in the embedding space. Moreover, the alignment measurement function in deep learning cannot be suitable for drug synergy prediction tasks due to differences in input types. Therefore, in this work, we propose a graph convolutional network with multi-representation alignment (GCNMRA) for predicting drug synergy. In the GCNMRA model, we designed a multi-representation alignment function suitable for the drug synergy prediction task so that the positional relationship between drug representations and cell line representation is reflected in the embedding space. In addition, the vector modulus of drug representations and cell line representation is considered to improve the accuracy of calculation results and accelerate model convergence. Finally, many relevant experiments were run on multiple drug synergy datasets to verify the effectiveness of the above innovative elements and the excellence of the GCNMRA model.

Biological and artificial information processing systems form representations that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the extent to which the representations formed by these diverse systems agree? Do similarities in representations then translate into similar behavior? How can a system's representations be modified to better match those of another system? These questions pertaining to the study of representational alignment are at the heart of some of the most active research areas in cognitive science, neuroscience, and machine learning. For example, cognitive scientists measure the representational alignment of multiple individuals to identify shared cognitive priors, neuroscientists align fMRI responses from multiple individuals into a shared representational space for group-level analyses, and ML researchers distill knowledge from teacher models into student models by increasing their alignment. Unfortunately, there is limited knowledge transfer between research communities interested in representational alignment, so progress in one field often ends up being rediscovered independently in another. Thus, greater cross-field communication would be advantageous. To improve communication between these fields, we propose a unifying framework that can serve as a common language between researchers studying representational alignment. We survey the literature from all three fields and demonstrate how prior work fits into this framework. Finally, we lay out open problems in representational alignment where progress can benefit all three of these fields. We hope that our work can catalyze cross-disciplinary collaboration and accelerate progress for all communities studying and developing information processing systems. We note that this is a working paper and encourage readers to reach out with their suggestions for future revisions.

Many text generation applications require the generated text to be factually consistent with input information. Automatic evaluation of factual consistency is challenging. Previous work has developed various metrics that often depend on specific functions, such as natural language inference (NLI) or question answering (QA), trained on limited data. Those metrics thus can hardly assess diverse factual inconsistencies (e.g., contradictions, hallucinations) that occur in varying inputs/outputs (e.g., sentences, documents) from different tasks. In this paper, we propose AlignScore, a new holistic metric that applies to a variety of factual inconsistency scenarios as above. AlignScore is based on a general function of information alignment between two arbitrary text pieces. Crucially, we develop a unified training framework of the alignment function by integrating a large diversity of data sources, resulting in 4.7M training examples from 7 well-established tasks (NLI, QA, paraphrasing, fact verification, information retrieval, semantic similarity, and summarization). We conduct extensive experiments on large-scale benchmarks including 22 evaluation datasets, where 19 of the datasets were never seen in the alignment training. AlignScore achieves substantial improvement over a wide range of previous metrics. Moreover, AlignScore (355M parameters) matches or even outperforms metrics based on ChatGPT and GPT-4 that are orders of magnitude larger.

Because implicit user feedback for the collaborative filtering (CF) models is biased toward popular items, CF models tend to yield recommendation lists with popularity bias. Previous studies have utilized inverse propensity weighting (IPW) or causal inference to mitigate this problem. However, they solely employ pointwise or pairwise loss functions and neglect to adopt a contrastive loss function for learning meaningful user and item representations. In this paper, we propose Unbiased ConTrastive Representation Learning (uCTRL), optimizing alignment and uniformity functions derived from the InfoNCE loss function for CF models. Specifically, we formulate an unbiased alignment function used in uCTRL. We also devise a novel IPW estimation method that removes the bias of both users and items. Despite its simplicity, uCTRL equipped with existing CF models consistently outperforms state-of-the-art unbiased recommender models, up to 12.22% for Recall@20 and 16.33% for NDCG@20 gains, on four benchmark datasets.