Longer contexts present a new attack surface for adversarial attacks. In search of a "fruit-fly" of long-context vulnerabilities, we study Many-shot Jailbreaking (MSJ; Figure 1), a simple yet effective and scalable jailbreak.

Recent work has shown that language models' (LMs) prompt-based learning capabilities make them well suited for automating data labeling in domains where manual annotation is expensive.

In-context learning (ICL) for text classification, which uses a few input-label demonstrations to describe a task, has demonstrated impressive performance on large language models (LLMs). However, the selection of in-context demonstrations plays a crucial role and can significantly affect LLMs' performance. Most existing demonstration selection methods primarily focus on semantic similarity between test inputs and demonstrations, often overlooking the importance of label distribution alignment. To address this limitation, we propose a two-stage demonstration selection method, TopK + Label Distribution Divergence (L2D), which leverages a fine-tuned BERT-like small language model (SLM) to generate label distributions and calculate their divergence for both test inputs and candidate demonstrations. This enables the selection of demonstrations that are not only semantically similar but also aligned in label distribution with the test input. Extensive experiments across seven text classification benchmarks show that our method consistently outperforms previous demonstration selection strategies. Further analysis reveals a positive correlation between the performance of LLMs and the accuracy of the underlying SLMs used for label distribution estimation.

Digital tool-based agents, powered by Large Language Models (LLMs), that invoke external Application Programming Interfaces (APIs) often rely on documentation to understand API functionality. However, such documentation is frequently missing, outdated, privatized, or inconsistent-hindering the development of reliable, general-purpose agents. In this work, we propose a new research direction: learning of API functionality directly from in-context demonstrations. This task is a new paradigm applicable in scenarios without documentation. Using API benchmarks, we collect demonstrations from both expert agents and from self-exploration. To understand what information demonstrations must convey for successful task completion, we extensively study how the number of demonstrations and the use of LLM-generated summaries and evaluations affect the task success rate of the API-based agent. Our experiments across 3 datasets and 6 models show that learning functionality from in-context demonstrations remains a non-trivial challenge, even for state-of-the-art LLMs. We find that providing explicit function calls and natural language critiques significantly improves the agent's task success rate due to more accurate parameter filling. We analyze failure modes, identify sources of error, and highlight key open challenges for future work in documentation-free, self-improving, API-based agents.

On-the-fly reasoning often requires adaptation to novel problems under limited data and distribution shift. This work introduces CausalARC: an experimental testbed for AI reasoning in low-data and out-of-distribution regimes, modeled after the Abstraction and Reasoning Corpus (ARC). Each CausalARC reasoning task is sampled from a fully specified causal world model, formally expressed as a structural causal model. Principled data augmentations provide observational, interventional, and counterfactual feedback about the world model in the form of few-shot, in-context learning demonstrations. As a proof-of-concept, we illustrate the use of CausalARC for four language model evaluation settings: (1) abstract reasoning with test-time training, (2) counterfactual reasoning with in-context learning, (3) program synthesis, and (4) causal discovery with logical reasoning. Within- and between-model performance varied heavily across tasks, indicating room for significant improvement in language model reasoning.

Sequence labeling (SL) tasks, where labels are assigned to tokens, are abundant in NLP (e.g., named entity recognition and aspect-based sentiment analysis). Owing to the intuition that they require bidirectional context, SL tasks are commonly tackled with encoder-only models. Recent work also shows that removing the causal mask in fine-tuning enables decoder-based LLMs to become effective token classifiers. Less work, however, focused on (supervised) generative SL, a more natural setting for causal LLMs. Due to their rapid scaling, causal LLMs applied to SL are expected to outperform encoders, whose own development has stagnated. In this work, we propose supervised in-context fine-tuning (SIFT) for generative SL. SIFT casts SL tasks as constrained response generation, natural to LLMs, combining in-context learning (ICL) from demonstrations with supervised fine-tuning. SIFT considerably outperforms both ICL and decoder-as-encoder fine-tuning baselines on a range of standard SL tasks. We further find that although long context hinders the performance of generative SL in both ICL and SIFT, this deficiency can be mitigated by removing the instruction, as instructions are shown to be largely unnecessary for achieving strong SL performance with SIFT. Our findings highlight strengths and limitations of SL with LLMs, underscoring the importance of a response-based generative task formulation for effective SL performance.

Large Language Models (LLMs) are widely used for downstream tasks such as tabular classification, where ensuring fairness in their outputs is critical for inclusivity, equal representation, and responsible AI deployment. This study introduces a novel approach to enhancing LLM performance and fairness through the concept of a dynamic validation set, which evolves alongside the test set, replacing the traditional static validation approach. We also propose an iterative algorithm, SMITE, to select optimal in-context examples, with each example set validated against its corresponding dynamic validation set. The in-context set with the lowest total error is used as the final demonstration set. Our experiments across four different LLMs show that our proposed techniques significantly improve both predictive accuracy and fairness compared to baseline methods. To our knowledge, this is the first study to apply dynamic validation in the context of in-context learning for LLMs.

Large Language Models (LLMs) show impressive inductive reasoning capabilities, enabling them to generate hypotheses that could generalize effectively to new instances when guided by in-context demonstrations. However, in real-world applications, LLMs' hypothesis generation is not solely determined by these demonstrations but is significantly shaped by task-specific model priors. Despite their critical influence, the distinct contributions of model priors versus demonstrations to hypothesis generation have been underexplored. This study bridges this gap by systematically evaluating three inductive reasoning strategies across five real-world tasks with three LLMs. Our empirical findings reveal that, hypothesis generation is primarily driven by the model's inherent priors; removing demonstrations results in minimal loss of hypothesis quality and downstream usage. Further analysis shows the result is consistent across various label formats with different label configurations, and prior is hard to override, even under flipped labeling. These insights advance our understanding of the dynamics of hypothesis generation in LLMs and highlight the potential for better utilizing model priors in real-world inductive reasoning tasks.