We present a simple on the fly method for faster inference of large language models. Unlike other (self-)speculative decoding techniques, our method does not require fine-tuning or black-box optimization to generate a fixed draft model, relying instead on simple rules to generate varying draft models adapted to the input context. We show empirically that our light-weight algorithm is competitive with the current SOTA for self-speculative decoding, while being a truly plug-and-play method.

Large Language Models (LLMs), with their increasing depth and number of parameters, have demonstrated outstanding performance across a variety of natural language processing tasks. However, this growth in scale leads to increased computational demands, particularly during inference and fine-tuning. To address these challenges, we introduce EchoAtt, a novel framework aimed at optimizing transformer-based models by analyzing and leveraging the similarity of attention patterns across layers. Our analysis reveals that many inner layers in LLMs, especially larger ones, exhibit highly similar attention matrices. By exploiting this similarity, EchoAtt enables the sharing of attention matrices in less critical layers, significantly reducing computational requirements without compromising performance. We incorporate this approach within a knowledge distillation setup, where a pre-trained teacher model guides the training of a smaller student model. The student model selectively shares attention matrices in layers with high similarity while inheriting key parameters from the teacher. Our best results with TinyLLaMA-1.1B demonstrate that EchoAtt improves inference speed by 15\%, training speed by 25\%, and reduces the number of parameters by approximately 4\%, all while improving zero-shot performance. These findings highlight the potential of attention matrix sharing to enhance the efficiency of LLMs, making them more practical for real-time and resource-limited applications.

Deployment of autoregressive large language models (LLMs) is costly, and as these models increase in size, the associated costs will become even more considerable. Consequently, different methods have been proposed to accelerate the token generation process and reduce costs. Speculative decoding (SD) is among the most promising approaches to speed up the LLM decoding process by verifying multiple tokens in parallel and using an auxiliary smaller draft model to generate the possible tokens. In SD, usually, one draft model is used to serve a specific target model; however, in practice, LLMs are diverse, and we might need to deal with many target models or more than one target model simultaneously. In this scenario, it is not clear which draft model should be used for which target model, and searching among different draft models or training customized draft models can further increase deployment costs. In this paper, we first introduce a novel multi-target scenario for the deployment of draft models for faster inference. Then, we present a novel, more efficient sorted speculative decoding mechanism that outperforms regular baselines in multi-target settings. We evaluated our method on Spec-Bench in different settings, including base models such as Vicuna 7B, 13B, and LLama Chat 70B. Our results suggest that our draft models perform better than baselines for multiple target models at the same time.

This paper introduces a novel method of Progressive Low Rank Decomposition (PLRD) tailored for the compression of large language models. Our approach leverages a pre-trained model, which is then incrementally decompressed to smaller sizes using progressively lower ranks. This method allows for significant reductions in computational overhead and energy consumption, as subsequent models are derived from the original without the need for retraining from scratch. We detail the implementation of PLRD, which strategically decreases the tensor ranks, thus optimizing the trade-off between model performance and resource usage. The efficacy of PLRD is demonstrated through extensive experiments showing that models trained with PLRD method on only 1B tokens maintain comparable performance with traditionally trained models while using 0.1% of the tokens. The versatility of PLRD is highlighted by its ability to generate multiple model sizes from a single foundational model, adapting fluidly to varying computational and memory budgets. Our findings suggest that PLRD could set a new standard for the efficient scaling of LLMs, making advanced AI more feasible on diverse platforms.

Although Large Language Models (LLMs) achieve remarkable performance across various tasks, they often struggle with complex reasoning tasks, such as answering mathematical questions. Recent efforts to address this issue have primarily focused on leveraging mathematical datasets through supervised fine-tuning or self-improvement techniques. However, these methods often depend on high-quality datasets that are difficult to prepare, or they require substantial computational resources for fine-tuning. Inspired by findings that LLMs know how to produce the right answer but struggle to select the correct reasoning path, we propose a purely inference-based searching method -- MindStar (M*). This method formulates reasoning tasks as searching problems and proposes two search ideas to identify the optimal reasoning paths. We evaluate the M* framework on both the GSM8K and MATH datasets, comparing its performance with existing open and closed-source LLMs. Our results demonstrate that M* significantly enhances the reasoning abilities of open-source models, such as Llama-2-13B and Mistral-7B, and achieves comparable performance to GPT-3.5 and Grok-1, but with substantially reduced model size and computational costs.

In this paper, we study how open-source large language models (LLMs) can be effectively deployed for improving query rewriting in conversational search, especially for ambiguous queries. We introduce CHIQ, a two-step method that leverages the capabilities of LLMs to resolve ambiguities in the conversation history before query rewriting. This approach contrasts with prior studies that predominantly use closed-source LLMs to directly generate search queries from conversation history. We demonstrate on five well-established benchmarks that CHIQ leads to state-of-the-art results across most settings, showing highly competitive performances with systems leveraging closed-source LLMs. Our study provides a first step towards leveraging open-source LLMs in conversational search, as a competitive alternative to the prevailing reliance on commercial LLMs. Data, models, and source code will be publicly available upon acceptance at https://github.com/fengranMark/CHIQ.

Recently, there has been considerable attention on detecting hallucinations and omissions in Machine Translation (MT) systems. The two dominant approaches to tackle this task involve analyzing the MT system's internal states or relying on the output of external tools, such as sentence similarity or MT quality estimators. In this work, we introduce OTTAWA, a novel Optimal Transport (OT)-based word aligner specifically designed to enhance the detection of hallucinations and omissions in MT systems. Our approach explicitly models the missing alignments by introducing a "null" vector, for which we propose a novel one-side constrained OT setting to allow an adaptive null alignment. Our approach yields competitive results compared to state-of-the-art methods across 18 language pairs on the HalOmi benchmark. In addition, it shows promising features, such as the ability to distinguish between both error types and perform word-level detection without accessing the MT system's internal states.

Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-training Quantization (PTQ) techniques have been developed to compress LLMs while avoiding expensive re-training. Most PTQ approaches formulate the quantization error based on a layer-wise $\ell_2$ loss, ignoring the model output. Then, each layer is calibrated using its layer-wise Hessian to update the weights towards minimizing the $\ell_2$ quantization error. The Hessian is also used for detecting the most salient weights to quantization. Such PTQ approaches are prone to accuracy drop in low-precision quantization. We propose Output-adaptive Calibration (OAC) to incorporate the model output in the calibration process. We formulate the quantization error based on the distortion of the output cross-entropy loss. OAC approximates the output-adaptive Hessian for each layer under reasonable assumptions to reduce the computational complexity. The output-adaptive Hessians are used to update the weight matrices and detect the salient weights towards maintaining the model output. Our proposed method outperforms the state-of-the-art baselines such as SpQR and BiLLM, especially, at extreme low-precision (2-bit and binary) quantization.

In this work, we dive deep into one of the popular knowledge-grounded dialogue benchmarks that focus on faithfulness, FaithDial. We show that a significant portion of the FaithDial data contains annotation artifacts, which may bias models towards completely ignoring the conversation history. We therefore introduce CHARP, a diagnostic test set, designed for an improved evaluation of hallucinations in conversational model. CHARP not only measures hallucination but also the compliance of the models to the conversation task. Our extensive analysis reveals that models primarily exhibit poor performance on CHARP due to their inability to effectively attend to and reason over the conversation history. Furthermore, the evaluation methods of FaithDial fail to capture these shortcomings, neglecting the conversational history. Our findings indicate that there is substantial room for contribution in both dataset creation and hallucination evaluation for knowledge-grounded dialogue, and that CHARP can serve as a tool for monitoring the progress in this particular research area. CHARP is publicly available at https://huggingface.co/datasets/huawei-noah/CHARP

The ever-growing computational complexity of Large Language Models (LLMs) necessitates efficient deployment strategies. The current state-of-the-art approaches for Post-training Quantization (PTQ) often require calibration to achieve the desired accuracy. This paper presents AdpQ, a novel zero-shot adaptive PTQ method for LLMs that achieves the state-of-the-art performance in low-precision quantization (e.g. 3-bit) without requiring any calibration data. Inspired by Adaptive LASSO regression model, our proposed approach tackles the challenge of outlier activations by separating salient weights using an adaptive soft-thresholding method. Guided by Adaptive LASSO, this method ensures that the quantized weights distribution closely follows the originally trained weights and eliminates the need for calibration data entirely, setting our method apart from popular approaches such as SpQR and AWQ. Furthermore, our method offers an additional benefit in terms of privacy preservation by eliminating any calibration or training data. We also delve deeper into the information-theoretic underpinnings of the proposed method. We demonstrate that it leverages the Adaptive LASSO to minimize the Kullback-Leibler divergence between the quantized weights and the originally trained weights. This minimization ensures the quantized model retains the Shannon information content of the original model to a great extent, guaranteeing efficient deployment without sacrificing accuracy or information. Our results achieve the same accuracy as the existing methods on various LLM benchmarks while the quantization time is reduced by at least 10x, solidifying our contribution to efficient and privacy-preserving LLM deployment.