Large language models (LLMs) have achieved remarkable success in NLP and multimodal tasks, among others. Despite these successes, two main challenges remain in developing LLMs: (i) high computational cost, and (ii) fair and objective evaluations. In this paper, we report a solution to significantly reduce LLM training cost through a growth strategy. We demonstrate that a 101B-parameter LLM with 0.31T tokens can be trained with a budget of 100K US dollars. Inspired by IQ tests, we also consolidate an additional range of evaluations on top of existing evaluations that focus on knowledge-oriented abilities. These IQ evaluations include symbolic mapping, rule understanding, pattern mining, and anti-interference. Such evaluations minimize the potential impact of memorization. Experimental results show that our model, named FLM-101B, trained with a budget of 100K US dollars, achieves performance comparable to powerful and well-known models, e.g., GPT-3 and GLM-130B, especially on the additional range of IQ evaluations. The checkpoint of FLM-101B is released at https://huggingface.co/CofeAI/FLM-101B.
Although demonstrating superb performance on various NLP tasks, large language models (LLMs) still suffer from the hallucination problem, which threatens the reliability of LLMs. To measure the level of hallucination of LLMs, previous works first categorize the hallucination according to the phenomenon similarity, then quantify the proportion that model outputs contain hallucinatory contents. However, such hallucination rates could easily be distorted by confounders. Moreover, such hallucination rates could not reflect the reasons for the hallucination, as similar hallucinatory phenomena may originate from different sources. To address these issues, we propose to combine the hallucination level quantification and hallucination reason investigation through an association analysis, which builds the relationship between the hallucination rate of LLMs with a set of risk factors. In this way, we are able to observe the hallucination level under each value of each risk factor, examining the contribution and statistical significance of each risk factor, meanwhile excluding the confounding effect of other factors. Additionally, by recognizing the risk factors according to a taxonomy of model capability, we reveal a set of potential deficiencies in commonsense memorization, relational reasoning, and instruction following, which may further provide guidance for the pretraining and supervised fine-tuning process of LLMs to mitigate the hallucination.
In the era of large-scale language models, the substantial parameter size poses significant challenges for deployment. Being a prevalent compression technique, quantization has emerged as the mainstream practice to tackle this issue, which is mainly centered on two recipes W8A8 and W4A16 (i.e. weights and activations in such bit widths). In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes. Therefore, we can leverage the benefit in the I/O utilization of 4-bit weight quantization and the acceleration due to 8-bit matrix computation. Nevertheless, the W4A8 faces notorious performance degradation. As a remedy, we involve layerwise activation quantization strategies which feature a novel logarithmic equalization for most intractable layers, and we combine them with fine-grained weight quantization. Without whistles and bells, we eliminate the necessity for further fine-tuning and obtain the state-of-the-art W4A8 quantized performance on BLOOM, LLaMA, and LLaMA-2 on standard benchmarks. We confirm that the W4A8 quantization is achievable for the deployment of large language models, fostering their wide-spreading real-world applications.
Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements. However, the huge memory consumption of state-of-the-art models makes it hard to deploy them on vehicles, and the non-trivial latency will affect the real-time perception of streaming applications. Despite the wide application of quantization to lighten models, we show in our paper that directly applying quantization in BEV tasks will 1) make the training unstable, and 2) lead to intolerable performance degradation. To solve these issues, our method QD-BEV enables a novel view-guided distillation (VGD) objective, which can stabilize the quantization-aware training (QAT) while enhancing the model performance by leveraging both image features and BEV features. Our experiments show that QD-BEV achieves similar or even better accuracy than previous methods with significant efficiency gains. On the nuScenes datasets, the 4-bit weight and 6-bit activation quantized QD-BEV-Tiny model achieves 37.2% NDS with only 15.8 MB model size, outperforming BevFormer-Tiny by 1.8% with an 8x model compression. On the Small and Base variants, QD-BEV models also perform superbly and achieve 47.9% NDS (28.2 MB) and 50.9% NDS (32.9 MB), respectively.
Subword tokenization is a key part of many NLP pipelines. However, little is known about why some tokenizer and hyperparameter combinations lead to better downstream model performance than others. We propose that good tokenizers lead to \emph{efficient} channel usage, where the channel is the means by which some input is conveyed to the model and efficiency can be quantified in information-theoretic terms as the ratio of the Shannon entropy to the maximum possible entropy of the token distribution. Yet, an optimal encoding according to Shannon entropy assigns extremely long codes to low-frequency tokens and very short codes to high-frequency tokens. Defining efficiency in terms of R\'enyi entropy, on the other hand, penalizes distributions with either very high or very low-frequency tokens. In machine translation, we find that across multiple tokenizers, the R\'enyi entropy with $\alpha = 2.5$ has a very strong correlation with \textsc{Bleu}: $0.78$ in comparison to just $-0.32$ for compressed length.
Byte-Pair Encoding (BPE) is a popular algorithm used for tokenizing data in NLP, despite being devised initially as a compression method. BPE appears to be a greedy algorithm at face value, but the underlying optimization problem that BPE seeks to solve has not yet been laid down. We formalize BPE as a combinatorial optimization problem. Via submodular functions, we prove that the iterative greedy version is a $\frac{1}{{\sigma(\boldsymbol{\mu}^\star)}}(1-e^{-{\sigma(\boldsymbol{\mu}^\star)}})$-approximation of an optimal merge sequence, where ${\sigma(\boldsymbol{\mu}^\star)}$ is the total backward curvature with respect to the optimal merge sequence $\boldsymbol{\mu}^\star$. Empirically the lower bound of the approximation is $\approx 0.37$. We provide a faster implementation of BPE which improves the runtime complexity from $\mathcal{O}\left(N M\right)$ to $\mathcal{O}\left(N \log M\right)$, where $N$ is the sequence length and $M$ is the merge count. Finally, we optimize the brute-force algorithm for optimal BPE using memoization.
Recently, there has been a growing interest in the development of gradient-based sampling algorithms for text generation, especially in the context of controlled generation. However, there exists a lack of theoretically grounded and principled approaches for this task. In this paper, we take an important step toward building a principled approach for sampling from language models with gradient-based methods. We use discrete distributions given by language models to define densities and develop an algorithm based on Hamiltonian Monte Carlo to sample from them. We name our gradient-based technique Structured Voronoi Sampling (SVS). In an experimental setup where the reference distribution is known, we show that the empirical distribution of SVS samples is closer to the reference distribution compared to alternative sampling schemes. Furthermore, in a controlled generation task, SVS is able to generate fluent and diverse samples while following the control targets significantly better than other methods.
To predict the next token, autoregressive models ordinarily examine the past. Could they also benefit from also examining hypothetical futures? We consider a novel Transformer-based autoregressive architecture that estimates the next-token distribution by extrapolating multiple continuations of the past, according to some proposal distribution, and attending to these extended strings. This architecture draws insights from classical AI systems such as board game players: when making a local decision, a policy may benefit from exploring possible future trajectories and analyzing them. On multiple tasks including morphological inflection and Boolean satisfiability, our lookahead model is able to outperform the ordinary Transformer model of comparable size. However, on some tasks, it appears to be benefiting from the extra computation without actually using the lookahead information. We discuss possible variant architectures as well as future speedups.
Language modeling, a central task in natural language processing, involves estimating a probability distribution over strings. In most cases, the estimated distribution sums to 1 over all finite strings. However, in some pathological cases, probability mass can ``leak'' onto the set of infinite sequences. In order to characterize the notion of leakage more precisely, this paper offers a measure-theoretic treatment of language modeling. We prove that many popular language model families are in fact tight, meaning that they will not leak in this sense. We also generalize characterizations of tightness proposed in previous works.