We present Code Comparison Tuning (CCT), a simple and effective tuning method for code large language models (Code LLMs) to better handle subtle code errors. Specifically, we integrate the concept of comparison into instruction tuning, both at the token and sequence levels, enabling the model to discern even the slightest deviations in code. To compare the original code with an erroneous version containing manually added code errors, we use token-level preference loss for detailed token-level comparisons. Additionally, we combine code segments to create a new instruction tuning sample for sequence-level comparisons, enhancing the model's bug-fixing capability. Experimental results on the HumanEvalFix benchmark show that CCT surpasses instruction tuning in pass@1 scores by up to 4 points across diverse code LLMs, and extensive analysis demonstrates the effectiveness of our method.

Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. Although GCG is a significant milestone, its attacking efficiency remains unsatisfactory. In this paper, we present several improved (empirical) techniques for optimization-based jailbreaks like GCG. We first observe that the single target template of "Sure" largely limits the attacking performance of GCG; given this, we propose to apply diverse target templates containing harmful self-suggestion and/or guidance to mislead LLMs. Besides, from the optimization aspects, we propose an automatic multi-coordinate updating strategy in GCG (i.e., adaptively deciding how many tokens to replace in each step) to accelerate convergence, as well as tricks like easy-to-hard initialisation. Then, we combine these improved technologies to develop an efficient jailbreak method, dubbed I-GCG. In our experiments, we evaluate on a series of benchmarks (such as NeurIPS 2023 Red Teaming Track). The results demonstrate that our improved techniques can help GCG outperform state-of-the-art jailbreaking attacks and achieve nearly 100% attack success rate. The code is released at https://github.com/jiaxiaojunQAQ/I-GCG.

Vision-Language Navigation (VLN) requires the agent to follow language instructions to reach a target position. A key factor for successful navigation is to align the landmarks implied in the instruction with diverse visual observations. However, previous VLN agents fail to perform accurate modality alignment especially in unexplored scenes, since they learn from limited navigation data and lack sufficient open-world alignment knowledge. In this work, we propose a new VLN paradigm, called COrrectable LaNdmark DiScOvery via Large ModEls (CONSOLE). In CONSOLE, we cast VLN as an open-world sequential landmark discovery problem, by introducing a novel correctable landmark discovery scheme based on two large models ChatGPT and CLIP. Specifically, we use ChatGPT to provide rich open-world landmark cooccurrence commonsense, and conduct CLIP-driven landmark discovery based on these commonsense priors. To mitigate the noise in the priors due to the lack of visual constraints, we introduce a learnable cooccurrence scoring module, which corrects the importance of each cooccurrence according to actual observations for accurate landmark discovery. We further design an observation enhancement strategy for an elegant combination of our framework with different VLN agents, where we utilize the corrected landmark features to obtain enhanced observation features for action decision. Extensive experimental results on multiple popular VLN benchmarks (R2R, REVERIE, R4R, RxR) show the significant superiority of CONSOLE over strong baselines. Especially, our CONSOLE establishes the new state-of-the-art results on R2R and R4R in unseen scenarios. Code is available at https://github.com/expectorlin/CONSOLE.

The integration of generative Large Language Models (LLMs) into various applications, including the legal domain, has been accelerated by their expansive and versatile nature. However, when facing a legal case, users without a legal background often struggle to formulate professional queries and may inadvertently overlook critical legal factors when presenting their case narrative to LLMs. To address this issue, we propose the Diagnostic Legal Large Language Model (D3LM), which utilizes adaptive lawyer-like diagnostic questions to collect additional case information and then provides high-quality feedback. D3LM incorporates an innovative graph-based Positive-Unlabeled Reinforcement Learning (PURL) algorithm, enabling the generation of critical questions and enhancing user-LLM interactions. Moreover, an integrated LLM-based stopping criterion facilitates precise Court Views Generation (CVG). Our research also introduces a new English-language CVG dataset based on the US case law database, enriching the realm of LLM research and deployment with a vital dimension. D3LM surpasses classical LLMs by delivering outstanding performance and a remarkable user experience in the legal domain.

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. [38] as a method to improve inference speed of language models by simultaneously predicting multiple future tokens, termed block drafts, which are subsequently verified and conditionally accepted by the autoregressive model. This paper contributes to the understanding and improvement of block drafts in two ways. First, we analyze the token distributions produced by multiple prediction heads. Secondly, we leverage this analysis to develop algorithms to improve BPD inference speed by refining the block drafts using n-gram and neural language models. Experiments demonstrate that refined block drafts yield a +5-21% increase in block efficiency (i.e., the number of accepted tokens from the block draft) across diverse datasets.

Knowledge editing aims to rectify inaccuracies in large language models (LLMs) without costly retraining for outdated or erroneous knowledge. However, current knowledge editing methods primarily focus on single editing, failing to meet the requirements for lifelong editing. This study reveals a performance degradation encountered by knowledge editing in lifelong editing, characterized by toxicity buildup and toxicity flash, with the primary cause identified as pattern unmatch. We introduce a knowledge editing approach named Wise-Layer Knowledge Editor (WilKE), which selects editing layer based on the pattern matching degree of editing knowledge across different layers in language models. Experimental results demonstrate that, in lifelong editing, WilKE exhibits an average improvement of 46.2% and 67.8% on editing GPT2-XL and GPT-J relative to state-of-the-art knowledge editing methods.

Open model developers have emerged as key actors in the political economy of artificial intelligence (AI), but we still have a limited understanding of collaborative practices in the open AI ecosystem. This paper responds to this gap with a three-part quantitative analysis of development activity on the Hugging Face (HF) Hub, a popular platform for building, sharing, and demonstrating models. First, various types of activity across 348,181 model, 65,761 dataset, and 156,642 space repositories exhibit right-skewed distributions. Activity is extremely imbalanced between repositories; for example, over 70% of models have 0 downloads, while 1% account for 99% of downloads. Furthermore, licenses matter: there are statistically significant differences in collaboration patterns in model repositories with permissive, restrictive, and no licenses. Second, we analyse a snapshot of the social network structure of collaboration in model repositories, finding that the community has a core-periphery structure, with a core of prolific developers and a majority of isolate developers (89%). Upon removing the isolate developers from the network, collaboration is characterised by high reciprocity regardless of developers' network positions. Third, we examine model adoption through the lens of model usage in spaces, finding that a minority of models, developed by a handful of companies, are widely used on the HF Hub. Overall, activity on the HF Hub is characterised by Pareto distributions, congruent with OSS development patterns on platforms like GitHub. We conclude with recommendations for researchers, companies, and policymakers to advance our understanding of open AI development.

Large language models (LLMs) have transformed AI and achieved breakthrough performance on a wide range of tasks that require human intelligence. In science, perhaps the most interesting application of LLMs is for hypothesis formation. A feature of LLMs, which results from their probabilistic structure, is that the output text is not necessarily a valid inference from the training text. These are 'hallucinations', and are a serious problem in many applications. However, in science, hallucinations may be useful: they are novel hypotheses whose validity may be tested by laboratory experiments. Here we experimentally test the use of LLMs as a source of scientific hypotheses using the domain of breast cancer treatment. We applied the LLM GPT4 to hypothesize novel pairs of FDA-approved non-cancer drugs that target the MCF7 breast cancer cell line relative to the non-tumorigenic breast cell line MCF10A. In the first round of laboratory experiments GPT4 succeeded in discovering three drug combinations (out of 12 tested) with synergy scores above the positive controls. These combinations were itraconazole + atenolol, disulfiram + simvastatin and dipyridamole + mebendazole. GPT4 was then asked to generate new combinations after considering its initial results. It then discovered three more combinations with positive synergy scores (out of four tested), these were disulfiram + fulvestrant, mebendazole + quinacrine and disulfiram + quinacrine. A limitation of GPT4 as a generator of hypotheses was that its explanations for them were formulaic and unconvincing. We conclude that LLMs are an exciting novel source of scientific hypotheses.

Benchmarks have been essential for driving progress in machine learning. A better understanding of LLM capabilities on real world tasks is vital for safe development. Designing adequate LLM benchmarks is challenging: Data from real-world tasks is hard to collect, public availability of static evaluation data results in test data contamination and benchmark overfitting, and periodically generating new evaluation data is tedious and may result in temporally inconsistent results. We introduce HelloFresh, based on continuous streams of real-world data generated by intrinsically motivated human labelers. It covers recent events from X (formerly Twitter) community notes and edits of Wikipedia pages, mitigating the risk of test data contamination and benchmark overfitting. Any X user can propose an X note to add additional context to a misleading post (formerly tweet); if the community classifies it as helpful, it is shown with the post. Similarly, Wikipedia relies on community-based consensus, allowing users to edit articles or revert edits made by other users. Verifying whether an X note is helpful or whether a Wikipedia edit should be accepted are hard tasks that require grounding by querying the web. We backtest state-of-the-art LLMs supplemented with simple web search access and find that HelloFresh yields a temporally consistent ranking. To enable continuous evaluation on HelloFresh, we host a public leaderboard and periodically updated evaluation data at https://tinyurl.com/hello-fresh-LLM.

Aligning pretrained language models (LMs) is a complex and resource-intensive process, often requiring access to large amounts of ground-truth preference data and substantial compute. Are these costs necessary? That is, it is possible to align using only inherent model knowledge and without additional training? We tackle this challenge with AlignEZ, a novel approach that uses (1) self-generated preference data and (2) representation editing to provide nearly cost-free alignment. During inference, AlignEZ modifies LM representations to reduce undesirable and boost desirable components using subspaces identified via self-generated preference pairs. Our experiments reveal that this nearly cost-free procedure significantly narrows the gap between base pretrained and tuned models by an average of 31.6%, observed across six datasets and three model architectures. Additionally, we explore the potential of using AlignEZ as a means of expediting more expensive alignment procedures. Our experiments show that AlignEZ improves DPO models tuned only using a small subset of ground-truth preference data. Lastly, we study the conditions under which improvement using AlignEZ is feasible, providing valuable insights into its effectiveness.