SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper presents a novel framework that leverages sparse autoencoders (SAE) to interpret how instruction following works in these models. We demonstrate how the features we identify can effectively steer model outputs to align with given instructions. Through analysis of SAE latent activations, we identify specific latents responsible for instruction following behavior. Our findings reveal that instruction following capabilities are encoded by a distinct set of instruction-relevant SAE latents. These latents both show semantic proximity to relevant instructions and demonstrate causal effects on model behavior. Our research highlights several crucial factors for achieving effective steering performance: precise feature identification, the role of final layer, and optimal instruction positioning. Additionally, we demonstrate that our methodology scales effectively across SAEs and LLMs of varying sizes.

Investigating the Shortcomings of LLMs in Step-by-Step Legal Reasoning

Reasoning abilities of LLMs have been a key focus in recent years. One challenging reasoning domain with interesting nuances is legal reasoning, which requires careful application of rules, and precedents while balancing deductive and analogical reasoning, and conflicts between rules. Although there have been a few works on using LLMs for legal reasoning, their focus has been on overall accuracy. In this paper, we dig deeper to do a step-by-step analysis and figure out where they commit errors. We use the college-level Multiple Choice Question-Answering (MCQA) task from the \textit{Civil Procedure} dataset and propose a new error taxonomy derived from initial manual analysis of reasoning chains with respect to several LLMs, including two objective measures: soundness and correctness scores. We then develop an LLM-based automated evaluation framework to identify reasoning errors and evaluate the performance of LLMs. The computation of soundness and correctness on the dataset using the auto-evaluator framework reveals several interesting insights. Furthermore, we show that incorporating the error taxonomy as feedback in popular prompting techniques marginally increases LLM performance. Our work will also serve as an evaluation framework that can be used in detailed error analysis of reasoning chains for logic-intensive complex tasks.

Effective Guidance for Model Attention with Simple Yes-no Annotations

Modern deep learning models often make predictions by focusing on irrelevant areas, leading to biased performance and limited generalization. Existing methods aimed at rectifying model attention require explicit labels for irrelevant areas or complex pixel-wise ground truth attention maps. We present CRAYON (Correcting Reasoning with Annotations of Yes Or No), offering effective, scalable, and practical solutions to rectify model attention using simple yes-no annotations. CRAYON empowers classical and modern model interpretation techniques to identify and guide model reasoning: CRAYON-ATTENTION directs classic interpretations based on saliency maps to focus on relevant image regions, while CRAYON-PRUNING removes irrelevant neurons identified by modern concept-based methods to mitigate their influence. Through extensive experiments with both quantitative and human evaluation, we showcase CRAYON's effectiveness, scalability, and practicality in refining model attention. CRAYON achieves state-of-the-art performance, outperforming 12 methods across 3 benchmark datasets, surpassing approaches that require more complex annotations.

ProFL: Performative Robust Optimal Federated Learning

Performative prediction (PP) is a framework that captures distribution shifts that occur during the training of machine learning models due to their deployment. As the trained model is used, its generated data could cause the model to evolve, leading to deviations from the original data distribution. The impact of such model-induced distribution shifts in the federated learning (FL) setup remains unexplored despite being increasingly likely to transpire in real-life use cases. Although Jin et al. (2024) recently extended PP to FL in a straightforward manner, the resulting model only converges to a performative stable point, which may be far from optimal. The methods in Izzo et al. (2021); Miller et al. (2021) can find a performative optimal point in centralized settings, but they require the performative risk to be convex and the training data to be noiseless, assumptions often violated in realistic FL systems. This paper overcomes all of these shortcomings and proposes Performative robust optimal Federated Learning (ProFL), an algorithm that finds performative optimal points in FL from noisy and contaminated data. We present the convergence analysis under the Polyak-Lojasiewicz condition, which applies to non-convex objectives. Extensive experiments on multiple datasets validate our proposed algorithms' efficiency.

Can Knowledge Editing Really Correct Hallucinations?

Large Language Models (LLMs) suffer from hallucinations, referring to the non-factual information in generated content, despite their superior capacities across tasks. Meanwhile, knowledge editing has been developed as a new popular paradigm to correct the erroneous factual knowledge encoded in LLMs with the advantage of avoiding retraining from scratch. However, one common issue of existing evaluation datasets for knowledge editing is that they do not ensure LLMs actually generate hallucinated answers to the evaluation questions before editing. When LLMs are evaluated on such datasets after being edited by different techniques, it is hard to directly adopt the performance to assess the effectiveness of different knowledge editing methods in correcting hallucinations. Thus, the fundamental question remains insufficiently validated: Can knowledge editing really correct hallucinations in LLMs? We proposed HalluEditBench to holistically benchmark knowledge editing methods in correcting real-world hallucinations. First, we rigorously construct a massive hallucination dataset with 9 domains, 26 topics and more than 6,000 hallucinations. Then, we assess the performance of knowledge editing methods in a holistic way on five dimensions including Efficacy, Generalization, Portability, Locality, and Robustness. Through HalluEditBench, we have provided new insights into the potentials and limitations of different knowledge editing methods in correcting hallucinations, which could inspire future improvements and facilitate the progress in the field of knowledge editing.

Deliberate Reasoning for LLMs as Structure-aware Planning with Accurate World Model

Enhancing the reasoning capabilities of large language models (LLMs) remains a key challenge, especially for tasks that require complex, multi-step decision-making. Humans excel at these tasks by leveraging deliberate planning with an internal world model to simulate the potential outcomes of various actions. Inspired by this, we propose a novel multi-step reasoning framework for LLMs, referred to as Structure-aware Planning with Accurate World Model (SWAP). Unlike previous approaches that rely solely on Chain-of-Thought (CoT) reasoning in natural language, SWAP incorporates structural information to guide the reasoning process via a world model and provides a soft verification mechanism over the steps. Moreover, SWAP overcomes the challenge of accurate world state predictions in complex reasoning tasks by introducing a Generator-Discriminator architecture, which enables more reliable world modeling. Specifically, the generator predicts the next state, and the discriminator ensures alignment with the logical consistency required by the problem context. SWAP also encourages the policy model to explore a broad range of potential actions to prevent premature convergence. By resolving the bottlenecks of generation diversity for both actions and states using diversity-based modeling (DBM) and improving discrimination accuracy through contrastive ranking (CR), SWAP significantly enhances the reasoning performance of LLMs. We evaluate SWAP across diverse reasoning-intensive benchmarks including math reasoning, logical reasoning, and coding tasks. Extensive experiments demonstrate that SWAP achieves substantial improvements over the baselines and consistently outperforms existing LLMs of similar sizes.

Benchmarking Graph Conformal Prediction: Empirical Analysis, Scalability, and Theoretical Insights

Conformal prediction has become increasingly popular for quantifying the uncertainty associated with machine learning models. Recent work in graph uncertainty quantification has built upon this approach for conformal graph prediction. The nascent nature of these explorations has led to conflicting choices for implementations, baselines, and method evaluation. In this work, we analyze the design choices made in the literature and discuss the tradeoffs associated with existing methods. Building on the existing implementations for existing methods, we introduce techniques to scale existing methods to large-scale graph datasets without sacrificing performance. Our theoretical and empirical results justify our recommendations for future scholarship in graph conformal prediction.

LightPure: Realtime Adversarial Image Purification for Mobile Devices Using Diffusion Models

Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where minor input perturbations can significantly impact outcomes. Common countermeasures involve adversarial training and/or data or network transformation. These methods, though effective, require full access to typically proprietary classifiers and are costly for large models. Recent solutions propose purification models, which add a "purification" layer before classification, eliminating the need to modify the classifier directly. Despite their effectiveness, these methods are compute-intensive, making them unsuitable for mobile systems where resources are limited and low latency is essential. This paper introduces LightPure, a new method that enhances adversarial image purification. It improves the accuracy of existing purification methods and provides notable enhancements in speed and computational efficiency, making it suitable for mobile devices with limited resources. Our approach uses a two-step diffusion and one-shot Generative Adversarial Network (GAN) framework, prioritizing latency without compromising robustness. We propose several new techniques to achieve a reasonable balance between classification accuracy and adversarial robustness while maintaining desired latency. We design and implement a proof-of-concept on a Jetson Nano board and evaluate our method using various attack scenarios and datasets. Our results show that LightPure can outperform existing methods by up to 10x in terms of latency while achieving higher accuracy and robustness for various attack scenarios. This method offers a scalable and effective solution for real-world mobile systems.

Enhancing Group Fairness in Federated Learning through Personalization

Personalized Federated Learning (FL) algorithms collaboratively train customized models for each client, enhancing the accuracy of the learned models on the client's local data (e.g., by clustering similar clients, or by fine-tuning models locally). In this paper, we investigate the impact of such personalization techniques on the group fairness of the learned models, and show that personalization can also lead to improved (local) fairness as an unintended benefit. We begin by illustrating these benefits of personalization through numerical experiments comparing two classes of personalized FL algorithms (clustering and fine-tuning) against a baseline FedAvg algorithm, elaborating on the reasons behind improved fairness using personalized FL, and then providing analytical support. Motivated by these, we further propose a new, Fairness-aware Federated Clustering Algorithm, Fair-FCA, in which clients can be clustered to obtain a (tuneable) fairness-accuracy tradeoff. Through numerical experiments, we demonstrate the ability of Fair-FCA to strike a balance between accuracy and fairness at the client level.

Can LLMs Reason in the Wild with Programs?

Large Language Models (LLMs) have shown superior capability to solve reasoning problems with programs. While being a promising direction, most of such frameworks are trained and evaluated in settings with a prior knowledge of task requirements. However, as LLMs become more capable, it is necessary to assess their reasoning abilities in more realistic scenarios where many real-world problems are open-ended with ambiguous scope, and often require multiple formalisms to solve. To investigate this, we introduce the task of reasoning in the wild, where an LLM is tasked to solve a reasoning problem of unknown type by identifying the subproblems and their corresponding formalisms, and writing a program to solve each subproblem, guided by a tactic. We create a large tactic-guided trajectory dataset containing detailed solutions to a diverse set of reasoning problems, ranging from well-defined single-form reasoning (e.g., math, logic), to ambiguous and hybrid ones (e.g., commonsense, combined math and logic). This allows us to test various aspects of LLMs reasoning at the fine-grained level such as the selection and execution of tactics, and the tendency to take undesired shortcuts. In experiments, we highlight that existing LLMs fail significantly on problems with ambiguous and mixed scope, revealing critical limitations and overfitting issues (e.g. accuracy on GSM8K drops by at least 50\%). We further show the potential of finetuning a local LLM on the tactic-guided trajectories in achieving better performance. Project repo is available at github.com/gblackout/Reason-in-the-Wild