Haritz Puerto, Tilek Chubakov, Xiaodan Zhu, Harish Tayyar Madabushi, Iryna Gurevych. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

We study privacy leakage in the reasoning traces of large reasoning models used as personal agents.Unlike final outputs, reasoning traces are often assumed to be internal and safe.We challenge this assumption by showing that reasoning traces frequently contain sensitive user data, which can be extracted via prompt injections or accidentally leak into outputs.Through probing and agentic evaluations, we demonstrate that test-time compute approaches, particularly increased reasoning steps, amplify such leakage.While increasing the budget of those test-time compute approaches makes models more cautious in their final answers, it also leads them to reason more verbosely and leak more in their own thinking.This reveals a core tension: reasoning improves utility but enlarges the privacy attack surface.We argue that safety efforts must extend to the model's internal thinking, not just its outputs. 1 * Work done during an internship at Parameter Lab. 1 Code available at github.com/parameterlab/leaky_thoughts.AirGapAgent-R benchmark available at huggingface.co/datasets/parameterlab/leaky_thoughts. Prior work on contextual privacy

Large Language Models (LLMs) are transforming search engines into Conversational Search Engines (CSE). Consequently, Search Engine Optimization (SEO) is being shifted into Conversational Search Engine Optimization (C-SEO). We are beginning to see dedicated C-SEO methods for modifying web documents to increase their visibility in CSE responses. However, they are often tested only for a limited breadth of application domains; we do not know whether certain C-SEO methods would be effective for a broad range of domains. Moreover, existing evaluations consider only a single-actor scenario where only one web document adopts a C-SEO method; in reality, multiple players are likely to competitively adopt the cutting-edge C-SEO techniques, drawing an analogy from the dynamics we have seen in SEO. We present C-SEO Bench, the first benchmark designed to evaluate C-SEO methods across multiple tasks, domains, and number of actors. We consider two search tasks, question answering and product recommendation, with three domains each. We also formalize a new evaluation protocol with varying adoption rates among involved actors. Our experiments reveal that most current C-SEO methods are not only largely ineffective but also frequently have a negative impact on document ranking, which is opposite to what is expected. Instead, traditional SEO strategies, those aiming to improve the ranking of the source in the LLM context, are significantly more effective. We also observe that as we increase the number of C-SEO adopters, the overall gains decrease, depicting a congested and zero-sum nature of the problem.

Reasoning is a fundamental component of language understanding.Recent prompting techniques, such as chain of thought, have consistently improved LLMs' performance on various reasoning tasks.Nevertheless, there is still little understanding of what triggers reasoning abilities in LLMs in the inference stage.In this paper, we investigate the effect of the input representation on the reasoning abilities of LLMs.We hypothesize that representing natural language tasks as code can enhance specific reasoning abilities such as entity tracking or logical reasoning.To study this, we propose code prompting, a methodology we operationalize as a chain of prompts that transforms a natural language problem into code and directly prompts the LLM using the generated code without resorting to external code execution.We find that code prompting exhibits a high-performance boost for multiple LLMs (up to 22.52 percentage points on GPT 3.5, 7.75 on Mixtral, and 16.78 on Mistral) across multiple conditional reasoning datasets.We then conduct comprehensive experiments to understand how the code representation triggers reasoning abilities and which capabilities are elicited in the underlying models.Our analysis on GPT 3.5 reveals that the code formatting of the input problem is essential for performance improvement.Furthermore, the code representation improves sample efficiency of in-context learning and facilitates state tracking of entities.1

The recent explosion of question-answering (QA) datasets and models has increased the interest in the generalization of models across multiple domains and formats by either training on multiple datasets or combining multiple models.Despite the promising results of multidataset models, some domains or QA formats may require specific architectures, and thus the adaptability of these models might be limited.In addition, current approaches for combining models disregard cues such as questionanswer compatibility.In this work, we propose to combine expert agents with a novel, flexible, and training-efficient architecture that considers questions, answer predictions, and answer-prediction confidence scores to select the best answer among a list of answer predictions.Through quantitative and qualitative experiments, we show that our model i) creates a collaboration between agents that outperforms previous multi-agent and multi-dataset approaches, ii) is highly data-efficient to train, and iii) can be adapted to any QA format.We release our code and a dataset of answer predictions from expert agents for 16 QA datasets to foster future research of multi-agent systems 1 .