{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JRB3HBUHNOZLCXTTRLV2SAAGC2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2a60db4c6a1626655b06492fbf0f40fc7fbce999914a19ca7098442e92e4afe0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T06:20:12Z","title_canon_sha256":"346144391ac46b8d013245e4cf4e63c0e66c048701ed8ca8241d8e1a9d44599b"},"schema_version":"1.0","source":{"id":"2406.01026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01026","created_at":"2026-07-05T08:28:11Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01026v2","created_at":"2026-07-05T08:28:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01026","created_at":"2026-07-05T08:28:11Z"},{"alias_kind":"pith_short_12","alias_value":"JRB3HBUHNOZL","created_at":"2026-07-05T08:28:11Z"},{"alias_kind":"pith_short_16","alias_value":"JRB3HBUHNOZLCXTT","created_at":"2026-07-05T08:28:11Z"},{"alias_kind":"pith_short_8","alias_value":"JRB3HBUH","created_at":"2026-07-05T08:28:11Z"}],"graph_snapshots":[{"event_id":"sha256:7cf4877c7489ec350b424cf8d5f52a61df2dbe84493ccb5f333564dc70e56fd3","target":"graph","created_at":"2026-07-05T08:28:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.01026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multiple-Choice Questions (MCQs) constitute a critical area of research in the study of Large Language Models (LLMs). Previous works have investigated the selection bias problem in MCQs within few-shot scenarios, in which the LLM's performance may be influenced by the presentation of answer choices, leaving the selection bias during Supervised Fine-Tuning (SFT) unexplored. In this paper, we reveal that selection bias persists in the SFT phase , primarily due to the LLM's inadequate Multiple Choice Symbol Binding (MCSB) ability. This limitation implies that the model struggles to associate the ","authors_text":"Chengguo Yin, Honglin Han, Kuo Liao, Liqun Liu, Mengge Xue, Meng Zhao, Shuang Li, Zhenyu Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T06:20:12Z","title":"Strengthened Symbol Binding Makes Large Language Models Reliable Multiple-Choice Selectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01026","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3e0969dc497f8cc85cae4c57dfac6efe38ba9432443915d35bbbfe2b807d7d75","target":"record","created_at":"2026-07-05T08:28:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2a60db4c6a1626655b06492fbf0f40fc7fbce999914a19ca7098442e92e4afe0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T06:20:12Z","title_canon_sha256":"346144391ac46b8d013245e4cf4e63c0e66c048701ed8ca8241d8e1a9d44599b"},"schema_version":"1.0","source":{"id":"2406.01026","kind":"arxiv","version":2}},"canonical_sha256":"4c43b386876bb2b15e738aeba9000616a5da539faac33b106c3313865090563f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c43b386876bb2b15e738aeba9000616a5da539faac33b106c3313865090563f","first_computed_at":"2026-07-05T08:28:11.031433Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:11.031433Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wxg2RyPPv19QrGWywKZDIzZ1YmLjKZLhI4lXHqGxDkVwSzujN/QrY+1oCvPlUSczoEef1hChRn3jXTxYuyhvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:11.031931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e0969dc497f8cc85cae4c57dfac6efe38ba9432443915d35bbbfe2b807d7d75","sha256:7cf4877c7489ec350b424cf8d5f52a61df2dbe84493ccb5f333564dc70e56fd3"],"state_sha256":"e9d693d2b816630f0c5a9f66dc2a0ec00e9a537a8cc5920456e5dc83f3b443ac"}