This paper addresses query scheduling for goal-oriented semantic communication in pull-based status update systems. We consider a system where multiple sensing agents (SAs) observe a source characterized by various attributes and provide updates to multiple actuation agents (AAs), which act upon the received information to fulfill their heterogeneous goals at the endpoint. A hub serves as an intermediary, querying the SAs for updates on observed attributes and maintaining a knowledge base, which is then broadcast to the AAs. The AAs leverage the knowledge to perform their actions effectively. To quantify the semantic value of updates, we introduce a grade of effectiveness (GoE) metric. Furthermore, we integrate cumulative perspective theory (CPT) into the long-term effectiveness analysis to account for risk awareness and loss aversion in the system. Leveraging this framework, we compute effect-aware scheduling policies aimed at maximizing the expected discounted sum of CPT-based total GoE provided by the transmitted updates while complying with a given query cost constraint. To achieve this, we propose a model-based solution based on dynamic programming and model-free solutions employing state-of-the-art deep reinforcement learning (DRL) algorithms. Our findings demonstrate that effect-aware scheduling significantly enhances the effectiveness of communicated updates compared to benchmark scheduling methods, particularly in settings with stringent cost constraints where optimal query scheduling is vital for system performance and overall effectiveness.

Quantifying the uncertainty in the factual parametric knowledge of Large Language Models (LLMs), especially in a black-box setting, poses a significant challenge. Existing methods, which gauge a model's uncertainty through evaluating self-consistency in responses to the original query, do not always capture true uncertainty. Models might respond consistently to the origin query with a wrong answer, yet respond correctly to varied questions from different perspectives about the same query, and vice versa. In this paper, we propose a novel method, DiverseAgentEntropy, for evaluating a model's uncertainty using multi-agent interaction under the assumption that if a model is certain, it should consistently recall the answer to the original query across a diverse collection of questions about the same original query. We further implement an abstention policy to withhold responses when uncertainty is high. Our method offers a more accurate prediction of the model's reliability and further detects hallucinations, outperforming other self-consistency-based methods. Additionally, it demonstrates that existing models often fail to consistently retrieve the correct answer to the same query under diverse varied questions even when knowing the correct answer.

Aligning Large Language Models (LLM) to address subjectivity and nuanced preference levels requires adequate flexibility and control, which can be a resource-intensive and time-consuming procedure. Existing training-time alignment methods require full re-training when a change is needed and inference-time ones typically require access to the reward model at each inference step. To address these limitations, we introduce inference-time model alignment method that learns encoded representations of preference dimensions, called Alignment Vectors (AV). These representations are computed by subtraction of the base model from the aligned model as in model editing enabling dynamically adjusting the model behavior during inference through simple linear operations. Even though the preference dimensions can span various granularity levels, here we focus on three gradual response levels across three specialized domains: medical, legal, and financial, exemplifying its practical potential. This new alignment paradigm introduces adjustable preference knobs during inference, allowing users to tailor their LLM outputs while reducing the inference cost by half compared to the prompt engineering approach. Additionally, we find that AVs are transferable across different fine-tuning stages of the same model, demonstrating their flexibility. AVs also facilitate multidomain, diverse preference alignment, making the process 12x faster than the retraining approach. Aligning LLMs is crucial for adapting them to meet human preferences. Standard training-time alignment methods, such as RLHF (Ouyang et al., 2022) and DPO (Rafailov et al., 2024), are conducted during model training. However, making nuanced preference adjustments during inference with these approaches would necessitate retraining, which requires substantial amounts of time, preference data and computational resources. Inference-time LLM alignment, by contrast, delays the alignment process until inference (Wang et al., 2024). While preference alignment can be achieved through training-time methods or targeted prompting, fine-grained control over preferences at inference remains largely unexplored in current State-of-the-Art (SOTA) works (Sahoo et al., 2024; Guo et al., 2024).

The safety alignment ability of Vision-Language Models (VLMs) is prone to be degraded by the integration of the vision module compared to its LLM backbone. We investigate this phenomenon, dubbed as ''safety alignment degradation'' in this paper, and show that the challenge arises from the representation gap that emerges when introducing vision modality to VLMs. In particular, we show that the representations of multi-modal inputs shift away from that of text-only inputs which represent the distribution that the LLM backbone is optimized for. At the same time, the safety alignment capabilities, initially developed within the textual embedding space, do not successfully transfer to this new multi-modal representation space. To reduce safety alignment degradation, we introduce Cross-Modality Representation Manipulation (CMRM), an inference time representation intervention method for recovering the safety alignment ability that is inherent in the LLM backbone of VLMs, while simultaneously preserving the functional capabilities of VLMs. The empirical results show that our framework significantly recovers the alignment ability that is inherited from the LLM backbone with minimal impact on the fluency and linguistic capabilities of pre-trained VLMs even without additional training. Specifically, the unsafe rate of LLaVA-7B on multi-modal input can be reduced from 61.53% to as low as 3.15% with only inference-time intervention. WARNING: This paper contains examples of toxic or harmful language.

Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on new domain risks Catastrophic Forgetting (CF). To address this, Lifelong Learning (LLL) algorithms have been proposed for ASR. Prior research has explored techniques such as Elastic Weight Consolidation, Knowledge Distillation, and Replay, all of which necessitate either additional parameters or access to prior domain data. We propose Sequential Model Editing as a novel method to continually learn new domains in ASR systems. Different than previous methods, our approach does not necessitate access to prior datasets or the introduction of extra parameters. Our study demonstrates up to 15% Word Error Rate Reduction (WERR) over fine-tuning baseline, and superior efficiency over other LLL techniques on CommonVoice English multi-accent dataset.

The development of large language models (LLM) has shown progress on reasoning, though studies have largely considered either English or simple reasoning tasks. To address this, we introduce a multilingual structured reasoning and explanation dataset, termed xSTREET, that covers four tasks across six languages. xSTREET exposes a gap in base LLM performance between English and non-English reasoning tasks. We then propose two methods to remedy this gap, building on the insight that LLMs trained on code are better reasoners. First, at training time, we augment a code dataset with multilingual comments using machine translation while keeping program code as-is. Second, at inference time, we bridge the gap between training and inference by employing a prompt structure that incorporates step-by-step code primitives to derive new facts and find a solution. Our methods show improved multilingual performance on xSTREET, most notably on the scientific commonsense reasoning subtask. Furthermore, the models show no regression on non-reasoning tasks, thus demonstrating our techniques maintain general-purpose abilities.

Reward machines inform reinforcement learning agents about the reward structure of the environment and often drastically speed up the learning process. However, reward machines only accept Boolean features such as robot-reached-gold. Consequently, many inherently numeric tasks cannot profit from the guidance offered by reward machines. To address this gap, we aim to extend reward machines with numeric features such as distance-to-gold. For this, we present two types of reward machines: numeric-Boolean and numeric. In a numeric-Boolean reward machine, distance-to-gold is emulated by two Boolean features distance-to-gold-decreased and robot-reached-gold. In a numeric reward machine, distance-to-gold is used directly alongside the Boolean feature robot-reached-gold. We compare our new approaches to a baseline reward machine in the Craft domain, where the numeric feature is the agent-to-target distance. We use cross-product Q-learning, Q-learning with counter-factual experiences, and the options framework for learning. Our experimental results show that our new approaches significantly outperform the baseline approach. Extending reward machines with numeric features opens up new possibilities of using reward machines in inherently numeric tasks.

This paper studies semantic-aware communication for remote estimation of multiple Markov sources over a lossy and rate-constrained channel. Unlike most existing studies that treat all source states equally, we exploit the semantics of information and consider that the remote actuator has different tolerances for the estimation errors of different states. We aim to find an optimal scheduling policy that minimizes the long-term state-dependent costs of estimation errors under a transmission frequency constraint. We theoretically show the structure of the optimal policy by leveraging the average-cost Constrained Markov Decision Process (CMDP) theory and the Lagrangian dynamic programming. By exploiting the optimal structural results, we develop a novel policy search algorithm, termed intersection search plus relative value iteration (Insec-RVI), that can find the optimal policy using only a few iterations. To avoid the ``curse of dimensionality'' of MDPs, we propose an online low-complexity drift-plus-penalty (DPP) scheduling algorithm based on the Lyapunov optimization theorem. We also design an efficient average-cost Q-learning algorithm to estimate the optimal policy without knowing a priori the channel and source statistics. Numerical results show that continuous transmission is inefficient, and remarkably, our semantic-aware policies can attain the optimum by strategically utilizing fewer transmissions by exploiting the timing of the important information.

Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs. Previous approaches augment textual dialogues with retrieved images, posing privacy, diversity, and quality constraints. In this work, we introduce \textbf{M}ultimodal \textbf{A}ugmented \textbf{G}enerative \textbf{I}mages \textbf{D}ialogues (MAGID), a framework to augment text-only dialogues with diverse and high-quality images. Subsequently, a diffusion model is applied to craft corresponding images, ensuring alignment with the identified text. Finally, MAGID incorporates an innovative feedback loop between an image description generation module (textual LLM) and image quality modules (addressing aesthetics, image-text matching, and safety), that work in tandem to generate high-quality and multi-modal dialogues. We compare MAGID to other SOTA baselines on three dialogue datasets, using automated and human evaluation. Our results show that MAGID is comparable to or better than baselines, with significant improvements in human evaluation, especially against retrieval baselines where the image database is small.

We consider the communication of natural language text from a source to a destination over noiseless and character-erasure channels. We exploit language's inherent correlations and predictability to constrain transmission costs by allowing the destination to predict or complete words with potential dissimilarity with the source text. Concretely, our objective is to obtain achievable $(\bar{c}, \bar{s})$ pairs, where $\bar{c}$ is the average transmission cost at the source and $\bar{s}$ is the average semantic similarity measured via cosine similarity between vector embedding of words at the source and those predicted/completed at the destination. We obtain $(\bar{c}, \bar{s})$ pairs for neural language and first-order Markov chain-based small language models (SLM) for prediction, using both a threshold policy that transmits a word if its cosine similarity with that predicted/completed at the destination is below a threshold, and a periodic policy, which transmits words after a specific interval and predicts/completes the words in between, at the destination. We adopt an SLM for word completion. We demonstrate that, when communication occurs over a noiseless channel, the threshold policy achieves a higher $\bar{s}$ for a given $\bar{c}$ than the periodic policy and that the $\bar{s}$ achieved with the neural SLM is greater than or equal to that of the Markov chain-based algorithm for the same $\bar{c}$. The improved performance comes with a higher complexity in terms of time and computing requirements. However, when communication occurs over a character-erasure channel, all prediction algorithms and scheduling policies perform poorly. Furthermore, if character-level Huffman coding is used, the required $\bar{c}$ to achieve a given $\bar{s}$ is reduced, but the above observations still apply.