On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots

• URL: http://arxiv.org/abs/2406.01633v1
• Date: Sat, 1 Jun 2024 15:54:45 GMT
• Title: On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
• Authors: Christine Herlihy, Jennifer Neville, Tobias Schnabel, Adith Swaminathan,
• Abstract summary: We study the use of Large Language Model (LLM)-based chatbots to power recommender systems. We observe that the chatbots respond poorly when they encounter under-specified requests. We conjecture that such miscalibrated response tendencies can be attributed to LLM fine-tuning using annotators.
• Score: 19.423566424346166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We explore the use of Large Language Model (LLM-based) chatbots to power recommender systems. We observe that the chatbots respond poorly when they encounter under-specified requests (e.g., they make incorrect assumptions, hedge with a long response, or refuse to answer). We conjecture that such miscalibrated response tendencies (i.e., conversational priors) can be attributed to LLM fine-tuning using annotators -- single-turn annotations may not capture multi-turn conversation utility, and the annotators' preferences may not even be representative of users interacting with a recommender system. We first analyze public LLM chat logs to conclude that query under-specification is common. Next, we study synthetic recommendation problems with configurable latent item utilities and frame them as Partially Observed Decision Processes (PODP). We find that pre-trained LLMs can be sub-optimal for PODPs and derive better policies that clarify under-specified queries when appropriate. Then, we re-calibrate LLMs by prompting them with learned control messages to approximate the improved policy. Finally, we show empirically that our lightweight learning approach effectively uses logged conversation data to re-calibrate the response strategies of LLM-based chatbots for recommendation tasks.

Related papers

• Modeling Future Conversation Turns to Teach LLMs to Ask Clarifying Questions [45.04582353648683]
  We propose to assign preference labels by simulating expected outcomes in the future turns. This allows LLMs to learn to ask clarifying questions when it can generate responses tailored to each user interpretation in future turns. We evaluate systems based on their ability to ask clarifying questions that can recover each user's interpretation and expected answer.
  arXiv  Detail & Related papers  (2024-10-17T17:29:04Z)
• Large Language Model Driven Recommendation [34.45328907249946]
  The advent of language-driven recommendation has unlocked the use of natural language (NL) interactions for recommendation. This chapter discusses how LLMs' abilities for general NL reasoning present novel opportunities to build highly personalized RSs.
  arXiv  Detail & Related papers  (2024-08-20T15:36:24Z)
• Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models [66.24055500785657]
  Traditional turn-based chat systems prevent users from verbally interacting with system while it is generating responses. To overcome these limitations, we adapt existing LLMs to listen users while generating output and provide users with instant feedback. We build a dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions.
  arXiv  Detail & Related papers  (2024-06-22T03:20:10Z)
• CHIQ: Contextual History Enhancement for Improving Query Rewriting in Conversational Search [67.6104548484555]
  We introduce CHIQ, a two-step method that leverages the capabilities of open-source large language models (LLMs) to resolve ambiguities in the conversation history before query rewriting. We demonstrate on five well-established benchmarks that CHIQ leads to state-of-the-art results across most settings.
  arXiv  Detail & Related papers  (2024-06-07T15:23:53Z)
• Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training [33.57497419019826]
  Action-Based Contrastive Self-Training allows for sample-efficient dialogue policy learning in multi-turn conversation. ACT demonstrates substantial conversation modeling improvements over standard approaches to supervised fine-tuning and DPO.
  arXiv  Detail & Related papers  (2024-05-31T22:44:48Z)
• Hidden in Plain Sight: Exploring Chat History Tampering in Interactive Language Models [12.920884182101142]
  Large Language Models (LLMs) have become prevalent in real-world applications, exhibiting impressive text generation performance. To behave interactively, LLM-based chat systems must integrate prior chat history as context into their inputs, following a pre-defined structure. This paper introduces a systematic methodology to inject user-supplied history into LLM conversations without any prior knowledge of the target model.
  arXiv  Detail & Related papers  (2024-05-30T16:36:47Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• Rethinking the Evaluation for Conversational Recommendation in the Era of Large Language Models [115.7508325840751]
  The recent success of large language models (LLMs) has shown great potential to develop more powerful conversational recommender systems (CRSs) In this paper, we embark on an investigation into the utilization of ChatGPT for conversational recommendation, revealing the inadequacy of the existing evaluation protocol. We propose an interactive Evaluation approach based on LLMs named iEvaLM that harnesses LLM-based user simulators.
  arXiv  Detail & Related papers  (2023-05-22T15:12:43Z)
• PALR: Personalization Aware LLMs for Recommendation [7.407353565043918]
  PALR aims to combine user history behaviors (such as clicks, purchases, ratings, etc.) with large language models (LLMs) to generate user preferred items. Our solution outperforms state-of-the-art models on various sequential recommendation tasks.
  arXiv  Detail & Related papers  (2023-05-12T17:21:33Z)
• Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback [127.75419038610455]
  Large language models (LLMs) are able to generate human-like, fluent responses for many downstream tasks. This paper proposes a LLM-Augmenter system, which augments a black-box LLM with a set of plug-and-play modules.
  arXiv  Detail & Related papers  (2023-02-24T18:48:43Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.