Large language models (LLMs) demonstrate remarkable capabilities but face deployment challenges due to their massive parameter counts. While existing compression techniques like pruning can reduce model size, it leads to significant accuracy degradation under high compression ratios. We present a novel perspective inspired by constant folding in compiler optimization. Our approach enables parameter reduction by treating activation functions in LLMs as linear functions. However, recent LLMs use complex non-linear activations like GELU that prevent direct application of this technique. We propose TARDIS, which enables optimization of LLMs with non-linear activations by partially approximating them with linear functions in frequently occurring input ranges. For outlier inputs, TARDIS employs an online predictor to dynamically fall back to original computations. Our experiments demonstrate that TARDIS achieves 80% parameter reduction in feed-forward networks, while significantly outperforming state-of-the-art pruning methods Wanda and RIA with up to 65% higher accuracy. In practical deployments for a 7B model, TARDIS achieves 1.6x end-to-end inference speedup when integrated with the vLLM serving system, and 1.4x speedup with the widely adopted HuggingFace implementation, while incurring only a 10.9% accuracy trade-off.

Large language models (LLMs) have shown significant improvements in many natural language processing (NLP) tasks, accelerating their rapid adoption across many industries. These models are resource-intensive, requiring extensive computational resources both during training and inference, leading to increased energy consumption and negative environmental impact. As their adoption accelerates, the sustainability of LLMs has become a critical issue, necessitating strategies to optimize their runtime efficiency without compromising performance. Hence, it is imperative to identify the parameters that significantly influence the performance and energy efficiency of LLMs. To that end, in this work, we investigate the effect of important parameters on the performance and energy efficiency of LLMs during inference and examine their trade-offs. First, we analyze how different types of models with varying numbers of parameters and architectures perform on tasks like text generation, question answering, and summarization by benchmarking LLMs such as Falcon-7B, Mistral-7B-v0.1, T5-3B, GPT-2, GPT-J-6B, and GPT-Neo-2.7B. Second, we study input and output sequence characteristics such as sequence length concerning energy consumption, performance, and throughput. Finally, we explore the impact of hardware-based power-saving techniques, i.e., Dynamic Voltage Frequency Scaling (DVFS), on the models' latency and energy efficiency. Our extensive benchmarking and statistical analysis reveal many interesting findings, uncovering how specific optimizations can reduce energy consumption while maintaining throughput and accuracy. This study provides actionable insights for researchers and practitioners to design energy-efficient LLM inference systems.

Resolving knowledge conflicts is a crucial challenge in Question Answering (QA) tasks, as the internet contains numerous conflicting facts and opinions. While some research has made progress in tackling ambiguous settings where multiple valid answers exist, these approaches often neglect to provide source citations, leaving users to evaluate the factuality of each answer. On the other hand, existing work on citation generation has focused on unambiguous settings with single answers, failing to address the complexity of real-world scenarios. Despite the importance of both aspects, no prior research has combined them, leaving a significant gap in the development of QA systems. In this work, we bridge this gap by proposing the novel task of QA with source citation in ambiguous settings, where multiple valid answers exist. To facilitate research in this area, we create a comprehensive framework consisting of: (1) five novel datasets, obtained by augmenting three existing reading comprehension datasets with citation meta-data across various ambiguous settings, such as distractors and paraphrasing; (2) the first ambiguous multi-hop QA dataset featuring real-world, naturally occurring contexts; (3) two new metrics to evaluate models' performances; and (4) several strong baselines using rule-based, prompting, and finetuning approaches over five large language models. We hope that this new task, datasets, metrics, and baselines will inspire the community to push the boundaries of QA research and develop more trustworthy and interpretable systems.

Emotional intelligence in large language models (LLMs) is of great importance in Natural Language Processing. However, the previous research mainly focus on basic sentiment analysis tasks, such as emotion recognition, which is not enough to evaluate LLMs' overall emotional intelligence. Therefore, this paper presents a novel framework named EmotionQueen for evaluating the emotional intelligence of LLMs. The framework includes four distinctive tasks: Key Event Recognition, Mixed Event Recognition, Implicit Emotional Recognition, and Intention Recognition. LLMs are requested to recognize important event or implicit emotions and generate empathetic response. We also design two metrics to evaluate LLMs' capabilities in recognition and response for emotion-related statements. Experiments yield significant conclusions about LLMs' capabilities and limitations in emotion intelligence.

Abstract--Domain-specific question answering remains challenging for language models, given the deep technical knowledge required to answer questions correctly. This difficulty is amplified for smaller language models that cannot encode as much information in their parameters as larger models. The "Specializing Large Language Models for Telecom Networks" challenge aimed to enhance the performance of two small language models, Phi-2 and Falcon-7B in telecommunication question answering. Our solutions achieved leading marks of 81.9% accuracy for Phi-2 and 57.3% for Falcon-7B. Advances in Large Language Models (LLMs) have significantly enhanced their performance across various Natural Language Processing (NLP) tasks.

Prompt engineering is crucial for deploying LLMs but is poorly understood mathematically. We formalize LLM systems as a class of discrete stochastic dynamical systems to explore prompt engineering through the lens of control theory. We investigate the reachable set of output token sequences $R_y(\mathbf x_0)$ for which there exists a control input sequence $\mathbf u$ for each $\mathbf y \in R_y(\mathbf x_0)$ that steers the LLM to output $\mathbf y$ from initial state sequence $\mathbf x_0$. We offer analytic analysis on the limitations on the controllability of self-attention in terms of reachable set, where we prove an upper bound on the reachable set of outputs $R_y(\mathbf x_0)$ as a function of the singular values of the parameter matrices. We present complementary empirical analysis on the controllability of a panel of LLMs, including Falcon-7b, Llama-7b, and Falcon-40b. Our results demonstrate a lower bound on the reachable set of outputs $R_y(\mathbf x_0)$ w.r.t. initial state sequences $\mathbf x_0$ sampled from the Wikitext dataset. We find that the correct next Wikitext token following sequence $\mathbf x_0$ is reachable over 97% of the time with prompts of $k\leq 10$ tokens. We also establish that the top 75 most likely next tokens, as estimated by the LLM itself, are reachable at least 85% of the time with prompts of $k\leq 10$ tokens. Intriguingly, short prompt sequences can dramatically alter the likelihood of specific outputs, even making the least likely tokens become the most likely ones. This control-centric analysis of LLMs demonstrates the significant and poorly understood role of input sequences in steering output probabilities, offering a foundational perspective for enhancing language model system capabilities.

We propose to extract meaning representations from autoregressive language models by considering the distribution of all possible trajectories extending an input text. This strategy is prompt-free, does not require fine-tuning, and is applicable to any pre-trained autoregressive model. Moreover, unlike vector-based representations, distribution-based representations can also model asymmetric relations (e.g., direction of logical entailment, hypernym/hyponym relations) by using algebraic operations between likelihood functions. These ideas are grounded in distributional perspectives on semantics and are connected to standard constructions in automata theory, but to our knowledge they have not been applied to modern language models. We empirically show that the representations obtained from large models align well with human annotations, outperform other zero-shot and prompt-free methods on semantic similarity tasks, and can be used to solve more complex entailment and containment tasks that standard embeddings cannot handle. Finally, we extend our method to represent data from different modalities (e.g., image and text) using multimodal autoregressive models. Our code is available at: https://github.com/tianyu139/meaning-as-trajectories