On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models

• URL: http://arxiv.org/abs/2311.07692v2
• Date: Sat, 25 Jan 2025 20:16:16 GMT
• Title: On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models
• Authors: Naman Goel,
• Abstract summary: We show that the surprisingly likely responses of large language models are more accurate in many cases compared to standard baselines.<n>For example, we observe up to 24 percentage points aggregate improvement on TruthfulQA.<n>We also provide further analysis of the results, including the cases when surprisingly likely responses are less or not more accurate.
• Score: 5.252280724532548
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The principle of rewarding a crowd for surprisingly common answers has been used in the literature for designing a number of truthful information elicitation mechanisms. A related method has also been proposed in the literature for better aggregation of crowd wisdom. Drawing a comparison between crowd based collective intelligence systems and large language models, we define the notion of 'surprisingly likely' textual response of a large language model. This notion is inspired by the surprisingly common principle, but tailored for text in a language model. Using benchmarks such as TruthfulQA and openly available LLMs: GPT-2 and LLaMA-2, we show that the surprisingly likely textual responses of large language models are more accurate in many cases compared to standard baselines. For example, we observe up to 24 percentage points aggregate improvement on TruthfulQA and up to 70 percentage points improvement on individual categories of questions in this benchmark. We also provide further analysis of the results, including the cases when surprisingly likely responses are less or not more accurate.

Related papers

• Evaluating Large Language Model with Knowledge Oriented Language Specific Simple Question Answering [73.73820209993515]
  We introduce KoLasSimpleQA, the first benchmark evaluating the multilingual factual ability of Large Language Models (LLMs)<n>Inspired by existing research, we created the question set with features such as single knowledge point coverage, absolute objectivity, unique answers, and temporal stability.<n>Results show significant performance differences between the two domains.
  arXiv  Detail & Related papers  (2025-05-22T12:27:02Z)
• Addressing Uncertainty in LLMs to Enhance Reliability in Generative AI [47.64301863399763]
  We present a dynamic semantic clustering approach inspired by the Chinese Restaurant Process. We quantify uncertainty of Large Language Models (LLMs) on a given query by calculating entropy of the generated semantic clusters. We propose leveraging the (negative) likelihood of these clusters as the (non)conformity score within Conformal Prediction framework.
  arXiv  Detail & Related papers  (2024-11-04T18:49:46Z)
• Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge [84.34545223897578]
  Despite their excellence in many domains, potential issues are under-explored, undermining their reliability and the scope of their utility. We identify 12 key potential biases and propose a new automated bias quantification framework-CALM- which quantifies and analyzes each type of bias in LLM-as-a-Judge. Our work highlights the need for stakeholders to address these issues and remind users to exercise caution in LLM-as-a-Judge applications.
  arXiv  Detail & Related papers  (2024-10-03T17:53:30Z)
• MACAROON: Training Vision-Language Models To Be Your Engaged Partners [95.32771929749514]
  Large vision-language models (LVLMs) generate detailed responses even when questions are ambiguous or unlabeled. In this study, we aim to shift LVLMs from passive answer providers to proactive engaged partners. We introduce MACAROON, self-iMaginAtion for ContrAstive pReference OptimizatiON, which instructs LVLMs to autonomously generate contrastive response pairs for unlabeled questions.
  arXiv  Detail & Related papers  (2024-06-20T09:27:33Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• Language Models can Evaluate Themselves via Probability Discrepancy [38.54454263880133]
  We propose a new self-evaluation method ProbDiff for assessing the efficacy of various Large Language Models (LLMs) It uniquely utilizes the LLMs being tested to compute the probability discrepancy between the initial response and its revised versions. Our findings reveal that ProbDiff achieves results on par with those obtained from evaluations based on GPT-4.
  arXiv  Detail & Related papers  (2024-05-17T03:50:28Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• Evaluating the Elementary Multilingual Capabilities of Large Language Models with MultiQ [16.637598165238934]
  Large language models (LLMs) need to serve everyone, including a global majority of non-English speakers. Recent research shows that, despite limits in their intended use, people prompt LLMs in many different languages. We introduce MultiQ, a new silver standard benchmark for basic open-ended question answering with 27.4k test questions.
  arXiv  Detail & Related papers  (2024-03-06T16:01:44Z)
• Exploring Value Biases: How LLMs Deviate Towards the Ideal [57.99044181599786]
  Large-Language-Models (LLMs) are deployed in a wide range of applications, and their response has an increasing social impact. We show that value bias is strong in LLMs across different categories, similar to the results found in human studies.
  arXiv  Detail & Related papers  (2024-02-16T18:28:43Z)
• PiCO: Peer Review in LLMs based on the Consistency Optimization [19.130941716491716]
  We use peer-review mechanisms to measure large language models (LLMs) automatically. We formalize it as a constrained optimization problem, intending to maximize the consistency of each LLM's capabilities and scores. We propose three metrics called PEN, CIN, and LIS to evaluate the gap in aligning human rankings.
  arXiv  Detail & Related papers  (2024-02-02T18:49:26Z)
• Self-Evaluation Improves Selective Generation in Large Language Models [54.003992911447696]
  We reformulate open-ended generation tasks into token-level prediction tasks. We instruct an LLM to self-evaluate its answers. We benchmark a range of scoring methods based on self-evaluation.
  arXiv  Detail & Related papers  (2023-12-14T19:09:22Z)
• Fine-tuning Language Models for Factuality [96.5203774943198]
  Large pre-trained language models (LLMs) have led to their widespread use, sometimes even as a replacement for traditional search engines. Yet language models are prone to making convincing but factually inaccurate claims, often referred to as 'hallucinations' In this work, we fine-tune language models to be more factual, without human labeling.
  arXiv  Detail & Related papers  (2023-11-14T18:59:15Z)
• Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs [56.526095828316386]
  We propose a novel framework for adaptation with self-evaluation to improve the selective prediction performance of large language models (LLMs) We evaluate our method on a variety of question-answering (QA) datasets and show that it outperforms state-of-the-art selective prediction methods.
  arXiv  Detail & Related papers  (2023-10-18T03:34:59Z)
• SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning [44.53966523376327]
  SeaEval is a benchmark for multilingual foundation models. We characterize how these models understand and reason with natural language. We also investigate how well they comprehend cultural practices, nuances, and values.
  arXiv  Detail & Related papers  (2023-09-09T11:42:22Z)
• Getting MoRE out of Mixture of Language Model Reasoning Experts [71.61176122960464]
  We propose a Mixture-of-Reasoning-Experts (MoRE) framework that ensembles diverse specialized language models. We specialize the backbone language model with prompts optimized for different reasoning categories, including factual, multihop, mathematical, and commonsense reasoning. Our human study confirms that presenting expert predictions and the answer selection process helps annotators more accurately calibrate when to trust the system's output.
  arXiv  Detail & Related papers  (2023-05-24T02:00:51Z)
• Evaluating and Modeling Attribution for Cross-Lingual Question Answering [80.4807682093432]
  This work is the first to study attribution for cross-lingual question answering. We collect data in 5 languages to assess the attribution level of a state-of-the-art cross-lingual QA system. We find that a substantial portion of the answers is not attributable to any retrieved passages.
  arXiv  Detail & Related papers  (2023-05-23T17:57:46Z)
• Evaluating statistical language models as pragmatic reasoners [39.72348730045737]
  We evaluate the capacity of large language models to infer meanings of pragmatic utterances. We find that LLMs can derive context-grounded, human-like distributions over the interpretations of several complex pragmatic utterances. Results inform the inferential capacity of statistical language models, and their use in pragmatic and semantic parsing applications.
  arXiv  Detail & Related papers  (2023-05-01T18:22:10Z)
• Query Expansion Using Contextual Clue Sampling with Language Models [69.51976926838232]
  We propose a combination of an effective filtering strategy and fusion of the retrieved documents based on the generation probability of each context. Our lexical matching based approach achieves a similar top-5/top-20 retrieval accuracy and higher top-100 accuracy compared with the well-established dense retrieval model DPR. For end-to-end QA, the reader model also benefits from our method and achieves the highest Exact-Match score against several competitive baselines.
  arXiv  Detail & Related papers  (2022-10-13T15:18:04Z)
• Sentiment analysis in tweets: an assessment study from classical to modern text representation models [59.107260266206445]
  Short texts published on Twitter have earned significant attention as a rich source of information. Their inherent characteristics, such as the informal, and noisy linguistic style, remain challenging to many natural language processing (NLP) tasks. This study fulfils an assessment of existing language models in distinguishing the sentiment expressed in tweets by using a rich collection of 22 datasets.
  arXiv  Detail & Related papers  (2021-05-29T21:05:28Z)

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.