LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on a website. To evaluate these risks, we propose SafeArena, a benchmark focused on the deliberate misuse of web agents. SafeArena comprises 250 safe and 250 harmful tasks across four websites. We classify the harmful tasks into five harm categories—misinformation, illegal activity, harassment, cybercrime, and social bias, designed to assess realistic misuses of web agents. We evaluate leading LLM-based web agents, including GPT-4o, Claude-3.5 Sonnet, Qwen-2-VL 72B, and Llama-3.2 90B, on our benchmark. To systematically assess their susceptibility to harmful tasks, we introduce the Agent Risk Assessment framework that categorizes agent behavior across four risk levels. We find agents are surprisingly compliant with malicious requests, with GPT-4o and Qwen-2 completing 34.7% and 27.3% of harmful requests, respectively. Our findings highlight the urgent need for safety alignment procedures for web agents.

In order to understand the in-context learning phenomenon, recent works have adopted a stylized experimental framework and demonstrated that Transformers can match the performance of gradient-based learning algorithms for various classes of real-valued functions. However, the limitations of Transformers in implementing learning algorithms, and their ability to learn other forms of algorithms are not well understood. Additionally, the degree to which these capabilities are confined to attention-based models is unclear. Furthermore, it remains to be seen whether the insights derived from these stylized settings can be extrapolated to pretrained Large Language Models (LLMs). In this work, we take a step towards answering these questions by demonstrating the following: (a) On a test-bed with a variety of Boolean function classes, we find that Transformers can nearly match the optimal learning algorithm for 'simpler' tasks, while their performance deteriorates on more 'complex' tasks. Additionally, we find that certain attention-free models perform (almost) identically to Transformers on a range of tasks. (b) When provided a *teaching sequence*, i.e. a set of examples that uniquely identifies a function in a class, we show that Transformers learn more sample-efficiently. Interestingly, our results show that Transformers can learn to implement *two distinct* algorithms to solve a *single* task, and can adaptively select the more sample-efficient algorithm depending on the sequence of in-context examples. (c) Lastly, we show that extant LLMs, e.g. LLaMA-2, GPT-4, can compete with nearest-neighbor baselines on prediction tasks that are guaranteed to not be in their training set.

Arkil Patel, Siva Reddy, Dzmitry Bahdanau, Pradeep Dasigi. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Despite the widespread success of Transformers on NLP tasks, recent works have found that they struggle to model several formal languages when compared to recurrent models.This raises the question of why Transformers perform well in practice and whether they have any properties that enable them to generalize better than recurrent models.In this work, we conduct an extensive empirical study on Boolean functions to demonstrate the following: (i) Random Transformers are relatively more biased towards functions of low sensitivity.(ii) When trained on Boolean functions, both Transformers and LSTMs prioritize learning functions of low sensitivity, with Transformers ultimately converging to functions of lower sensitivity.(iii) On sparse Boolean functions which have low sensitivity, we find that Transformers generalize near perfectly even in the presence of noisy labels whereas LSTMs overfit and achieve poor generalization accuracy.Overall, our results provide strong quantifiable evidence that suggests differences in the inductive biases of Transformers and recurrent models which may help explain Transformer's effective generalization performance despite relatively limited expressiveness.

Humans possess a remarkable ability to assign novel interpretations to linguistic expressions, enabling them to learn new words and understand community-specific connotations.However, Large Language Models (LLMs) have a knowledge cutoff and are costly to finetune repeatedly.Therefore, it is crucial for LLMs to learn novel interpretations in-context.In this paper, we systematically analyse the ability of LLMs to acquire novel interpretations using incontext learning.To facilitate our study, we introduce MAGNIFICO, an evaluation suite implemented within a text-to-SQL semantic parsing framework that incorporates diverse tokens and prompt settings to simulate real-world complexity.Experimental results on MAGNIFICO demonstrate that LLMs exhibit a surprisingly robust capacity for comprehending novel interpretations from natural language descriptions as well as from discussions within long conversations.Nevertheless, our findings also highlight the need for further improvements, particularly when interpreting unfamiliar words or when composing multiple novel interpretations simultaneously in the same example.Additionally, our analysis uncovers the semantic predispositions in LLMs and reveals the impact of recency bias for information presented in long contexts.

Humans can reason compositionally whilst grounding language utterances to the real world.Recent benchmarks like ReaSCAN (Wu et al., 2021) use navigation tasks grounded in a grid world to assess whether neural models exhibit similar capabilities.In this work, we present a simple transformer-based model that outperforms specialized architectures on ReaSCAN and a modified version (Qiu et al., 2021) of gSCAN (Ruis et al., 2020).On analyzing the task, we find that identifying the target location in the grid world is the main challenge for the models.Furthermore, we show that a particular split in ReaSCAN, which tests depth generalization, is unfair.On an amended version of this split, we show that transformers can generalize to deeper input structures.Finally, we design a simpler grounded compositional generalization task, RefEx, to investigate how transformers reason compositionally.We show that a single self-attention layer with a single head generalizes to novel combinations of object attributes.Moreover, we derive a precise mathematical construction of the transformer's computations from the learned network.Overall, we provide valuable insights about the grounded compositional generalization task and the behaviour of transformers on it, which would be useful for researchers working in this area.

The problem of designing NLP solvers for math word problems (MWP) has seen sustained research activity and steady gains in the test accuracy.Since existing solvers achieve high performance on the benchmark datasets for elementary level MWPs containing one-unknown arithmetic word problems, such problems are often considered "solved" with the bulk of research attention moving to more complex MWPs.In this paper, we restrict our attention to English MWPs taught in grades four and lower.We provide strong evidence that the existing MWP solvers rely on shallow heuristics to achieve high performance on the benchmark datasets.To this end, we show that MWP solvers that do not have access to the question asked in the MWP can still solve a large fraction of MWPs.Similarly, models that treat MWPs as bag-ofwords can also achieve surprisingly high accuracy.Further, we introduce a challenge dataset, SVAMP, created by applying carefully chosen variations over examples sampled from existing datasets.The best accuracy achieved by state-of-the-art models is substantially lower on SVAMP, thus showing that much remains to be done even for the simplest of the MWPs.PROBLEM: Text: Jack had 8 pens and Mary had 5 pens.Jack gave 3 pens to Mary.How many pens does Jack have now?Equation: 8 -3 = 5 QUESTION SENSITIVITY VARIATION: Text: Jack had 8 pens and Mary had 5 pens.Jack gave 3 pens to Mary.How many pens does Mary have now?Equation: 5 + 3 = 8 REASONING ABILITY VARIATION: Text: Jack had 8 pens and Mary had 5 pens.Mary gave 3 pens to Jack.How many pens

Transformers are being used extensively across several sequence modeling tasks.Significant research effort has been devoted to experimentally probe the inner workings of Transformers.However, our conceptual and theoretical understanding of their power and inherent limitations is still nascent.In particular, the roles of various components in Transformers such as positional encodings, attention heads, residual connections, and feedforward networks, are not clear.In this paper, we take a step towards answering these questions.We analyze the computational power as captured by Turing-completeness.We first provide an alternate and simpler proof to show that vanilla Transformers are Turing-complete and then we prove that Transformers with only positional masking and without any positional encoding are also Turing-complete.We further analyze the necessity of each component for the Turing-completeness of the network; interestingly, we find that a particular type of residual connection is necessary.We demonstrate the practical implications of our results via experiments on machine translation and synthetic tasks.

In the fast-growing world, a significant increase in the number of vehicles has opened an opportunity to transform vehicles from a mechanical device to an intelligent system. The vehicular ad-hoc network (VANET) is designed to exchange messages with nearby devices. However, it is tough to transmit information from a sender to a receiver in a public environment due to malicious activities (by an adversary), wireless connection, mobility, and high-cost requirement. In this paper, we propose a state-of-the-art protocol, names as “VehicleChain” for smart transportation to ensure secure and cost-effective vehicle-to-vehicle and vehicle-to-infrastructure communications. The VehicleChain combines the robustness of a blockchain with elliptic-curve cryptography (ECC) to improve the system security level without increasing the computational cost. The VehicleChain is protected against different attacks, i.e., insider, server spoofing, modification, man-in-the-middle, plaintext, replay, and impersonation. Further, the proposed scheme comparatively achieves better results for different performance measures.