KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts for more than 80\% of this memory consumption. Nowadays, most existing KV cache compression methods focus on intra-layer compression within a single Transformer layer but few works consider layer-wise compression. In this paper, we propose a plug-and-play method called \textit{KVSharer}, which shares the KV cache between layers to achieve layer-wise compression. Rather than intuitively sharing based on higher similarity, we discover a counterintuitive phenomenon: sharing dissimilar KV caches better preserves the model performance. Experiments show that \textit{KVSharer} can reduce KV cache computation by 30\%, thereby lowering memory consumption without significantly impacting model performance and it can also achieve at least 1.3 times generation acceleration. Additionally, we verify that \textit{KVSharer} is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.

Instruction-Driven Game Engine: A Poker Case Study

The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game descriptions and generate game-play processes. The IDGE allows users to create games simply by natural language instructions, which significantly lowers the barrier for game development. We approach the learning process for IDGEs as a Next State Prediction task, wherein the model autoregressively predicts the game states given player actions. The computation of game states must be precise; otherwise, slight errors could corrupt the game-play experience. This is challenging because of the gap between stability and diversity. To address this, we train the IDGE in a curriculum manner that progressively increases its exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, which not only supports a wide range of poker variants but also allows for highly individualized new poker games through natural language inputs. This work lays the groundwork for future advancements in transforming how games are created and played.

Are LLMs Aware that Some Questions are not Open-ended?

Large Language Models (LLMs) have shown the impressive capability of answering questions in a wide range of scenarios. However, when LLMs face different types of questions, it is worth exploring whether LLMs are aware that some questions have limited answers and need to respond more deterministically but some do not. We refer to this as question awareness of LLMs. The lack of question awareness in LLMs leads to two phenomena that LLMs are: (1) too casual to answer non-open-ended questions or (2) too boring to answer open-ended questions. In this paper, we first evaluate the question awareness in LLMs. The experimental results show that LLMs have the issues of lacking awareness of questions in certain domains, e.g. factual knowledge, resulting in hallucinations during the generation. To mitigate these, we propose a method called Question Awareness Temperature Sampling (QuATS). This method enhances the question awareness of LLMs by adaptively adjusting the output distributions based on question features. The automatic adjustment in QuATS eliminates the need for manual temperature tuning in text generation and consistently improves model performance in various benchmarks.

VHASR: A Multimodal Speech Recognition System With Vision Hotwords

The image-based multimodal automatic speech recognition (ASR) model enhances speech recognition performance by incorporating audio-related image. However, some works suggest that introducing image information to model does not help improving ASR performance. In this paper, we propose a novel approach effectively utilizing audio-related image information and set up VHASR, a multimodal speech recognition system that uses vision as hotwords to strengthen the model's speech recognition capability. Our system utilizes a dual-stream architecture, which firstly transcribes the text on the two streams separately, and then combines the outputs. We evaluate the proposed model on four datasets: Flickr8k, ADE20k, COCO, and OpenImages. The experimental results show that VHASR can effectively utilize key information in images to enhance the model's speech recognition ability. Its performance not only surpasses unimodal ASR, but also achieves SOTA among existing image-based multimodal ASR.

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT assists the model in adapting to tasks through minimal parameter modifications, but the training process still demands high hardware requirements, even with a small number of parameters involved. To address these challenges, we propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning, maintaining low inference costs. RTD constructs a reference datastore from the provided training examples and optimizes the LLM's final vocabulary distribution by flexibly selecting suitable references based on the input, resulting in more trustable responses and enabling the model to adapt to downstream tasks at a low cost. Experimental evaluations on various LLMs using different benchmarks demonstrate that RTD establishes a new paradigm for augmenting models to downstream tasks. Furthermore, our method exhibits strong orthogonality with traditional methods, allowing for concurrent usage.

A Coin Has Two Sides: A Novel Detector-Corrector Framework for Chinese Spelling Correction

Chinese Spelling Correction (CSC) stands as a foundational Natural Language Processing (NLP) task, which primarily focuses on the correction of erroneous characters in Chinese texts. Certain existing methodologies opt to disentangle the error correction process, employing an additional error detector to pinpoint error positions. However, owing to the inherent performance limitations of error detector, precision and recall are like two sides of the coin which can not be both facing up simultaneously. Furthermore, it is also worth investigating how the error position information can be judiciously applied to assist the error correction. In this paper, we introduce a novel approach based on error detector-corrector framework. Our detector is designed to yield two error detection results, each characterized by high precision and recall. Given that the occurrence of errors is context-dependent and detection outcomes may be less precise, we incorporate the error detection results into the CSC task using an innovative feature fusion strategy and a selective masking strategy. Empirical experiments conducted on mainstream CSC datasets substantiate the efficacy of our proposed method.

Nothing in Excess: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering

Safety alignment is indispensable for Large language models (LLMs) to defend threats from malicious instructions. However, recent researches reveal safety-aligned LLMs prone to reject benign queries due to the exaggerated safety issue, limiting their helpfulness. In this paper, we propose a Safety-Conscious Activation Steering (SCANS) method to mitigate the exaggerated safety concerns in aligned LLMs. First, SCANS extracts the refusal steering vectors within the activation space and utilizes vocabulary projection to anchor some specific safety-critical layers which influence model refusal behavior. Second, by tracking the hidden state transition, SCANS identifies the steering direction and steers the model behavior accordingly, achieving a balance between exaggerated safety and adequate safety. Experiments show that SCANS achieves new state-of-the-art performance on XSTest and OKTest benchmarks, without impairing their defense capability against harmful queries and maintaining almost unchanged model capability.

MEGen: Generative Backdoor in Large Language Models via Model Editing

Large language models (LLMs) have demonstrated remarkable capabilities. Their powerful generative abilities enable flexible responses based on various queries or instructions. Emerging as widely adopted generalists for diverse tasks, LLMs are still vulnerable to backdoors. This paper proposes an editing-based generative backdoor, named MEGen, aiming to create a customized backdoor for NLP tasks with the least side effects. In our approach, we first leverage a language model to insert a trigger selected on fixed metrics into the input, then design a pipeline of model editing to directly embed a backdoor into an LLM. By adjusting a small set of local parameters with a mini-batch of samples, MEGen significantly enhances time efficiency and achieves high robustness. Experimental results indicate that our backdoor attack strategy achieves a high attack success rate on poison data while maintaining the model's performance on clean data. Notably, the backdoored model, when triggered, can freely output pre-set dangerous information while successfully completing downstream tasks. This suggests that future LLM applications could be guided to deliver certain dangerous information, thus altering the LLM's generative style. We believe this approach provides insights for future LLM applications and the execution of backdoor attacks on conversational AI systems.

BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction

Retrosynthesis analysis is pivotal yet challenging in drug discovery and organic chemistry. Despite the proliferation of computational tools over the past decade, AI-based systems often fall short in generalizing across diverse reaction types and exploring alternative synthetic pathways. This paper presents BatGPT-Chem, a large language model with 15 billion parameters, tailored for enhanced retrosynthesis prediction. Integrating chemical tasks via a unified framework of natural language and SMILES notation, this approach synthesizes extensive instructional data from an expansive chemical database. Employing both autoregressive and bidirectional training techniques across over one hundred million instances, BatGPT-Chem captures a broad spectrum of chemical knowledge, enabling precise prediction of reaction conditions and exhibiting strong zero-shot capabilities. Superior to existing AI methods, our model demonstrates significant advancements in generating effective strategies for complex molecules, as validated by stringent benchmark tests. BatGPT-Chem not only boosts the efficiency and creativity of retrosynthetic analysis but also establishes a new standard for computational tools in synthetic design. This development empowers chemists to adeptly address the synthesis of novel compounds, potentially expediting the innovation cycle in drug manufacturing and materials science. We release our trial platform at \url{https://www.batgpt.net/dapp/chem}.

Self-Directed Turing Test for Large Language Models

The Turing test examines whether AIs can exhibit human-like behaviour in natural language conversations. Traditional Turing tests adopt a rigid dialogue format where each participant sends only one message each time and require continuous human involvement to direct the entire interaction with the test subject. This fails to reflect a natural conversational style and hinders the evaluation of Large Language Models (LLMs) in complex and prolonged dialogues. This paper proposes the Self-Directed Turing Test, which extends the original test with a burst dialogue format, allowing more dynamic exchanges by multiple consecutive messages. It further efficiently reduces human workload by having the LLM self-direct the majority of the test process, iteratively generating dialogues that simulate its interaction with humans. With the pseudo-dialogue history, the model then engages in a shorter dialogue with a human, which is paired with a human-human conversation on the same topic to be judged using questionnaires. We introduce the X-Turn Pass-Rate metric to assess the human likeness of LLMs across varying durations. While LLMs like GPT-4 initially perform well, achieving pass rates of 51.9% and 38.9% during 3 turns and 10 turns of dialogues respectively, their performance drops as the dialogue progresses, which underscores the difficulty in maintaining consistency in the long term.