FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs

• URL: http://arxiv.org/abs/2410.19317v1
• Date: Fri, 25 Oct 2024 06:06:31 GMT
• Title: FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs
• Authors: Zhiting Fan, Ruizhe Chen, Tianxiang Hu, Zuozhu Liu,
• Abstract summary: We propose a fairness benchmark for large language model (LLM)-based chatbots in multi-turn dialogue scenarios, textbfFairMT-Bench. To ensure coverage of diverse bias types and attributes, we employ our template to construct a multi-turn dialogue dataset, textttFairMT-10K. Experiments and analyses on textttFairMT-10K reveal that in multi-turn dialogue scenarios, current LLMs are more likely to generate biased responses, and there is significant variation in performance across different tasks and models.
• Score: 8.37667737406383
• License:
• Abstract: The growing use of large language model (LLM)-based chatbots has raised concerns about fairness. Fairness issues in LLMs can lead to severe consequences, such as bias amplification, discrimination, and harm to marginalized communities. While existing fairness benchmarks mainly focus on single-turn dialogues, multi-turn scenarios, which in fact better reflect real-world conversations, present greater challenges due to conversational complexity and potential bias accumulation. In this paper, we propose a comprehensive fairness benchmark for LLMs in multi-turn dialogue scenarios, \textbf{FairMT-Bench}. Specifically, we formulate a task taxonomy targeting LLM fairness capabilities across three stages: context understanding, user interaction, and instruction trade-offs, with each stage comprising two tasks. To ensure coverage of diverse bias types and attributes, we draw from existing fairness datasets and employ our template to construct a multi-turn dialogue dataset, \texttt{FairMT-10K}. For evaluation, GPT-4 is applied, alongside bias classifiers including Llama-Guard-3 and human validation to ensure robustness. Experiments and analyses on \texttt{FairMT-10K} reveal that in multi-turn dialogue scenarios, current LLMs are more likely to generate biased responses, and there is significant variation in performance across different tasks and models. Based on this, we curate a challenging dataset, \texttt{FairMT-1K}, and test 15 current state-of-the-art (SOTA) LLMs on this dataset. The results show the current state of fairness in LLMs and showcase the utility of this novel approach for assessing fairness in more realistic multi-turn dialogue contexts, calling for future work to focus on LLM fairness improvement and the adoption of \texttt{FairMT-1K} in such efforts.

Related papers

• Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement [51.601916604301685]
  Large language models (LLMs) generate content that can undermine trust in online discourse. Current methods often focus on binary classification, failing to address the complexities of real-world scenarios like human-AI collaboration. To move beyond binary classification and address these challenges, we propose a new paradigm for detecting LLM-generated content.
  arXiv  Detail & Related papers  (2024-10-18T08:14:10Z)
• MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs [61.56904387052982]
  This paper proposes a new visual grounding task called multi-context visual grounding. It aims to localize instances of interest across multiple images based on open-ended text prompts. We benchmark over 20 state-of-the-art MLLMs and foundation models with potential multi-context visual grounding capabilities.
  arXiv  Detail & Related papers  (2024-10-16T07:52:57Z)
• Fairness in Large Language Models in Three Hours [2.443957114877221]
  This tutorial provides a systematic overview of recent advances in the literature concerning large language models. The concept of fairness in LLMs is then explored, summarizing the strategies for evaluating bias and the algorithms designed to promote fairness.
  arXiv  Detail & Related papers  (2024-08-02T03:44:14Z)
• Evaluating Fairness in Large Vision-Language Models Across Diverse Demographic Attributes and Prompts [27.66626125248612]
  We empirically investigate visual fairness in several mainstream large vision-language models (LVLMs) Our fairness evaluation framework employs direct and single-choice question prompt on visual question-answering/classification tasks. We propose a potential multi-modal Chain-of-thought (CoT) based strategy for bias mitigation, applicable to both open-source and closed-source LVLMs.
  arXiv  Detail & Related papers  (2024-06-25T23:11:39Z)
• MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions [58.57255822646756]
  This paper introduces MathChat, a benchmark designed to evaluate large language models (LLMs) across a broader spectrum of mathematical tasks. We evaluate the performance of various SOTA LLMs on the MathChat benchmark, and we observe that while these models excel in single turn question answering, they significantly underperform in more complex scenarios. We develop MathChat sync, a synthetic dialogue based math dataset for LLM finetuning, focusing on improving models' interaction and instruction following capabilities in conversations.
  arXiv  Detail & Related papers  (2024-05-29T18:45:55Z)
• MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues [58.33076950775072]
  MT-Bench-101 is designed to evaluate the fine-grained abilities of Large Language Models (LLMs) in multi-turn dialogues. We construct a three-tier hierarchical ability taxonomy comprising 4208 turns across 1388 multi-turn dialogues in 13 distinct tasks. We then evaluate 21 popular LLMs based on MT-Bench-101, conducting comprehensive analyses from both ability and task perspectives.
  arXiv  Detail & Related papers  (2024-02-22T18:21:59Z)
• Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One [43.37522760105383]
  We develop FairThinking, a pipeline designed to automatically generate roles that enable LLMs to articulate diverse perspectives for fair expressions. To evaluate FairThinking, we create a dataset with a thousand items covering three fairness-related topics and conduct experiments on GPT-3.5, GPT-4, Llama2, and Mistral.
  arXiv  Detail & Related papers  (2024-02-19T14:02:22Z)
• A Group Fairness Lens for Large Language Models [34.0579082699443]
  Large language models can perpetuate biases and unfairness when deployed in social media contexts. We propose evaluating LLM biases from a group fairness lens using a novel hierarchical schema characterizing diverse social groups. We pioneer a novel chain-of-thought method GF-Think to mitigate biases of LLMs from a group fairness perspective.
  arXiv  Detail & Related papers  (2023-12-24T13:25:15Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics [32.123919380959485]
  Multi-modal large language models (MLLMs) are trained based on large language models (LLM) While they excel in multi-modal tasks, the pure NLP abilities of MLLMs are often underestimated and left untested. We show that visual instruction tuning, a prevailing strategy for transitioning LLMs into MLLMs, unexpectedly and interestingly helps models attain both improved truthfulness and ethical alignment.
  arXiv  Detail & Related papers  (2023-09-13T17:57:21Z)
• Cue-CoT: Chain-of-thought Prompting for Responding to In-depth Dialogue Questions with LLMs [59.74002011562726]
  We propose a novel linguistic cue-based chain-of-thoughts (textitCue-CoT) to provide a more personalized and engaging response. We build a benchmark with in-depth dialogue questions, consisting of 6 datasets in both Chinese and English. Empirical results demonstrate our proposed textitCue-CoT method outperforms standard prompting methods in terms of both textithelpfulness and textitacceptability on all datasets.
  arXiv  Detail & Related papers  (2023-05-19T16:27:43Z)

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.