Related papers: Algorithmic Collusion by Large Language Models

Related papers

ARIES: Autonomous Reasoning with LLMs on Interactive Thought Graph Environments [7.508204100423766]
We introduce ARIES, a multi-agent architecture for reasoning with LLMs. We observe that using off-the-shelf LLMs as policy agents with no supervised fine-tuning (SFT) can yield up to $29%$ higher accuracy on HumanEval. We also conduct a thorough analysis of observed failure modes, highlighting that limitations on LLM sizes and the depth of problem decomposition can be seen as challenges to scaling LLM-guided reasoning.
arXiv Detail & Related papers (2025-02-28T16:28:13Z)
Universal Model Routing for Efficient LLM Inference [72.65083061619752]
We consider the problem of dynamic routing, where new, previously unobserved LLMs are available at test time. We propose a new approach to this problem that relies on representing each LLM as a feature vector, derived based on predictions on a set of representative prompts. We prove that these strategies are estimates of a theoretically optimal routing rule, and provide an excess risk bound to quantify their errors.
arXiv Detail & Related papers (2025-02-12T20:30:28Z)
Differentially Private Steering for Large Language Model Alignment [55.30573701583768]
We present the first study of aligning Large Language Models with private datasets. Our work proposes the Private Steering for LLM Alignment (PSA) algorithm to edit activations with differential privacy guarantees. Our results show that PSA achieves DP guarantees for LLM alignment with minimal loss in performance.
arXiv Detail & Related papers (2025-01-30T17:58:36Z)
Prompting Strategies for Enabling Large Language Models to Infer Causation from Correlation [68.58373854950294]
We focus on causal reasoning and address the task of establishing causal relationships based on correlation information. We introduce a prompting strategy for this problem that breaks the original task into fixed subquestions. We evaluate our approach on an existing causal benchmark, Corr2Cause.
arXiv Detail & Related papers (2024-12-18T15:32:27Z)
Control Large Language Models via Divide and Conquer [94.48784966256463]
This paper investigates controllable generation for large language models (LLMs) with prompt-based control, focusing on Lexically Constrained Generation (LCG) We evaluate the performance of LLMs on satisfying lexical constraints with prompt-based control, as well as their efficacy in downstream applications.
arXiv Detail & Related papers (2024-10-06T21:20:06Z)
Artificial Intelligence and Algorithmic Price Collusion in Two-sided Markets [9.053163124987535]
We examine how AI agents using Q-learning engage in tacit collusion in two-sided markets. Our experiments reveal that AI-driven platforms achieve higher collusion levels compared to Bertrand competition. Increased network externalities significantly enhance collusion, suggesting AI algorithms exploit them to maximize profits.
arXiv Detail & Related papers (2024-07-04T17:57:56Z)
Contextual Dynamic Pricing: Algorithms, Optimality, and Local Differential Privacy Constraints [10.057344315478709]
We study contextual dynamic pricing problems where a firm sells products to $T$ sequentially-arriving consumers. We first show the optimal regret is of order $sqrtdT$, up to logarithmic factors. We extend our study to dynamic pricing under mixed privacy constraints, improving the privacy-utility tradeoff by leveraging public data.
arXiv Detail & Related papers (2024-06-04T15:44:10Z)
By Fair Means or Foul: Quantifying Collusion in a Market Simulation with Deep Reinforcement Learning [1.5249435285717095]
This research employs an experimental oligopoly model of repeated price competition. We investigate the strategies and emerging pricing patterns developed by the agents, which may lead to a collusive outcome. Our findings indicate that RL-based AI agents converge to a collusive state characterized by the charging of supracompetitive prices.
arXiv Detail & Related papers (2024-06-04T15:35:08Z)
Building Accurate Translation-Tailored LLMs with Language Aware Instruction Tuning [57.323716555996114]
Off-target translation remains an unsolved problem, especially for low-resource languages. Recent works have either designed advanced prompting strategies to highlight the functionality of translation instructions or exploited the in-context learning ability of LLMs. In this work, we design a two-stage fine-tuning algorithm to improve the instruction-following ability (especially the translation direction) of LLMs.
arXiv Detail & Related papers (2024-03-21T13:47:40Z)
How Can LLM Guide RL? A Value-Based Approach [68.55316627400683]
Reinforcement learning (RL) has become the de facto standard practice for sequential decision-making problems by improving future acting policies with feedback. Recent developments in large language models (LLMs) have showcased impressive capabilities in language understanding and generation, yet they fall short in exploration and self-improvement capabilities. We develop an algorithm named LINVIT that incorporates LLM guidance as a regularization factor in value-based RL, leading to significant reductions in the amount of data needed for learning.
arXiv Detail & Related papers (2024-02-25T20:07:13Z)
Measuring Bargaining Abilities of LLMs: A Benchmark and A Buyer-Enhancement Method [17.388837360641276]
This paper describes the Bargaining task as an asymmetric incomplete information game. It allows us to quantitatively assess an agent's performance in the Bargain task. We propose a novel approach called OG-Narrator that integrates a deterministic Offer Generator to control the price range of Buyer's offers.
arXiv Detail & Related papers (2024-02-24T13:36:58Z)
Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMs [60.40396361115776]
This paper introduces a novel collaborative approach, namely SlimPLM, that detects missing knowledge in large language models (LLMs) with a slim proxy model. We employ a proxy model which has far fewer parameters, and take its answers as answers. Heuristic answers are then utilized to predict the knowledge required to answer the user question, as well as the known and unknown knowledge within the LLM.
arXiv Detail & Related papers (2024-02-19T11:11:08Z)
Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues [47.977032883078664]
We develop assistive agents based on Large Language Models (LLMs) We simulate business negotiations by letting two LLM-based agents engage in role play. A third LLM acts as a remediator agent to rewrite utterances violating norms for improving negotiation outcomes.
arXiv Detail & Related papers (2024-01-29T09:07:40Z)
On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach [7.996010840316654]
We propose an uncertainty reduction framework using Large Language Models (LLMs) to improve entity resolution results. LLMs capitalize on their advanced linguistic capabilities and a pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. We show that our method is efficient and effective, offering promising applications in real-world tasks.
arXiv Detail & Related papers (2024-01-07T09:06:58Z)
LLMRefine: Pinpointing and Refining Large Language Models via Fine-Grained Actionable Feedback [65.84061725174269]
Recent large language models (LLM) are leveraging human feedback to improve their generation quality. We propose LLMRefine, an inference time optimization method to refine LLM's output. We conduct experiments on three text generation tasks, including machine translation, long-form question answering (QA), and topical summarization. LLMRefine consistently outperforms all baseline approaches, achieving improvements up to 1.7 MetricX points on translation tasks, 8.1 ROUGE-L on ASQA, 2.2 ROUGE-L on topical summarization.
arXiv Detail & Related papers (2023-11-15T19:52:11Z)
Red Teaming Language Model Detectors with Language Models [114.36392560711022]
Large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. Recent works have proposed algorithms to detect LLM-generated text and protect LLMs. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation.
arXiv Detail & Related papers (2023-05-31T10:08:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.