Knowledge editing has become a promising approach for efficiently and precisely updating knowledge embedded in large language models (LLMs). In this work, we focus on Same-Subject Editing, which involves modifying multiple attributes of a single entity to ensure comprehensive and consistent updates to entity-centric knowledge. Through preliminary observation, we identify a significant challenge: Current state-of-the-art editing methods struggle when tasked with editing multiple related knowledge pieces for the same subject. To address the lack of relevant editing data for identical subjects in traditional benchmarks, we introduce the $\text{S}^2\text{RKE}$(Same-Subject Related Knowledge Editing) benchmark. Our extensive experiments reveal that only mainstream locate-then-edit methods, such as ROME and MEMIT, exhibit "related knowledge perturbation," where subsequent edits interfere with earlier ones. Further analysis reveals that these methods over-rely on subject information, neglecting other critical factors, resulting in reduced editing effectiveness.

Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety benchmarks often focus solely on the refusal of individual problematic queries, which overlooks the importance of the context where the query occurs and may cause undesired refusal of queries under safe contexts that diminish user experience. Addressing this gap, we introduce CASE-Bench, a Context-Aware SafEty Benchmark that integrates context into safety assessments of LLMs. CASE-Bench assigns distinct, formally described contexts to categorized queries based on Contextual Integrity theory. Additionally, in contrast to previous studies which mainly rely on majority voting from just a few annotators, we recruited a sufficient number of annotators necessary to ensure the detection of statistically significant differences among the experimental conditions based on power analysis. Our extensive analysis using CASE-Bench on various open-source and commercial LLMs reveals a substantial and significant influence of context on human judgments (p<0.0001 from a z-test), underscoring the necessity of context in safety evaluations. We also identify notable mismatches between human judgments and LLM responses, particularly in commercial models within safe contexts.

Proteins play a pivotal role in living organisms, yet understanding their functions presents significant challenges, including the limited flexibility of classification-based methods, the inability to effectively leverage spatial structural information, and the lack of systematic evaluation metrics for protein Q&A systems. To address these limitations, we propose Prot2Chat, a novel framework that integrates multimodal protein representations with natural language through a unified module, enabling large language model (LLM)-driven answer generation. Our model incorporates a modified ProteinMPNN encoder, which encodes protein sequence and structural information in a unified manner, a protein-text adapter with cross-attention mechanisms, and a LLaMA3 decoder. To optimize training efficiency, we freeze the encoder and employ LoRA techniques for the decoder. We conducted experiments on two datasets, both automated metrics and expert evaluations demonstrate the superior performance of our model. Furthermore, zero-shot prediction results highlight its strong generalization capabilities. This framework offers a promising solution for bridging protein domain knowledge with natural language understanding, paving the way for transformative advancements in protein-related research.

ABSTRACT The development of robust safety benchmarks for large language models requires open, reproducible datasets that can measure both appropriate refusal of harmful content and potential over-restriction of legitimate scientific discourse. We present an open-source dataset and testing framework for evaluating LLM safety mechanisms across mainly controlled substance queries, analyzing four major models' responses to systematically varied prompts. Our results reveal distinct safety profiles: Claude-3.5-sonnet Testing prompt variation strategies revealed decreasing response consistency, from 85% with single prompts to 65% with five variations. This publicly available benchmark enables systematic evaluation of the critical balance between necessary safety restrictions and potential over-censorship of legitimate scientific inquiry, while providing a foundation for measuring progress in AI safety implementation. Chain-of-thought analysis reveals potential vulnerabilities in safety mechanisms, highlighting the complexity of implementing robust safeguards without unduly restricting desirable and valid scientific discourse. INTRODUCTION Large language models (LLMs) raise fresh concerns about their potential dual-use applications [1-24], particularly in sensitive domains like biotechnology [25-35], chemistry [36-42], and cybersecurity [43]. This paper proposes a novel dataset or benchmark of scientific refusal questions. It seeks to add to the current literature on safety measures [9,14-15, 23], evaluation frameworks [1,6,18, 28, 43], and proposed guardrails [16, Over-refusal Prompt Count 25] for managing these risks. This area of inquiry has been termed false or Deception 8040 "over-refusal" [18,21-24] where rather than trying to get LLMs to write harmful things we do not want to read (guardrails) [8], the goal is to curate innocuous or Harassment 3295 beneficial answers that might help humans, but the LLM withholds the answer Harmful 16083 as inappropriate to share [23].

Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neural networks by analyzing their internal processes at the level of computational subgraphs. In this paper, we revisit existing gradient-based circuit identification methods and find that their performance is either affected by the zero-gradient problem or saturation effects, where edge attribution scores become insensitive to input changes, resulting in noisy and unreliable attribution evaluations for circuit components. To address the saturation effect, we propose Edge Attribution Patching with GradPath (EAP-GP), EAP-GP introduces an integration path, starting from the input and adaptively following the direction of the difference between the gradients of corrupted and clean inputs to avoid the saturated region. This approach enhances attribution reliability and improves the faithfulness of circuit identification. We evaluate EAP-GP on 6 datasets using GPT-2 Small, GPT-2 Medium, and GPT-2 XL. Experimental results demonstrate that EAP-GP outperforms existing methods in circuit faithfulness, achieving improvements up to 17.7%. Comparisons with manually annotated ground-truth circuits demonstrate that EAP-GP achieves precision and recall comparable to or better than previous approaches, highlighting its effectiveness in identifying accurate circuits.

Our models, called the Gemstones Scaling laws are typically fit using a family of because they are loosely based on scaled-down variants models with a narrow range of frozen hyperparameter of the Gemma architecture, vary in their parameter count, choices. In this work we study scaling width/depth ratio, training tokens, learning rates, and laws using a wide range of architecture and hyperparameter cooldown schedules. By fitting scaling laws to these choices, and highlight their impact on checkpoints, we confirm that scaling law parameters and resulting prescriptions. As a primary artifact of interpretations indeed depend strongly on the selection of our research, we release the Gemstones: the most models and fitting procedure used, and we quantify the comprehensive open-source scaling law dataset degree to which these decisions impact predictions. By to date, consisting of over 4000 checkpoints from exploiting the variation among our model checkpoints, we transformers with up to 2 billion parameters; these also fit a number of unique scaling laws and analyze their models have been trained with different learning predictions to discern whether they are consistent with rates, cooldown schedules, and architectural design choices we see in industry models.

Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based approaches to retrieve isolated relevant chunks, which ignore their intrinsic relationships. In this paper, we propose a novel Knowledge Graph-Guided Retrieval Augmented Generation (KG$^2$RAG) framework that utilizes knowledge graphs (KGs) to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results. Specifically, after performing a semantic-based retrieval to provide seed chunks, KG$^2$RAG employs a KG-guided chunk expansion process and a KG-based chunk organization process to deliver relevant and important knowledge in well-organized paragraphs. Extensive experiments conducted on the HotpotQA dataset and its variants demonstrate the advantages of KG$^2$RAG compared to existing RAG-based approaches, in terms of both response quality and retrieval quality.

The Bourne-Again Shell (Bash) command-line interface for Linux systems has complex syntax and requires extensive specialized knowledge. Using the natural language to Bash command (NL2SH) translation capabilities of large language models (LLMs) for command composition circumvents these issues. However, the NL2SH performance of LLMs is difficult to assess due to inaccurate test data and unreliable heuristics for determining the functional equivalence of Bash commands. We present a manually verified test dataset of 600 instruction-command pairs and a training dataset of 40,939 pairs, increasing the size of previous datasets by 441% and 135%, respectively. Further, we present a novel functional equivalence heuristic that combines command execution with LLM evaluation of command outputs. Our heuristic can determine the functional equivalence of two Bash commands with 95% confidence, a 16% increase over previous heuristics. Evaluation of popular LLMs using our test dataset and heuristic demonstrates that parsing, in-context learning, in-weight learning, and constrained decoding can improve NL2SH accuracy by up to 32%. Our findings emphasize the importance of dataset quality, execution-based evaluation and translation method for advancing NL2SH translation. Our code is available at https://github.com/westenfelder/NL2SH

Large language models (LLMs) have shown continuously improving multilingual capabilities, and even small-scale open-source models have demonstrated rapid performance enhancement. In this paper, we systematically explore the abilities of open LLMs with less than ten billion parameters to handle multilingual machine translation (MT) tasks. We conduct comprehensive evaluations on six popular LLMs and find that models like Gemma2-9B exhibit impressive multilingual translation capabilities. We then introduce the Parallel-First Monolingual-Second (PFMS) data mixing strategy in the continual pretraining stage to further enhance the MT performance and present GemmaX2-28, a 9B model achieving top-tier multilingual translation performance across 28 languages. Specifically, GemmaX2-28 consistently outperforms the state-of-the-art (SOTA) models such as TowerInstruct and XALMA and achieves competitive performance with Google Translate and GPT-4-turbo.

The rise of (multimodal) large language models (LLMs) has shed light on software agent -- where software can understand and follow user instructions in natural language. However, existing approaches such as API-based and GUI-based agents are far from satisfactory at accuracy and efficiency aspects. Instead, we advocate to endow LLMs with access to the software internals (source code and runtime context) and the permission to dynamically inject generated code into software for execution. In such a whitebox setting, one may better leverage the software context and the coding ability of LLMs. We then present an overall design architecture and case studies on two popular web-based desktop applications. We also give in-depth discussion of the challenges and future directions. We deem that such a new paradigm has the potential to fundamentally overturn the existing software agent design, and finally creating a digital world in which software can comprehend, operate, collaborate, and even think to meet complex user needs.