Right Knowledge, Wrong Answer: Test-Time Steering for Temporal Fact Conflicts in Open-Weight Language Models

• URL: http://arxiv.org/abs/2606.20959v1
• Date: Thu, 18 Jun 2026 21:56:18 GMT
• Title: Right Knowledge, Wrong Answer: Test-Time Steering for Temporal Fact Conflicts in Open-Weight Language Models
• Abstract summary: Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdated answer.<n>We formalize this problem as Parametric Temporal Conflict (PTC) and introduce Temporal Attractor Steering (TAS)<n>TAS detects likely conflicts, identifies a conflict-critical layer, and steers hidden states toward newer-fact representations without retraining or external retrieval.
• Score: 2.11832654407998
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models can store both outdated facts and newer superseding facts in their parameters, but standard prompting may still elicit the outdated answer. We formalize this problem as Parametric Temporal Conflict (PTC) and introduce Temporal Attractor Steering (TAS), a three-stage test-time intervention that detects likely conflicts, identifies a conflict-critical layer, and steers hidden states toward newer-fact representations without retraining or external retrieval. We construct an 8,746-record verified benchmark across five Wikidata relations and evaluate four open-weight language models from three families: Qwen-2.5-1.5B/7B, Mistral-7B-v0.3, and Llama-3.1-8B. Single-layer activation patching achieves answer-flip rates of 0.72-0.85 across all models. End-to-end TAS resolves 29-57% of PTC cases while preserving 85-99% accuracy on non-conflict queries, outperforming a matched ITI baseline on three of four models. These results show that outdated parametric knowledge can be selectively overridden at inference time.

Related papers

• MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language Models [49.47300047353726]
  We introduce MemToC, a benchmark for post-tool-return arbitration with executable tools.<n>MemToC comprises 6,504 evaluation episodes constructed from 542 quality-controlled factual questions.<n>Across five open-weight 7-9B models, tool returns strongly dominate elicited closed-book answers.
  arXiv  Detail & Related papers  (2026-08-26T18:22:03Z)
• FADE: From Passive Verification to Active Discovery in Counterfactual Video Understanding [19.559643217912114]
  Existing multiple-choice question (MCQ) benchmarks inadvertently leak target events through their questions and candidate options.<n>We present FADE, an effective training framework for counterfactual discovery and explanation.<n>FADE achieves state-of-the-art strict paired scores across all three tasks on DualityVidQA-test and IPV-Bench, outperforming GPT-5.6.
  arXiv  Detail & Related papers  (2026-08-11T10:22:08Z)
• Large Language Model-Powered Query-Driven Event Timeline Summarization in Industrial Search [49.02761046363752]
  We present QDET (Query-Driven Event Timeline Summarization), a production system deployed on Baidu Search.<n>QDET identifies and organizes sub-events closely relevant to the query from noisy candidate sets formed by millions of documents retrieved daily.<n>Online A/B tests on Baidu Search validate real-world effectiveness, showing 5.5% CTR improvement, 4.6% longer dwell time, and 4.4% deeper exploration.
  arXiv  Detail & Related papers  (2026-05-26T14:16:27Z)
• Beyond Inference-Only Deployment: Comparing Weight-Based Consolidation Against Cascading Compaction [1.6214121783846343]
  We evaluate a nightly consolidation of interaction knowledge into model weights via synthesis, synthesis, and Low-Rank Adaptation (LoRA) fine-tuning on a single consumer.<n>Across ten realistic software development conversations, cascading compaction retain 36.8 +/- 3.0% of knowledge.<n>LoRA consolidates interaction knowledge into model weights via synthesis, synthesis, and Low-Rank Adaptation (LoRA) fine-tuning on a single consumer.
  arXiv  Detail & Related papers  (2026-05-23T16:57:25Z)
• PBT-Bench: Benchmarking AI Agents on Property-Based Testing [29.035258104995204]
  We introduce PBT-Bench, a benchmark of 100 curated property-based testing problems across 40 real Python libraries.<n>Each problem injects one or more semantic bugs (365 in total, mean 3.65 per problem) designed so that default-strategy random inputs almost never trigger them.<n>Bug recall under the PBT-guided prompt ranges from 42.1% to 83.4% across models; under the open-ended baseline, from 31.4% to 76.7%.
  arXiv  Detail & Related papers  (2026-05-13T18:01:05Z)
• Three Regimes of Context-Parametric Conflict: A Predictive Framework and Empirical Validation [0.0]
  We study how large language models handle conflict between their training knowledge and a contradicting document.<n>We propose a three-regime framework: Regime 1 (single-source updating), Regime 2 (competitive integration), and Regime 3 (task-appropriate selection)<n>We validate the framework across Claude Sonnet 4.6, GPT-5.5, Gemini 2.5 Flash, Llama 4 Maverick, and DeepSeek V3 using 9,970 API calls in three experimental phases.
  arXiv  Detail & Related papers  (2026-05-12T06:00:48Z)
• ClawArena: Benchmarking AI Agents in Evolving Information Environments [61.664633997138004]
  ClawArena is a benchmark for evaluating AI agents in evolving information environments.<n>Each scenario maintains a complete hidden ground truth while exposing the agent only to noisy, partial, and sometimes contradictory traces.<n> evaluation is organized around three coupled challenges: multi-source conflict reasoning, dynamic belief revision, and implicit personalization.
  arXiv  Detail & Related papers  (2026-04-05T17:55:23Z)
• OrgForge-IT: A Verifiable Synthetic Benchmark for LLM-Based Insider Threat Detection [0.0]
  We present a verifiable synthetic benchmark in which a deterministic simulation engine maintains ground truth and language models generate only surface prose.<n>The corpus spans 51 simulated days, 2,904 telemetry records at a 96.4% noise rate, and four detection scenarios designed to defeat single-surface and single-day triage strategies.
  arXiv  Detail & Related papers  (2026-03-23T19:03:53Z)
• AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge [57.66282463340297]
  Knowledge conflict arises from discrepancies between information in the context of a large language model and the knowledge stored in its parameters.<n>We propose a fine-grained, instance-level approach called AdaCAD, which dynamically infers the weight of adjustment based on the degree of conflict.<n>We show that ADACAD consistently outperforms other decoding baselines with average QA accuracy gains of 14.21% (absolute) over a static contrastive baseline, and improves the factuality of summaries by 6.19 (AlignScore)
  arXiv  Detail & Related papers  (2024-09-11T16:35:18Z)
• How Can We Know When Language Models Know? On the Calibration of Language Models for Question Answering [80.82194311274694]
  We examine the question "how can we know when language models know, with confidence, the answer to a particular query?" We examine three strong generative models -- T5, BART, and GPT-2 -- and study whether their probabilities on QA tasks are well calibrated. We then examine methods to calibrate such models to make their confidence scores correlate better with the likelihood of correctness.
  arXiv  Detail & Related papers  (2020-12-02T03:53:13Z)
• TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task [80.38130122127882]
  TACRED is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE) In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement? We find that label errors account for 8% absolute F1 test error, and that more than 50% of the examples need to be relabeled.
  arXiv  Detail & Related papers  (2020-04-30T15:07:37Z)

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.